Computer vision - Knowledge

1111: 1002:. There is a significant overlap in the range of techniques and applications that these cover. This implies that the basic techniques that are used and developed in these fields are similar, something which can be interpreted as there is only one field with different names. On the other hand, it appears to be necessary for research groups, scientific journals, conferences, and companies to present or market themselves as belonging specifically to one of these fields and, hence, various characterizations which distinguish each of the fields from the others have been presented. In image processing, the input is an image and the output is an image as well, whereas in computer vision, an image or a video is taken as an input and the output could be an enhanced image, an understanding of the content of an image or even behavior of a computer system based on such understanding. 1407:

finger mold and sensors could then be placed on top of a small sheet of rubber containing an array of rubber pins. A user can then wear the finger mold and trace a surface. A computer can then read the data from the strain gauges and measure if one or more of the pins are being pushed upward. If a pin is being pushed upward then the computer can recognize this as an imperfection in the surface. This sort of technology is useful in order to receive accurate data on imperfections on a very large surface. Another variation of this finger mold sensor are sensors that contain a camera suspended in silicon. The silicon forms a dome around the outside of the camera and embedded in the silicon are point markers that are equally spaced. These cameras can then be placed on devices such as robotic hands in order to allow the computer to receive highly accurate tactile data.

1532:; this is a benchmark in object classification and detection, with millions of images and 1000 object classes used in the competition. Performance of convolutional neural networks on the ImageNet tests is now close to that of humans. The best algorithms still struggle with objects that are small or thin, such as a small ant on the stem of a flower or a person holding a quill in their hand. They also have trouble with images that have been distorted with filters (an increasingly common phenomenon with modern digital cameras). By contrast, those kinds of images rarely trouble humans. Humans, however, tend to have trouble with other issues. For example, they are not good at classifying objects into fine-grained classes, such as the particular breed of dog or species of bird, whereas convolutional neural networks handle this with ease. 1713:

be extracted from them also gets damaged. Therefore, we need to recover or restore the image as it was intended to be. The aim of image restoration is the removal of noise (sensor noise, motion blur, etc.) from images. The simplest possible approach for noise removal is various types of filters, such as low-pass filters or median filters. More sophisticated methods assume a model of how the local image structures look to distinguish them from noise. By first analyzing the image data in terms of the local image structures, such as lines or edges, and then controlling the filtering based on local information from the analysis step, a better level of noise removal is usually obtained compared to the simpler approaches.

681: 47: 1930: 826:—indeed, just as many strands of AI research are closely tied with research into human intelligence and the use of stored knowledge to interpret, integrate, and utilize visual information. The field of biological vision studies and models the physiological processes behind visual perception in humans and other animals. Computer vision, on the other hand, develops and describes the algorithms implemented in software and hardware behind artificial vision systems. An interdisciplinary exchange between biological and computer vision has proven fruitful for both fields. 1311:. More advanced systems for missile guidance send the missile to an area rather than a specific target, and target selection is made when the missile reaches the area based on locally acquired image data. Modern military concepts, such as "battlefield awareness", imply that various sensors, including image sensors, provide a rich set of information about a combat scene that can be used to support strategic decisions. In this case, automatic processing of the data is used to reduce complexity and to fuse information from multiple sensors to increase reliability. 749: 1320: 1520: – the image data are scanned for specific objects along with their locations. Examples include the detection of an obstacle in the car's field of view and possible abnormal cells or tissues in medical images or the detection of a vehicle in an automatic road toll system. Detection based on relatively simple and fast computations is sometimes used for finding smaller regions of interesting image data which can be further analyzed by more computationally demanding techniques to produce a correct interpretation. 773: 838:. Many methods for processing one-variable signals, typically temporal signals, can be extended in a natural way to the processing of two-variable signals or multi-variable signals in computer vision. However, because of the specific nature of images, there are many methods developed within computer vision that have no counterpart in the processing of one-variable signals. Together with the multi-dimensionality of the signal, this defines a subfield in signal processing as a part of computer vision. 1553: 1107:

automated image analysis which is used in many fields. Machine vision usually refers to a process of combining automated image analysis with other methods and technologies to provide automated inspection and robot guidance in industrial applications. In many computer-vision applications, computers are pre-programmed to solve a particular task, but methods based on learning are now becoming increasingly common. Examples of applications of computer vision include systems for:

1056:). This implies that image sensor technologies and control theory often are integrated with the processing of image data to control a robot and that real-time processing is emphasized by means of efficient implementations in hardware and software. It also implies that external conditions such as lighting can be and are often more controlled in machine vision than they are in general computer vision, which can enable the use of different algorithms. 1473:, in the forms of decisions. Understanding in this context means the transformation of visual images (the input of the retina) into descriptions of the world that can interface with other thought processes and elicit appropriate action. This image understanding can be seen as the disentangling of symbolic information from image data using models constructed with the aid of geometry, physics, statistics, and learning theory. 1744:, tomography devices, radar, ultra-sonic cameras, etc. Depending on the type of sensor, the resulting image data is an ordinary 2D image, a 3D volume, or an image sequence. The pixel values typically correspond to light intensity in one or several spectral bands (gray images or colour images) but can also be related to various physical measures, such as depth, absorption or reflectance of sonic or electromagnetic waves, or 982:. Finally, a significant part of the field is devoted to the implementation aspect of computer vision; how existing methods can be realized in various combinations of software and hardware, or how these methods can be modified in order to gain processing speed without losing too much performance. Computer vision is also used in fashion eCommerce, inventory management, patent search, furniture, and the beauty industry. 5922: 5902: 1729:

mechanical actuators, planning, information databases, man-machine interfaces, etc. The specific implementation of a computer vision system also depends on whether its functionality is pre-specified or if some part of it can be learned or modified during operation. Many functions are unique to the application. There are, however, typical functions that are found in many computer vision systems.

672:-based methods used in conjunction with machine learning techniques and complex optimization frameworks. The advancement of Deep Learning techniques has brought further life to the field of computer vision. The accuracy of deep learning algorithms on several benchmark computer vision data sets for tasks ranging from classification, segmentation and optical flow has surpassed prior methods. 1398: 1390: 796:

how natural vision systems operate in order to solve certain vision-related tasks. These results have led to a sub-field within computer vision where artificial systems are designed to mimic the processing and behavior of biological systems at different levels of complexity. Also, some of the learning-based methods developed within computer vision (

1946:

vision system contains software, as well as a display in order to monitor the system. Vision systems for inner spaces, as most industrial ones, contain an illumination system and may be placed in a controlled environment. Furthermore, a completed system includes many accessories, such as camera supports, cables, and connectors.

1239: 1034:, by pixel-wise operations such as contrast enhancement, local operations such as edge extraction or noise removal, or geometrical transformations such as rotating the image. This characterization implies that image processing/analysis neither requires assumptions nor produces interpretations about the image content. 1345:). The level of autonomy ranges from fully autonomous (unmanned) vehicles to vehicles where computer-vision-based systems support a driver or a pilot in various situations. Fully autonomous vehicles typically use computer vision for navigation, e.g., for knowing where they are or mapping their environment ( 1945:

There are many kinds of computer vision systems; however, all of them contain these basic elements: a power source, at least one image acquisition device (camera, ccd, etc.), a processor, and control and communication cables or some kind of wireless interconnection mechanism. In addition, a practical

778:

Subsequent run of the network on an input image (left): The network correctly detects the starfish. However, the weakly weighted association between ringed texture and sea urchin also confers a weak signal to the latter from one of two intermediate nodes. In addition, a shell that was not included in

1703:

of the scene. In the simplest case, the model can be a set of 3D points. More sophisticated methods produce a complete 3D surface model. The advent of 3D imaging not requiring motion or scanning, and related processing algorithms is enabling rapid advances in this field. Grid-based 3D sensing can be

795:

has greatly influenced the development of computer vision algorithms. Over the last century, there has been an extensive study of eyes, neurons, and brain structures devoted to the processing of visual stimuli in both humans and various animals. This has led to a coarse yet convoluted description of

1712:

Image restoration comes into the picture when the original image is degraded or damaged due to some external factors like lens wrong positioning, transmission interference, low lighting or motion blurs, etc., which is referred to as noise. When the images are degraded or damaged, the information to

1406:

Materials such as rubber and silicon are being used to create sensors that allow for applications such as detecting microundulations and calibrating robotic hands. Rubber can be used in order to create a mold that can be placed over a finger, inside of this mold would be multiple strain gauges. The

446:

of computer vision is concerned with the theory behind artificial systems that extract information from images. The image data can take many forms, such as video sequences, views from multiple cameras, multi-dimensional data from a 3D scanner, 3D point clouds from LiDaR sensors, or medical scanning

3027:

Convolutional neural networks (CNNs) represent deep learning architectures that are currently used in a wide range of applications, including computer vision, speech recognition, identification of albuminous sequences in bioinformatics, production control, time series analysis in finance, and many

438:

in the human analog) into descriptions of the world that make sense to thought processes and can elicit appropriate action. This image understanding can be seen as the disentangling of symbolic information from image data using models constructed with the aid of geometry, physics, statistics, and

1920:

While inference refers to the process of deriving new, not explicitly represented facts from currently known facts, control refers to the process that selects which of the many inference, search, and matching techniques should be applied at a particular stage of processing. Inference and control

1995:

has made high-speed image acquisition, processing, and display possible for real-time systems on the order of hundreds to thousands of frames per second. For applications in robotics, fast, real-time video systems are critically important and often can simplify the processing needed for certain

1106:

systems which, say, inspect bottles speeding by on a production line, to research into artificial intelligence and computers or robots that can comprehend the world around them. The computer vision and machine vision fields have significant overlap. Computer vision covers the core technology of

1401:

Above is a silicon mold with a camera inside containing many different point markers. When this sensor is pressed against the surface, the silicon deforms, and the position of the point markers shifts. A computer can then take this data and determine how exactly the mold is pressed against the

1728:

The organization of a computer vision system is highly application-dependent. Some systems are stand-alone applications that solve a specific measurement or detection problem, while others constitute a sub-system of a larger design which, for example, also contains sub-systems for control of

1912:

Image-understanding systems (IUS) include three levels of abstraction as follows: low level includes image primitives such as edges, texture elements, or regions; intermediate level includes boundaries, surfaces and volumes; and high level includes objects, scenes, or events. Many of these

1294:

from coming to market in an unusable manner. Another example is a measurement of the position and orientation of details to be picked up by a robot arm. Machine vision is also heavily used in the agricultural processes to remove undesirable foodstuff from bulk material, a process called

522:

can do. "Computer vision is concerned with the automatic extraction, analysis, and understanding of useful information from a single image or a sequence of images. It involves the development of a theoretical and algorithmic basis to achieve automatic visual understanding." As a

1449:

Each of the application areas described above employ a range of computer vision tasks; more or less well-defined measurement problems or processing problems, which can be solved using a variety of methods. Some examples of typical computer vision tasks are presented below.

493:

Adopting computer vision technology might be painstaking for organizations as there is no single-point solution for it. Very few companies provide a unified and distributed platform or Operating System where computer vision applications can be easily deployed and managed.

1286:, where information is extracted for the purpose of supporting a production process. One example is quality control where details or final products are being automatically inspected in order to find defects. One of the most prevalent fields for such inspection is the 857:. A detailed understanding of these environments is required to navigate through them. Information about the environment could be provided by a computer vision system, acting as a vision sensor and providing high-level information about the environment and the robot 1274:, about the structure of the brain or the quality of medical treatments. Applications of computer vision in the medical area also include enhancement of images interpreted by humans—ultrasonic images or X-ray images, for example—to reduce the influence of noise. 1754:– Before a computer vision method can be applied to image data in order to extract some specific piece of information, it is usually necessary to process the data in order to ensure that it satisfies certain assumptions implied by the method. Examples are: 1544: – finding all images in a larger set of images which have a specific content. The content can be specified in different ways, for example in terms of similarity relative to a target image (give me all images similar to image X) by utilizing 1067:

includes substantial work on the analysis of image data in medical applications. Progress in convolutional neural networks (CNNs) has improved the accurate detection of disease in medical images, particularly in cardiology, pathology, dermatology, and

1656:

Several tasks relate to motion estimation, where an image sequence is processed to produce an estimate of the velocity either at each points in the image or in the 3D scene or even of the camera that produces the images. Examples of such tasks are:

1353:, a UAV looking for forest fires. Examples of supporting systems are obstacle warning systems in cars, cameras and LiDAR sensors in vehicles, and systems for autonomous landing of aircraft. Several car manufacturers have demonstrated systems for 1047:

is the process of applying a range of technologies and methods to provide imaging-based automatic inspection, process control, and robot guidance in industrial applications. Machine vision tends to focus on applications, mainly in manufacturing,

1916:

The representational requirements in the designing of IUS for these levels are: representation of prototypical concepts, concept organization, spatial knowledge, temporal knowledge, scaling, and description by comparison and differentiation.

1243: 1240: 766:. The starfish match with a ringed texture and a star outline, whereas most sea urchins match with a striped texture and oval shape. However, the instance of a ring-textured sea urchin creates a weakly weighted association between them. 551:

as a stepping stone to endowing robots with intelligent behavior. In 1966, it was believed that this could be achieved through an undergraduate summer project, by attaching a camera to a computer and having it "describe what it saw".

527:, computer vision is concerned with the theory behind artificial systems that extract information from images. The image data can take many forms, such as video sequences, views from multiple cameras, or multi-dimensional data from a 1921:

requirements for IUS are: search and hypothesis activation, matching and hypothesis testing, generation and use of expectations, change and focus of attention, certainty and strength of belief, inference and goal satisfaction.

1357:. There are ample examples of military autonomous vehicles ranging from advanced missiles to UAVs for recon missions or missile guidance. Space exploration is already being made with autonomous vehicles using computer vision, 1570: – estimating the position or orientation of a specific object relative to the camera. An example application for this technique would be assisting a robot arm in retrieving objects from a conveyor belt in an 3919: 1242: 3000:

Chervyakov, N. I.; Lyakhov, P. A.; Deryabin, M. A.; Nagornov, N. N.; Valueva, M. V.; Valuev, G. V. (2020). "Residue Number System-Based Solution for Reducing the Hardware Cost of a Convolutional Neural Network".

969:

Besides the above-mentioned views on computer vision, many of the related research topics can also be studied from a purely mathematical point of view. For example, many methods in computer vision are based on

1866:– At this step, the input is typically a small set of data, for example, a set of points or an image region, which is assumed to contain a specific object. The remaining processing deals with, for example: 3780: 433:

data from the real world in order to produce numerical or symbolic information, e.g. in the forms of decisions. Understanding in this context means the transformation of visual images (the input to the

1041:, how to reconstruct structure or other information about the 3D scene from one or several images. Computer vision often relies on more or less complex assumptions about the scene depicted in an image. 1270:

or other malign changes, and a variety of dental pathologies; measurements of organ dimensions, blood flow, etc. are another example. It also supports medical research by providing new information:

535:

refers to a systems engineering discipline, especially in the context of factory automation. In more recent times, the terms computer vision and machine vision have converged to a greater degree.

1110: 1498:) – one or several pre-specified or learned objects or object classes can be recognized, usually together with their 2D positions in the image or 3D poses in the scene. Blippar, 5796: 3573:

Russakovsky, Olga; Deng, Jia; Su, Hao; Krause, Jonathan; Satheesh, Sanjeev; Ma, Sean; Huang, Zhiheng; Karpathy, Andrej; Khosla, Aditya; Bernstein, Michael; Berg, Alexander C. (December 2015).

735:

to provide a complete understanding of the image formation process. Also, various measurement problems in physics can be addressed using computer vision, for example, motion in fluids.

2847:

Soltani, A. A.; Huang, H.; Wu, J.; Kulkarni, T. D.; Tenenbaum, J. B. (2017). "Synthesizing 3D Shapes via Modeling Multi-view Depth Maps and Silhouettes with Deep Generative Networks".

2360: 1485:

is that of determining whether or not the image data contains some specific object, feature, or activity. Different varieties of recognition problem are described in the literature.

1614:

a technology that enables the matching of faces in digital images or video frames to a face database, which is now widely used for mobile phone facelock, smart door locking, etc.

306: 3860: 936:

and visualization, surveying, multimedia systems, virtual heritage, special effects in movies and television, and ultimately computer games, for which conclusively centers in

4671: 4578: 5638: 5044: 1548:

techniques, or in terms of high-level search criteria given as text input (give me all images which contain many houses, are taken during winter and have no cars in them).

1241: 397: 2795: 4701: 4623: 4598:

Widely adopted open-source container for GPU accelerated computer vision applications. Used by researchers, universities, private companies, as well as the U.S. Gov't.

1678:, vehicles, objects, humans or other organisms) in the image sequence. This has vast industry applications as most high-running machinery can be monitored in this way. 1008:

produces image data from 3D models, and computer vision often produces 3D models from image data. There is also a trend towards a combination of the two disciplines,

4011: 4995: 4696: 1160: 3835: 1690:, its apparent motion. This motion is a result of both how the corresponding 3D point is moving in the scene and how the camera is moving relative to the scene. 4928: 4661: 563:

structure from images with the goal of achieving full scene understanding. Studies in the 1970s formed the early foundations for many of the computer vision

2922: 4656: 158: 2943:

Esteva, Andre; Chou, Katherine; Yeung, Serena; Naik, Nikhil; Madani, Ali; Mottaghi, Ali; Liu, Yun; Topol, Eric; Dean, Jeff; Socher, Richard (2021-01-08).

1826:– At some point in the processing, a decision is made about which image points or regions of the image are relevant for further processing. Examples are: 1307:

Military applications are probably one of the largest areas of computer vision. The obvious examples are the detection of enemy soldiers or vehicles and

932:

The core challenges are the acquisition, processing, analysis and rendering of visual information. Application areas include industrial quality control,

3156: 4691: 1949:

Most computer vision systems use visible-light cameras passively viewing a scene at frame rates of at most 60 frames per second (usually far slower).

2669:

Jiao, Licheng; Zhang, Fan; Liu, Fang; Yang, Shuyuan; Li, Lingling; Feng, Zhixi; Qu, Rong (2019). "A Survey of Deep Learning-Based Object Detection".

1984:, etc. Such hardware captures "images" that are then processed often using the same computer vision algorithms used to process visible-light images. 4759: 1704:

used to acquire 3D images from multiple angles. Algorithms are now available to stitch multiple 3D images together into point clouds and 3D models.

257: 235: 3762: 779:

the training gives a weak signal for the oval shape, also resulting in a weak signal for the sea urchin output. These weak signals may result in a

586:

The next decade saw studies based on more rigorous mathematical analysis and quantitative aspects of computer vision. These include the concept of

5154: 1168: 193: 171: 1508: – an individual instance of an object is recognized. Examples include identification of a specific person's face or fingerprint, 447:

devices. The technological discipline of computer vision seeks to apply its theories and models to the construction of computer vision systems.

5037: 4776: 626: 95: 1063:

which primarily focuses on the process of producing images, but sometimes also deals with the processing and analysis of images. For example,

4796: 4509: 4450: 4418: 4393: 4365: 4346: 4323: 4300: 4281: 4260: 4239: 4220: 4201: 4180: 4158: 4139: 4113: 4090: 4071: 4047: 3978: 3945: 3539: 3376: 3320: 3201: 2874: 2765: 2544: 2517: 2490: 2437: 2412: 2356: 2320: 2246: 2219: 2191: 2163: 2132: 1952:

A few computer vision systems use image-acquisition hardware with active illumination or something other than visible light or both, such as

1346: 390: 316: 270: 225: 220: 5827: 4706: 4676: 4666: 4646: 4616: 646: 3630: 1996:

algorithms. When combined with a high-speed projector, fast image acquisition allows 3D measurement and feature tracking to be realized.

1666: – determining the 3D rigid motion (rotation and translation) of the camera from an image sequence produced by the camera. 531:. As a technological discipline, computer vision seeks to apply its theories and models for the construction of computer vision systems. 5928: 5479: 5216: 1775: 1372: 754:

Simplified example of training a neural network in object detection: The network is trained by multiple images that are known to depict

369: 341: 336: 230: 785:

In reality, textures and outlines would not be represented by single nodes, but rather by associated weight patterns of multiple nodes.

4861: 4686: 4528: 4490: 4471: 2731: 2288: 2101: 953: 945: 680: 329: 198: 188: 178: 5740: 5367: 5174: 5030: 4716: 301: 247: 213: 80: 617:. With the advent of optimization methods for camera calibration, it was realized that a lot of the ideas were already explored in 4410: 5695: 4866: 1135: 641:. This decade also marked the first time statistical learning techniques were used in practice to recognize faces in images (see 383: 287: 133: 3099:"Optimizing Strawberry Disease and Quality Detection with Vision Transformers and Attention-Based Convolutional Neural Networks" 2384:

Principles, algorithms, Applications, Learning 5th Edition by E.R. Davies Academic Press, Elsevier 2018 ISBN 978-0-12-809284-2

2058: 1075:

is a field that uses various methods to extract information from signals in general, mainly based on statistical approaches and

598:. Researchers also realized that many of these mathematical concepts could be treated within the same optimization framework as 4851: 4609: 1647:- deals with recognizing the activity from a series of video frames, such as, if the person is picking up an object or walking. 65: 5882: 5822: 5420: 2792: 2294: 487: 3769:." Information Processing and Management of Uncertainty in Knowledge-Based Systems. Springer International Publishing, 2014. 2771: 1929: 3390: 3334: 1779:– Image features at various levels of complexity are extracted from the image data. Typical examples of such features are: 1586:

in images of printed or handwritten text, usually with a view to encoding the text in a format more amenable to editing or

46: 5415: 5104: 4960: 4891: 4742: 2096: 1578: 1540: 634: 1858:

of one or multiple videos into a series of per-frame foreground masks while maintaining its temporal semantic continuity.

5966: 5857: 5211: 5164: 5159: 4003: 1525: 599: 1118:

have enabled researchers to build models that are able to generate and reconstruct 3D shapes from single or multi-view

5908: 5204: 5130: 4711: 4057: 1953: 1435: 1259: 1190: 1037:

Computer vision includes 3D analysis from 2D images. This analyzes the 3D scene projected onto one or several images,

252: 203: 100: 3660: 645:). Toward the end of the 1990s, a significant change came about with the increased interaction between the fields of 3305:

2020 International Conference on Power Electronics & IoT Applications in Renewable Energy and its Control (PARC)

5532: 5467: 5068: 4856: 3760:

Visual Taxometric Approach to Image Segmentation Using Fuzzy-Spatial Taxon Cut Yields Contextually Relevant Regions

2091: 1745: 1686: – to determine, for each point in the image, how that point is moving relative to the image plane, 1179: 1076: 975: 913: 75: 4595: 4558: 1341:, land-based vehicles (small robots with wheels, cars, or trucks), aerial vehicles, and unmanned aerial vehicles ( 748: 723:. The process by which light interacts with surfaces is explained using physics. Physics explains the behavior of 5961: 5933: 5791: 5430: 5261: 5084: 4908: 4821: 2918: 2033: 2010: 1988: 1934: 1848: 1609: 800: 763: 704: 669: 153: 3411:

Balasundaram, A; Ashokkumar, S; Kothandaraman, D; kora, SeenaNaik; Sudarshan, E; Harshaverdhan, A (2020-12-01).

2338: 5956: 5832: 5089: 5012: 4886: 1992: 1981: 1973: 1844: 1794: 933: 889: 556: 277: 4037: 1987:

While traditional broadcast and consumer video systems operate at a rate of 30 frames per second, advances in

1402:

surface. This can be used to calibrate robotic hands in order to make sure they can grasp objects effectively.

1393:

Rubber artificial skin layer with the flexible structure for the shape estimation of micro-undulation surfaces

1290:

industry in which every single Wafer is being measured and inspected for inaccuracies or defects to prevent a

1835:

Segmentation of image into nested scene architecture comprising foreground, object groups, single objects or

5877: 5862: 5515: 5510: 5410: 5278: 5059: 4948: 4938: 4681: 4250: 3097:

Aghamohammadesmaeilketabforoosh, Kimia; Nikan, Soodeh; Antonini, Giorgio; Pearce, Joshua M. (January 2024).

2048: 2002:

systems are composed of a wearable camera that automatically take pictures from a first-person perspective.

1840: 1836: 1509: 1342: 1255: 544: 58: 38: 3473:"trackdem: Automated particle tracking to obtain population counts and size distributions from videos in r" 1319: 5837: 5597: 5316: 5311: 4985: 4953: 4732: 2006: 1855: 1566: 1223: 1091: 937: 929: 630: 148: 3961:

Kagami, Shingo (2010). "High-speed vision systems and projectors for real-time perception of the world".

3681:

Barrett, Lisa Feldman; Adolphs, Ralph; Marsella, Stacy; Martinez, Aleix M.; Pollak, Seth D. (July 2019).

5867: 5852: 5817: 5505: 5405: 5273: 4990: 4801: 4747: 3759: 3219:"Rubber artificial skin layer with flexible structure for shape estimation of micro-undulation surfaces" 2028: 1583: 893: 650: 524: 443: 5735: 4383: 815:, is an early example of computer vision taking direct inspiration from neurobiology, specifically the 3260:"Dexterous object manipulation by a multi-fingered robotic hand with visual-tactile fingertip sensors" 2814:"Computational Vision and Business Intelligence in the Beauty Segment - An Analysis through Instagram" 2345:

The British Machine Vision Association and Society for Pattern Recognition Retrieved February 20, 2017

772: 5887: 5842: 5288: 5233: 5079: 5074: 4913: 4896: 4876: 4846: 4404: 3875: 3795: 3484: 3471:

Bruijning, Marjolein; Visser, Marco D.; Hallmann, Caspar A.; Jongejans, Eelke; Golding, Nick (2018).

3424: 2688: 2627: 2023: 1961: 1957: 1643: 1545: 1152: 1087: 941: 595: 463: 90: 1674: – following the movements of a (usually) smaller set of interest points or objects ( 1552: 948:

for developing research. This is especially the circumstance with the research advancements between

5462: 5440: 5189: 5184: 5142: 5094: 4918: 4781: 3861:"Segment-Tube: Spatio-Temporal Action Localization in Untrimmed Videos with Per-Frame Segmentation" 1631: 1617: 1287: 1072: 925: 909: 696: 614: 607: 603: 548: 519: 503: 242: 5901: 699:

is another field that is closely related to computer vision. Most computer vision systems rely on

5847: 5425: 5254: 4933: 4841: 4826: 4786: 4589: 4123: 3984: 3827: 3739: 3683:"Emotional Expressions Reconsidered: Challenges to Inferring Emotion From Human Facial Movements" 3622: 3586: 3450: 3382: 3326: 3018: 2880: 2813: 2704: 2678: 2651: 1881: 1822: 1741: 1490: 1291: 1258:, or medical image processing, characterized by the extraction of information from image data to 1208: 1186: 1019:

The following characterizations appear relevant but should not be taken as universally accepted:

854: 812: 807:

based image and feature analysis and classification) have their background in neurobiology. The

638: 606:. By the 1990s, some of the previous research topics became more active than others. Research in 475: 471: 292: 1052:, vision-based robots and systems for vision-based inspection, measurement, or picking (such as 3042:"Plant Species Identification Using Computer Vision Techniques: A Systematic Literature Review" 1623:

a subset of facial recognition, emotion recognition refers to the process of classifying human

5913: 5705: 5357: 5228: 5221: 4871: 4816: 4768: 4524: 4505: 4486: 4467: 4446: 4414: 4389: 4361: 4342: 4319: 4296: 4277: 4256: 4235: 4216: 4197: 4176: 4154: 4135: 4109: 4086: 4067: 4043: 3974: 3941: 3911: 3893: 3819: 3811: 3779:

Liu, Ziyi; Wang, Le; Hua, Gang; Zhang, Qilin; Niu, Zhenxing; Wu, Ying; Zheng, Nanning (2018).

3720: 3702: 3614: 3535: 3512: 3442: 3372: 3357:"State-of-the-Art Analysis of Modern Drowsiness Detection Algorithms Based on Computer Vision" 3316: 3281: 3240: 3197: 3138: 3120: 3079: 3061: 2982: 2964: 2870: 2761: 2727: 2643: 2593: 2540: 2513: 2507: 2486: 2433: 2408: 2316: 2284: 2242: 2215: 2187: 2159: 2128: 2073: 2043: 2038: 1999: 1875: 1700: 1627:

Psychologists caution, however, that internal emotions cannot be reliably detected from faces.

1367: 1325: 1146: 1013: 1005: 897: 881: 835: 823: 732: 716: 618: 610: 580: 560: 479: 451: 70: 3859:

Wang, Le; Duan, Xuhuan; Zhang, Qilin; Niu, Zhenxing; Hua, Gang; Zheng, Nanning (2018-05-22).

5658: 5648: 5455: 5249: 5199: 5194: 5137: 5125: 4980: 4943: 4791: 4651: 4379: 4311: 4168: 3966: 3963:

2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops

3901: 3883: 3803: 3710: 3694: 3604: 3596: 3502: 3492: 3432: 3428: 3364: 3308: 3271: 3230: 3128: 3110: 3069: 3053: 3010: 2972: 2956: 2860: 2852: 2696: 2635: 2583: 2573: 2461: 2276: 1818: 1798: 1516: 1466: 1458: 1349:), for detecting obstacles. It can also be used for detecting certain task-specific events, 1308: 1267: 1023: 991: 957: 917: 905: 901: 885: 873: 867: 846: 684: 572: 455: 430: 418: 208: 143: 128: 5771: 5715: 5537: 5179: 5099: 4975: 4923: 4584: 4562: 3766: 2802:." Proceedings of International Conference on Robotics and Automation. Vol. 2. IEEE, 1997. 2799: 2342: 1977: 1901:

Flag for further human review in medical, military, security and recognition applications.

1787: 1699:

Given one or (typically) more images of a scene, or a video, scene reconstruction aims at

1423: 1296: 1064: 1060: 720: 658: 528: 483: 459: 3437: 3412: 1832:

Segmentation of one or multiple image regions that contain a specific object of interest.

1229:

Tracking surfaces or planes in 3D coordinates for allowing Augmented Reality experiences.

3879: 3799: 3488: 3133: 3098: 2692: 2631: 5745: 5710: 5700: 5525: 5283: 5109: 5000: 4970: 4881: 4806: 4737: 4375: 4334: 4271: 3906: 3715: 3682: 3074: 3041: 2977: 2944: 2453: 2068: 2063: 1802: 1783: 1670: 1636: 1557: 1499: 1482: 1462: 1415: 1354: 1283: 1164: 1103: 1083: 1044: 1027: 999: 995: 949: 780: 712: 622: 568: 532: 467: 422: 2612: 1869:

Verification that the data satisfies model-based and application-specific assumptions.

1114:

Learning 3D shapes has been a challenging task in computer vision. Recent advances in

1079:. A significant part of this field is devoted to applying these methods to image data. 5950: 5690: 5670: 5587: 5266: 4965: 4574: 3574: 3454: 3386: 3368: 3330: 3022: 2708: 2588: 2236: 2151: 2078: 2053: 1965: 1571: 1330: 1115: 850: 816: 804: 728: 708: 700: 507: 426: 138: 3988: 3831: 2884: 5776: 5607: 4903: 3626: 3157:"New AI model developed at Western detects strawberry diseases, takes aim at waste" 2655: 1737: 1682: 1587: 1454: 1429: 1212: 808: 792: 576: 414: 282: 17: 4128: 4102: 3781:"Joint Video Object Discovery and Segmentation by Coupled Dynamic Markov Networks" 3312: 2263: 1872:

Estimation of application-specific parameters, such as object pose or object size.

3301:"Drowsiness Detection of a Driver using Conventional Computer Vision Application" 3014: 2751: 2534: 2480: 2402: 1760:

Noise reduction to ensure that sensor noise does not introduce false information.

5872: 5643: 5552: 5547: 5169: 5147: 4811: 2898:

Turek, Fred (June 2011). "Machine Vision Fundamentals, How to Make Robots See".

2700: 1766: 1598: 1469:

data from the real world in order to produce numerical or symbolic information,

1338: 1053: 662: 587: 515: 506:

that deals with how computers can be made to gain high-level understanding from

311: 296: 3970: 3356: 3300: 3276: 3259: 3235: 3218: 2960: 2357:"Star Trek's "tricorder" medical scanner just got closer to becoming a reality" 1639:

systems differentiating human beings (head and shoulder patterns) from objects.

1502:, and LikeThat provide stand-alone programs that illustrate this functionality. 876:

is a generic term for all computer science disciplines dealing with images and

5766: 5725: 5720: 5633: 5542: 5450: 5362: 5342: 4568: 3600: 3057: 2578: 2561: 1717: 1397: 1282:

A second application area in computer vision is in industry, sometimes called

971: 759: 543:

In the late 1960s, computer vision began at universities that were pioneering

4552:– a complete list of papers of the most relevant computer vision conferences. 3897: 3815: 3807: 3706: 3698: 3618: 3516: 3446: 3285: 3244: 3124: 3065: 2968: 2597: 2280: 822:

Some strands of computer vision research are closely related to the study of

5761: 5730: 5628: 5472: 5435: 5372: 5326: 5321: 5306: 3497: 3472: 2757: 1839:

object parts (also referred to as spatial-taxon scene hierarchy), while the

1662: 1389: 1119: 642: 564: 346: 110: 5022: 4061: 3915: 3823: 3724: 3142: 3083: 2986: 2647: 3652: 3115: 2856: 5663: 5495: 4356:

R. Fisher; K Dawson-Howe; A. Fitzgibbon; C. Robertson; E. Trucco (2005).

4191: 3738:

A. Maity (2015). "Improvised Salient Object Detection and Manipulation".

3609: 2865: 1769:

representation to enhance image structures at locally appropriate scales.

1763:

Contrast enhancement to ensure that relevant information can be detected.

1529: 1337:

One of the newer application areas is autonomous vehicles, which include

979: 921: 877: 755: 654: 183: 105: 2639: 2212:

Computer Vision and Applications, A Guide for Students and Practitioners

5786: 5623: 5577: 5500: 5400: 5395: 5347: 4565:– news, source code, datasets and job offers related to computer vision 4555: 4440: 3507: 2465: 2432:. Cambridge, Massachusetts London, England: The MIT Press. p. 28. 1624: 1602: 591: 575:, representation of objects as interconnections of smaller structures, 351: 3888: 2849:

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

5801: 5781: 5653: 5445: 4577:– supporting computer vision research within the UK via the BMVC and 4549: 2335: 1892:

Making the final decision required for the application, for example:

1377: 1263: 724: 435: 4544: 2533:

Nicu Sebe; Ira Cohen; Ashutosh Garg; Thomas S. Huang (3 June 2005).

2272: 3744: 3217:

Ando, Mitsuhito; Takei, Toshinobu; Mochiyama, Hiromi (2020-03-03).

2683: 1740:, which, besides various types of light-sensitive cameras, include 1030:

tend to focus on 2D images, how to transform one image to another,

5602: 5582: 5572: 5567: 5562: 5557: 5520: 5352: 4601: 3591: 1969: 1938: 1928: 1812:

More complex features may be related to texture, shape, or motion.

1757:

Re-sampling to ensure that the image coordinate system is correct.

1594: 1551: 1396: 1388: 1318: 1247: 1237: 1109: 679: 511: 3413:"Computer vision based fatigue detection using facial parameters" 2009:

are emerging as a new class of processors to complement CPUs and

1884:– comparing and combining two different views of the same object. 5592: 1481:

The classical problem in computer vision, image processing, and

1362: 5026: 4605: 3653:"AI Image Recognition: Inevitable Trending of Modern Lifestyle" 1535:

Several specialized tasks based on recognition exist, such as:

1189:

model has been developed to help farmers automatically detect

555:

What distinguished computer vision from the prevalent field of

4424: 4004:"A Third Type Of Processor For VR/AR: Movidius' Myriad 2 VPU" 727:

which are a core part of most imaging systems. Sophisticated

4461: 4406:

Digital Image Processing: An Algorithmic Approach Using Java

3361:

2021 29th Conference of Open Innovations Association (FRUCT)

2793:

Stereo vision-based mapping and navigation for mobile robots

2750:

Steger, Carsten; Markus Ulrich; Christian Wiedemann (2018).

633:

and further multi-view stereo techniques. At the same time,

45: 4521:

Feature Extraction and Image Processing for Computer Vision

4249:

Reinhard Klette; Karsten Schluens; Andreas Koschan (1998).

2560:

William Freeman; Pietro Perona; Bernhard Scholkopf (2008).

1524:

Currently, the best algorithms for such tasks are based on

3940:. New York: John Wiley & Sons, Inc. pp. 643–646. 1878:– classifying a detected object into different categories. 1440:

Tracking and counting organisms in the biological sciences

762:, which are correlated with "nodes" that represent visual 2407:. Springer Science & Business Media. pp. 10–16. 4173:

Three-Dimensional Computer Vision, A Geometric Viewpoint

3417:

IOP Conference Series: Materials Science and Engineering

1528:. An illustration of their capabilities is given by the 2562:"Guest Editorial: Machine Learning for Computer Vision" 2205: 2203: 2146: 2144: 1913:

requirements are entirely topics for further research.

990:

The fields most closely related to computer vision are

4211:

James L. Crowley; Henrik I. Christensen, eds. (1995).

3466: 3464: 2611:

LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey (2015).

4252:

Computer Vision – Three-Dimensional Data from Images

2823:. American Research Institute for Policy Development 1465:

and understanding digital images, and extraction of

1329:, an example of an uncrewed land-based vehicle. The 5810: 5754: 5683: 5616: 5488: 5388: 5381: 5335: 5299: 5242: 5118: 5058: 4767: 4758: 4725: 4639: 4483:

Algorithms for Image Processing and Computer Vision

4439:Pedram Azad; Tilo Gockel; Rüdiger Dillmann (2008). 3575:"ImageNet Large Scale Visual Recognition Challenge" 1200:, medical image analysis or topographical modeling; 1185:monitoring agricultural crops, e.g. an open-source 590:, the inference of shape from various cues such as 571:from images, labeling of lines, non-polyhedral and 4385:Handbook of Mathematical Models in Computer Vision 4358:Dictionary of Computer Vision and Image Processing 4127: 4101: 3194:Machine Vision: Theory, Algorithms, Practicalities 1560:purposes in public places, malls, shopping centers 1134:Assisting humans in identification tasks, e.g., a 940:. Conclusively, this includes the extenuations of 627:3-D reconstructions of scenes from multiple images 3938:Encyclopedia of Artificial Intelligence, Volume 1 1597:). A related task is reading of 2D codes such as 1530:ImageNet Large Scale Visual Recognition Challenge 1102:Applications range from tasks such as industrial 3046:Archives of Computational Methods in Engineering 2311:Milan Sonka; Vaclav Hlavac; Roger Boyle (2008). 2262:Huang, T. (1996-11-19). Vandoni, Carlo E (ed.). 1736:– A digital image is produced by one or several 1254:One of the most prominent application fields is 834:Yet another field related to computer vision is 4273:Introductory Techniques for 3-D Computer Vision 3355:Hasan, Fudail; Kashevnik, Alexey (2021-05-14). 2945:"Deep learning-enabled medical computer vision" 2482:Mind as Machine: A History of Cognitive Science 2396: 2394: 2392: 2390: 1895:Pass/fail on automatic inspection applications. 1829:Selection of a specific set of interest points. 27:Computerized information extraction from images 4596:Computer Vision Container, Joe Hoeller GitHub: 3258:Choi, Seung-hyun; Tahara, Kenji (2020-03-12). 3187: 3185: 3183: 3181: 3179: 3177: 2313:Image Processing, Analysis, and Machine Vision 2235:Dana H. Ballard; Christopher M. Brown (1982). 1512:, or the identification of a specific vehicle. 5038: 4617: 4571:– Bob Fisher's Compendium of Computer Vision. 3040:Wäldchen, Jana; Mäder, Patrick (2017-01-07). 2745: 2743: 2177: 2175: 2118: 2116: 811:, a neural network developed in the 1970s by 391: 8: 4463:Computer Vision: Algorithms and Applications 3687:Psychological Science in the Public Interest 2919:"The Future of Automated Random Bin Picking" 2404:Computer Vision: Algorithms and Applications 2265:Computer Vision : Evolution And Promise 908:. Visual computing also includes aspects of 2456:(1966-07-01). "The Summer Vision Project". 1898:Match/no-match in recognition applications. 707:, which is typically in the form of either 5385: 5045: 5031: 5023: 4764: 4624: 4610: 4602: 4270:Emanuele Trucco; Alessandro Verri (1998). 4100:Barghout, Lauren; Lawrence W. Lee (2003). 2753:Machine Vision Algorithms and Applications 1453:Computer vision tasks include methods for 1122:or silhouettes seamlessly and efficiently. 1086:also overlaps with computer vision, e.g., 398: 384: 29: 4442:Computer Vision – Principles and Practice 4316:Multiple View Geometry in Computer Vision 4230:Gösta H. Granlund; Hans Knutsson (1995). 3905: 3887: 3743: 3714: 3608: 3590: 3506: 3496: 3436: 3275: 3234: 3132: 3114: 3073: 2976: 2864: 2682: 2587: 2577: 2539:. Springer Science & Business Media. 2512:. Springer Science & Business Media. 1262:. An example of this is the detection of 4545:USC Iris computer vision conference list 4104:Perceptual information processing system 3579:International Journal of Computer Vision 2842: 2840: 2838: 2566:International Journal of Computer Vision 1226:databases of images and image sequences. 629:. Progress was made on the dense stereo 2112: 1250:'s Visual Media Reasoning concept video 853:or deliberation for robotic systems to 668:Recent work has seen the resurgence of 450:Sub-domains of computer vision include 37: 4777:3D reconstruction from multiple images 4403:Wilhelm Burger; Mark J. Burge (2007). 4108:. U.S. Patent Application 10/618,543. 4081:Azriel Rosenfeld; Avinash Kak (1982). 2401:Richard Szeliski (30 September 2010). 1574:situation or picking parts from a bin. 518:, it seeks to automate tasks that the 4797:Simultaneous localization and mapping 4519:Nixon, Mark; Aguado, Alberto (2019). 4232:Signal Processing for Computer Vision 4193:Scale-Space Theory in Computer Vision 3788:IEEE Transactions on Image Processing 3568: 3566: 3530:David A. Forsyth; Jean Ponce (2003). 2210:Bernd Jähne; Horst Haußecker (2000). 559:at that time was a desire to extract 7: 5883:Generative adversarial network (GAN) 3965:. Vol. 2010. pp. 100–107. 3555:Forsyth, David; Ponce, Jean (2012). 2184:Computer Vision and Image Processing 1510:identification of handwritten digits 4151:Computer Vision for robotic systems 4014:from the original on March 15, 2023 2791:Murray, Don, and Cullen Jennings. " 2536:Machine Learning in Computer Vision 1582:(OCR) – identifying 1418:creation for cinema and broadcast, 649:and computer vision. This included 4862:Automatic number-plate recognition 4575:British Machine Vision Association 4502:Computer Vision for Visual Effects 4445:. Elektor International Media BV. 4339:Emerging Topics in Computer Vision 3557:Computer vision: a modern approach 3532:Computer Vision, A Modern Approach 2336:http://www.bmva.org/visionoverview 2102:Outline of artificial intelligence 1196:Modeling objects or environments, 954:Generative Artificial Intelligence 946:Generative Artificial Intelligence 25: 4550:Computer vision papers on the web 4042:. University of Minnesota Press. 1410:Other application areas include: 719:. The sensors are designed using 625:. This led to methods for sparse 5921: 5920: 5900: 4867:Automated species identification 4523:(4th ed.). Academic Press. 4002:Seth Colaner (January 3, 2016). 3925:from the original on 2018-09-07. 3477:Methods in Ecology and Evolution 3369:10.23919/FRUCT52173.2021.9435480 2509:Three-Dimensional Machine Vision 2506:Takeo Kanade (6 December 2012). 2485:. Clarendon Press. p. 781. 2363:from the original on 2 July 2017 2300:from the original on 2018-02-07. 2275:. Geneva: CERN. pp. 21–25. 1131:, in manufacturing applications; 866:This section is an excerpt from 849:sometimes deals with autonomous 771: 747: 4852:Audio-visual speech recognition 3663:from the original on 2022-12-02 3633:from the original on 2023-03-15 3393:from the original on 2022-06-27 3337:from the original on 2022-06-27 2925:from the original on 2018-01-11 2821:Journal of Marketing Management 2774:from the original on 2023-03-15 2722:Ferrie, C.; Kaiser, S. (2019). 2428:Sejnowski, Terrence J. (2018). 1333:is mounted on top of the rover. 1178:, as the input to a device for 855:navigate through an environment 613:led to better understanding of 66:Artificial general intelligence 5833:Recurrent neural network (RNN) 5823:Differentiable neural computer 4697:Recognition and categorization 4504:. Cambridge University Press. 4318:. Cambridge University Press. 3438:10.1088/1757-899x/981/2/022005 2355:Murphy, Mike (13 April 2017). 596:contour models known as snakes 1: 5878:Variational autoencoder (VAE) 5838:Long short-term memory (LSTM) 5105:Computational learning theory 4961:Optical character recognition 4892:Content-based image retrieval 4234:. Kluwer Academic Publisher. 4149:Michael C. Fairhurst (1988). 4066:. W. H. Freeman and Company. 3313:10.1109/PARC49193.2020.236556 3299:Garg, Hitendra (2020-02-29). 2273:19th CERN School of Computing 2154:; George C. Stockman (2001). 2097:List of emerging technologies 1579:Optical character recognition 1541:Content-based image retrieval 1526:convolutional neural networks 1059:There is also a field called 904:, upon which extenuates into 5858:Convolutional neural network 4039:The Birth of Computer Vision 3651:Quinn, Arthur (2022-10-09). 3015:10.1016/j.neucom.2020.04.018 2430:The deep learning revolution 1954:structured-light 3D scanners 1716:An example in this field is 1632:Shape Recognition Technology 567:that exist today, including 547:. It was meant to mimic the 5853:Multilayer perceptron (MLP) 3936:Shapiro, Stuart C. (1992). 2812:Andrade, Norberto Almeida. 2701:10.1109/ACCESS.2019.2939201 2479:Margaret Ann Boden (2006). 2059:Teknomo–Fernandez algorithm 1908:Image-understanding systems 1436:Driver drowsiness detection 942:large language models (LLM) 101:Natural language processing 5983: 5929:Artificial neural networks 5843:Gated recurrent unit (GRU) 5069:Differentiable programming 4857:Automatic image annotation 4692:Noise reduction techniques 4083:Digital Picture Processing 3971:10.1109/CVPRW.2010.5543776 3277:10.1186/s40648-020-00162-5 3236:10.1186/s40648-020-00159-0 2961:10.1038/s41746-020-00376-2 2756:(2nd ed.). Weinheim: 2724:Neural Networks for Babies 2458:MIT AI Memos (1959 - 2004) 2092:Outline of computer vision 1993:consumer graphics hardware 1746:magnetic resonance imaging 1644:Human activity recognition 1355:autonomous driving of cars 1180:computer-human interaction 1077:artificial neural networks 914:human-computer interaction 865: 514:. From the perspective of 486:, 3D scene modeling, and 413:tasks include methods for 154:Hybrid intelligent systems 76:Recursive self-improvement 5896: 5262:Artificial neural network 5085:Automatic differentiation 5009: 4822:Free viewpoint television 4500:Richard J. Radke (2013). 4460:Richard Szeliski (2010). 3601:10.1007/s11263-015-0816-y 3058:10.1007/s11831-016-9206-z 2900:NASA Tech Briefs Magazine 2589:21.11116/0000-0003-30FB-C 2579:10.1007/s11263-008-0127-7 2034:Computational photography 2011:graphics processing units 1989:digital signal processing 1974:magnetic resonance images 705:electromagnetic radiation 659:panoramic image stitching 621:theory from the field of 594:, texture and focus, and 5090:Neuromorphic engineering 5053:Differentiable computing 4887:Computer-aided diagnosis 4293:Digital Image Processing 4036:James E. Dobson (2023). 3808:10.1109/tip.2018.2859622 3699:10.1177/1529100619832930 2281:10.5170/CERN-1996-008.21 2123:Reinhard Klette (2014). 1982:synthetic aperture sonar 1843:is often implemented as 1218:Organizing information, 934:medical image processing 557:digital image processing 278:Artificial consciousness 5863:Residual neural network 5279:Artificial Intelligence 4949:Moving object detection 4939:Medical image computing 4702:Research infrastructure 4672:Image sensor technology 4588:(open-source journal), 4485:(2nd ed.). Wiley. 4255:. Springer, Singapore. 4190:Tony Lindeberg (1994). 3498:10.1111/2041-210X.12975 3429:2020MS&E..981b2005B 2125:Concise Computer Vision 2049:Machine vision glossary 2007:vision processing units 1256:medical computer vision 1141:Controlling processes, 930:security visualization. 635:variations of graph cut 545:artificial intelligence 504:interdisciplinary field 149:Evolutionary algorithms 39:Artificial intelligence 4986:Video content analysis 4954:Small object detection 4733:Computer stereo vision 4556:Computer Vision Online 3192:E. Roy Davies (2005). 2851:. pp. 1511–1519. 2186:. Palgrave Macmillan. 1942: 1561: 1403: 1394: 1334: 1251: 1136:species identification 1127:Automatic inspection, 1123: 1092:computer stereo vision 938:User Experience Design 783:result for sea urchin. 688: 657:, view interpolation, 631:correspondence problem 502:Computer vision is an 478:, learning, indexing, 50: 5818:Neural Turing machine 5406:Human image synthesis 4991:Video motion analysis 4802:Structure from motion 4748:3D object recognition 4481:J. R. Parker (2011). 3116:10.3390/foods13121869 2857:10.1109/CVPR.2017.269 2029:Computational imaging 2013:(GPUs) in this role. 1962:hyperspectral imagers 1958:thermographic cameras 1932: 1864:High-level processing 1555: 1496:object classification 1400: 1392: 1322: 1246: 1113: 894:computational imaging 817:primary visual cortex 683: 663:light-field rendering 651:image-based rendering 525:scientific discipline 444:scientific discipline 49: 5909:Computer programming 5888:Graph neural network 5463:Text-to-video models 5441:Text-to-image models 5289:Large language model 5274:Scientific computing 5080:Statistical manifold 5075:Information geometry 4914:Foreground detection 4897:Reverse image search 4877:Bioimage informatics 4847:Activity recognition 4592:and one-day meetings 4378:and Yunmei Chen and 4310:Richard Hartley and 4291:Bernd Jähne (2002). 4008:www.tomshardware.com 3363:. pp. 141–149. 2949:npj Digital Medicine 2024:Chessboard detection 1701:computing a 3D model 1695:Scene reconstruction 1556:Computer vision for 1546:reverse image search 1323:Artist's concept of 1193:with 98.4% accuracy. 1088:stereophotogrammetry 604:Markov random fields 464:activity recognition 452:scene reconstruction 429:, and extraction of 91:General game playing 5967:Packaging machinery 5255:In-context learning 5095:Pattern recognition 4981:Autonomous vehicles 4919:Gesture recognition 4782:2D to 3D conversion 4466:. Springer-Verlag. 4215:. Springer-Verlag. 3880:2018Senso..18.1657W 3800:2018ITIP...27.5840L 3758:Barghout, Lauren. " 3489:2018MEcEv...9..965B 3196:. Morgan Kaufmann. 2693:2019IEEEA...7l8837J 2640:10.1038/nature14539 2632:2015Natur.521..436L 2182:Tim Morris (2004). 1935:2020 model iPad Pro 1618:Emotion recognition 1315:Autonomous vehicles 1191:strawberry diseases 1187:vision transformers 1169:restaurant industry 1161:visual surveillance 1073:pattern recognition 926:computer simulation 910:pattern recognition 892:, computer vision, 697:Solid-state physics 692:Solid-state physics 637:were used to solve 611:3-D reconstructions 573:polyhedral modeling 569:extraction of edges 549:human visual system 520:human visual system 243:Machine translation 159:Systems integration 96:Knowledge reasoning 33:Part of a series on 18:Image understanding 5848:Echo state network 5736:Jürgen Schmidhuber 5431:Facial recognition 5426:Speech recognition 5336:Software libraries 4996:Video surveillance 4934:Landmark detection 4842:3D pose estimation 4827:Volumetric capture 4787:Gaussian splatting 4743:Object recognition 4657:Commercial systems 4590:BMVA Summer School 4561:2011-11-30 at the 4124:Berthold K.P. Horn 4085:. Academic Press. 3765:2018-11-14 at the 3307:. pp. 50–53. 2798:2020-10-31 at the 2341:2017-02-16 at the 2214:. Academic Press. 1943: 1882:Image registration 1849:temporal attention 1776:Feature extraction 1621: – 1612: – 1610:Facial recognition 1562: 1491:Object recognition 1404: 1395: 1335: 1260:diagnose a patient 1252: 1209:autonomous vehicle 1124: 958:Visual Computation 906:Design Computation 842:Robotic navigation 813:Kunihiko Fukushima 689: 639:image segmentation 615:camera calibration 476:3D pose estimation 472:object recognition 425:and understanding 51: 5944: 5943: 5706:Stephen Grossberg 5679: 5678: 5020: 5019: 4929:Image restoration 4872:Augmented reality 4837: 4836: 4817:4D reconstruction 4769:3D reconstruction 4662:Feature detection 4511:978-0-521-76687-6 4452:978-0-905705-71-2 4420:978-1-84628-379-6 4395:978-0-387-26371-7 4367:978-0-470-01526-1 4348:978-0-13-101366-7 4341:. Prentice Hall. 4325:978-0-521-54051-3 4302:978-3-540-67754-3 4283:978-0-13-261108-4 4276:. Prentice Hall. 4262:978-981-3083-71-4 4241:978-0-7923-9530-0 4222:978-3-540-58143-7 4213:Vision as Process 4203:978-0-7923-9418-1 4182:978-0-262-06158-2 4160:978-0-13-166919-2 4153:. Prentice Hall. 4141:978-0-262-08159-7 4115:978-0-262-08159-7 4092:978-0-12-597301-4 4073:978-0-7167-1284-8 4049:978-1-5179-1421-9 3980:978-1-4244-7029-7 3947:978-0-471-50306-4 3889:10.3390/s18051657 3794:(12): 5840–5853. 3541:978-0-13-085198-7 3534:. Prentice Hall. 3378:978-952-69244-5-8 3322:978-1-7281-6575-2 3203:978-0-12-206093-9 2876:978-1-5386-0457-1 2767:978-3-527-41365-2 2677:: 128837–128868. 2626:(7553): 436–444. 2546:978-1-4020-3274-5 2519:978-1-4613-1981-8 2492:978-0-19-954316-8 2439:978-0-262-03803-4 2414:978-1-84882-935-0 2322:978-0-495-08252-1 2248:978-0-13-165316-0 2241:. Prentice Hall. 2221:978-0-13-085198-7 2193:978-0-333-99451-1 2165:978-0-13-030796-5 2158:. Prentice Hall. 2134:978-1-4471-6320-6 2074:Visual perception 2044:Egocentric vision 2039:Computer audition 2000:Egocentric vision 1876:Image recognition 1734:Image acquisition 1708:Image restoration 1244: 1014:augmented reality 1012:, as explored in 1006:Computer graphics 898:augmented reality 882:computer graphics 836:signal processing 830:Signal processing 824:biological vision 733:quantum mechanics 717:ultraviolet light 647:computer graphics 619:bundle adjustment 581:motion estimation 561:three-dimensional 488:image restoration 480:motion estimation 439:learning theory. 408: 407: 144:Bayesian networks 71:Intelligent agent 16:(Redirected from 5974: 5962:Image processing 5934:Machine learning 5924: 5923: 5904: 5659:Action selection 5649:Self-driving car 5456:Stable Diffusion 5421:Speech synthesis 5386: 5250:Machine learning 5126:Gradient descent 5047: 5040: 5033: 5024: 4944:Object detection 4909:Face recognition 4792:Shape from focus 4765: 4652:Digital geometry 4626: 4619: 4612: 4603: 4579:MIUA conferences 4534: 4515: 4496: 4477: 4456: 4435: 4433: 4432: 4423:. Archived from 4399: 4380:Olivier Faugeras 4371: 4352: 4333:Gérard Medioni; 4329: 4312:Andrew Zisserman 4306: 4287: 4266: 4245: 4226: 4207: 4186: 4169:Olivier Faugeras 4164: 4145: 4133: 4119: 4107: 4096: 4077: 4053: 4024: 4023: 4021: 4019: 3999: 3993: 3992: 3958: 3952: 3951: 3933: 3927: 3926: 3924: 3909: 3891: 3865: 3856: 3850: 3849: 3847: 3846: 3840: 3834:. Archived from 3785: 3776: 3770: 3756: 3750: 3749: 3747: 3735: 3729: 3728: 3718: 3678: 3672: 3671: 3669: 3668: 3648: 3642: 3641: 3639: 3638: 3612: 3594: 3570: 3561: 3560: 3552: 3546: 3545: 3527: 3521: 3520: 3510: 3500: 3468: 3459: 3458: 3440: 3408: 3402: 3401: 3399: 3398: 3352: 3346: 3345: 3343: 3342: 3296: 3290: 3289: 3279: 3264:ROBOMECH Journal 3255: 3249: 3248: 3238: 3223:ROBOMECH Journal 3214: 3208: 3207: 3189: 3172: 3171: 3169: 3168: 3153: 3147: 3146: 3136: 3118: 3094: 3088: 3087: 3077: 3037: 3031: 3030: 2997: 2991: 2990: 2980: 2940: 2934: 2933: 2931: 2930: 2915: 2909: 2907: 2895: 2889: 2888: 2868: 2844: 2833: 2832: 2830: 2828: 2818: 2809: 2803: 2789: 2783: 2782: 2780: 2779: 2747: 2738: 2737: 2719: 2713: 2712: 2686: 2666: 2660: 2659: 2617: 2608: 2602: 2601: 2591: 2581: 2557: 2551: 2550: 2530: 2524: 2523: 2503: 2497: 2496: 2476: 2470: 2469: 2450: 2444: 2443: 2425: 2419: 2418: 2398: 2385: 2379: 2373: 2372: 2370: 2368: 2352: 2346: 2333: 2327: 2326: 2308: 2302: 2301: 2299: 2270: 2259: 2253: 2252: 2232: 2226: 2225: 2207: 2198: 2197: 2179: 2170: 2169: 2152:Linda G. Shapiro 2148: 2139: 2138: 2120: 1854:Segmentation or 1467:high-dimensional 1385:Tactile feedback 1309:missile guidance 1268:arteriosclerosis 1245: 1153:Detecting events 1147:industrial robot 1024:Image processing 992:image processing 918:machine learning 902:video processing 886:image processing 874:Visual computing 868:Visual computing 861:Visual computing 847:Robot navigation 775: 751: 685:Object detection 456:object detection 431:high-dimensional 400: 393: 386: 307:Existential risk 129:Machine learning 30: 21: 5982: 5981: 5977: 5976: 5975: 5973: 5972: 5971: 5957:Computer vision 5947: 5946: 5945: 5940: 5892: 5806: 5772:Google DeepMind 5750: 5716:Geoffrey Hinton 5675: 5612: 5538:Project Debater 5484: 5382:Implementations 5377: 5331: 5295: 5238: 5180:Backpropagation 5114: 5100:Tensor calculus 5054: 5051: 5021: 5016: 5005: 4976:Robotic mapping 4924:Image denoising 4833: 4754: 4721: 4687:Motion analysis 4635: 4633:Computer vision 4630: 4563:Wayback Machine 4541: 4531: 4518: 4512: 4499: 4493: 4480: 4474: 4459: 4453: 4438: 4430: 4428: 4421: 4402: 4396: 4374: 4368: 4355: 4349: 4332: 4326: 4309: 4303: 4290: 4284: 4269: 4263: 4248: 4242: 4229: 4223: 4210: 4204: 4189: 4183: 4167: 4161: 4148: 4142: 4122: 4116: 4099: 4093: 4080: 4074: 4056: 4050: 4035: 4032: 4030:Further reading 4027: 4017: 4015: 4001: 4000: 3996: 3981: 3960: 3959: 3955: 3948: 3935: 3934: 3930: 3922: 3863: 3858: 3857: 3853: 3844: 3842: 3838: 3783: 3778: 3777: 3773: 3767:Wayback Machine 3757: 3753: 3737: 3736: 3732: 3680: 3679: 3675: 3666: 3664: 3650: 3649: 3645: 3636: 3634: 3572: 3571: 3564: 3554: 3553: 3549: 3542: 3529: 3528: 3524: 3470: 3469: 3462: 3410: 3409: 3405: 3396: 3394: 3379: 3354: 3353: 3349: 3340: 3338: 3323: 3298: 3297: 3293: 3257: 3256: 3252: 3216: 3215: 3211: 3204: 3191: 3190: 3175: 3166: 3164: 3155: 3154: 3150: 3096: 3095: 3091: 3039: 3038: 3034: 2999: 2998: 2994: 2942: 2941: 2937: 2928: 2926: 2917: 2916: 2912: 2897: 2896: 2892: 2877: 2846: 2845: 2836: 2826: 2824: 2816: 2811: 2810: 2806: 2800:Wayback Machine 2790: 2786: 2777: 2775: 2768: 2749: 2748: 2741: 2734: 2726:. Sourcebooks. 2721: 2720: 2716: 2668: 2667: 2663: 2615: 2613:"Deep Learning" 2610: 2609: 2605: 2559: 2558: 2554: 2547: 2532: 2531: 2527: 2520: 2505: 2504: 2500: 2493: 2478: 2477: 2473: 2454:Papert, Seymour 2452: 2451: 2447: 2440: 2427: 2426: 2422: 2415: 2400: 2399: 2388: 2382:Computer Vision 2380: 2376: 2366: 2364: 2354: 2353: 2349: 2343:Wayback Machine 2334: 2330: 2323: 2310: 2309: 2305: 2297: 2291: 2268: 2261: 2260: 2256: 2249: 2238:Computer Vision 2234: 2233: 2229: 2222: 2209: 2208: 2201: 2194: 2181: 2180: 2173: 2166: 2156:Computer Vision 2150: 2149: 2142: 2135: 2122: 2121: 2114: 2110: 2088: 2083: 2019: 1978:side-scan sonar 1927: 1910: 1890:Decision making 1856:co-segmentation 1841:visual salience 1795:interest points 1726: 1710: 1697: 1654: 1652:Motion analysis 1567:Pose estimation 1479: 1447: 1426:(match moving). 1424:camera tracking 1387: 1317: 1305: 1297:optical sorting 1280: 1238: 1236: 1167:, e.g., in the 1165:people counting 1100: 1065:medical imaging 988: 967: 962: 961: 950:Embodied Agents 871: 863: 844: 832: 790: 789: 788: 787: 786: 784: 776: 768: 767: 752: 741: 721:quantum physics 703:, which detect 694: 687:in a photograph 678: 541: 529:medical scanner 500: 484:visual servoing 460:event detection 411:Computer vision 404: 375: 374: 365: 357: 356: 332: 322: 321: 293:Control problem 273: 263: 262: 174: 164: 163: 124: 116: 115: 86:Computer vision 61: 28: 23: 22: 15: 12: 11: 5: 5980: 5978: 5970: 5969: 5964: 5959: 5949: 5948: 5942: 5941: 5939: 5938: 5937: 5936: 5931: 5918: 5917: 5916: 5911: 5897: 5894: 5893: 5891: 5890: 5885: 5880: 5875: 5870: 5865: 5860: 5855: 5850: 5845: 5840: 5835: 5830: 5825: 5820: 5814: 5812: 5808: 5807: 5805: 5804: 5799: 5794: 5789: 5784: 5779: 5774: 5769: 5764: 5758: 5756: 5752: 5751: 5749: 5748: 5746:Ilya Sutskever 5743: 5738: 5733: 5728: 5723: 5718: 5713: 5711:Demis Hassabis 5708: 5703: 5701:Ian Goodfellow 5698: 5693: 5687: 5685: 5681: 5680: 5677: 5676: 5674: 5673: 5668: 5667: 5666: 5656: 5651: 5646: 5641: 5636: 5631: 5626: 5620: 5618: 5614: 5613: 5611: 5610: 5605: 5600: 5595: 5590: 5585: 5580: 5575: 5570: 5565: 5560: 5555: 5550: 5545: 5540: 5535: 5530: 5529: 5528: 5518: 5513: 5508: 5503: 5498: 5492: 5490: 5486: 5485: 5483: 5482: 5477: 5476: 5475: 5470: 5460: 5459: 5458: 5453: 5448: 5438: 5433: 5428: 5423: 5418: 5413: 5408: 5403: 5398: 5392: 5390: 5383: 5379: 5378: 5376: 5375: 5370: 5365: 5360: 5355: 5350: 5345: 5339: 5337: 5333: 5332: 5330: 5329: 5324: 5319: 5314: 5309: 5303: 5301: 5297: 5296: 5294: 5293: 5292: 5291: 5284:Language model 5281: 5276: 5271: 5270: 5269: 5259: 5258: 5257: 5246: 5244: 5240: 5239: 5237: 5236: 5234:Autoregression 5231: 5226: 5225: 5224: 5214: 5212:Regularization 5209: 5208: 5207: 5202: 5197: 5187: 5182: 5177: 5175:Loss functions 5172: 5167: 5162: 5157: 5152: 5151: 5150: 5140: 5135: 5134: 5133: 5122: 5120: 5116: 5115: 5113: 5112: 5110:Inductive bias 5107: 5102: 5097: 5092: 5087: 5082: 5077: 5072: 5064: 5062: 5056: 5055: 5052: 5050: 5049: 5042: 5035: 5027: 5018: 5017: 5010: 5007: 5006: 5004: 5003: 5001:Video tracking 4998: 4993: 4988: 4983: 4978: 4973: 4971:Remote sensing 4968: 4963: 4958: 4957: 4956: 4951: 4941: 4936: 4931: 4926: 4921: 4916: 4911: 4906: 4901: 4900: 4899: 4889: 4884: 4882:Blob detection 4879: 4874: 4869: 4864: 4859: 4854: 4849: 4844: 4838: 4835: 4834: 4832: 4831: 4830: 4829: 4824: 4814: 4809: 4807:View synthesis 4804: 4799: 4794: 4789: 4784: 4779: 4773: 4771: 4762: 4756: 4755: 4753: 4752: 4751: 4750: 4740: 4738:Motion capture 4735: 4729: 4727: 4723: 4722: 4720: 4719: 4714: 4709: 4704: 4699: 4694: 4689: 4684: 4679: 4674: 4669: 4664: 4659: 4654: 4649: 4643: 4641: 4637: 4636: 4631: 4629: 4628: 4621: 4614: 4606: 4600: 4599: 4593: 4583:Annals of the 4572: 4566: 4553: 4547: 4540: 4539:External links 4537: 4536: 4535: 4530:978-0128149768 4529: 4516: 4510: 4497: 4492:978-0470643853 4491: 4478: 4473:978-1848829343 4472: 4457: 4451: 4436: 4419: 4400: 4394: 4376:Nikos Paragios 4372: 4366: 4360:. John Wiley. 4353: 4347: 4335:Sing Bing Kang 4330: 4324: 4307: 4301: 4288: 4282: 4267: 4261: 4246: 4240: 4227: 4221: 4208: 4202: 4187: 4181: 4165: 4159: 4146: 4140: 4120: 4114: 4097: 4091: 4078: 4072: 4054: 4048: 4031: 4028: 4026: 4025: 3994: 3979: 3953: 3946: 3928: 3851: 3771: 3751: 3730: 3673: 3643: 3585:(3): 211–252. 3562: 3547: 3540: 3522: 3483:(4): 965–973. 3460: 3403: 3377: 3347: 3321: 3291: 3250: 3209: 3202: 3173: 3148: 3089: 3052:(2): 507–543. 3032: 3003:Neurocomputing 2992: 2935: 2910: 2890: 2875: 2834: 2804: 2784: 2766: 2739: 2733:978-1492671206 2732: 2714: 2661: 2603: 2552: 2545: 2525: 2518: 2498: 2491: 2471: 2445: 2438: 2420: 2413: 2386: 2374: 2347: 2328: 2321: 2303: 2290:978-9290830955 2289: 2254: 2247: 2227: 2220: 2199: 2192: 2171: 2164: 2140: 2133: 2111: 2109: 2106: 2105: 2104: 2099: 2094: 2087: 2084: 2082: 2081: 2076: 2071: 2069:Visual agnosia 2066: 2064:Vision science 2061: 2056: 2051: 2046: 2041: 2036: 2031: 2026: 2020: 2018: 2015: 1926: 1923: 1909: 1906: 1905: 1904: 1903: 1902: 1899: 1896: 1887: 1886: 1885: 1879: 1873: 1870: 1861: 1860: 1859: 1852: 1833: 1830: 1814: 1813: 1809: 1808: 1807: 1806: 1791: 1772: 1771: 1770: 1764: 1761: 1758: 1752:Pre-processing 1749: 1725: 1724:System methods 1722: 1709: 1706: 1696: 1693: 1692: 1691: 1679: 1667: 1653: 1650: 1649: 1648: 1640: 1637:people counter 1628: 1615: 1606: 1575: 1558:people counter 1550: 1549: 1522: 1521: 1513: 1506:Identification 1503: 1500:Google Goggles 1483:machine vision 1478: 1475: 1446: 1443: 1442: 1441: 1438: 1433: 1427: 1416:visual effects 1386: 1383: 1316: 1313: 1304: 1301: 1284:machine vision 1279: 1278:Machine vision 1276: 1235: 1232: 1231: 1230: 1227: 1216: 1201: 1194: 1183: 1172: 1150: 1139: 1132: 1104:machine vision 1099: 1096: 1084:Photogrammetry 1081: 1080: 1069: 1057: 1045:Machine vision 1042: 1035: 1028:image analysis 1000:machine vision 996:image analysis 987: 984: 966: 963: 872: 864: 862: 859: 843: 840: 831: 828: 781:false positive 777: 770: 769: 753: 746: 745: 744: 743: 742: 740: 737: 693: 690: 677: 676:Related fields 674: 655:image morphing 623:photogrammetry 600:regularization 540: 537: 533:Machine vision 508:digital images 499: 496: 468:video tracking 427:digital images 406: 405: 403: 402: 395: 388: 380: 377: 376: 373: 372: 366: 363: 362: 359: 358: 355: 354: 349: 344: 339: 333: 328: 327: 324: 323: 320: 319: 314: 309: 304: 299: 290: 285: 280: 274: 269: 268: 265: 264: 261: 260: 255: 250: 245: 240: 239: 238: 228: 223: 218: 217: 216: 211: 206: 196: 191: 189:Earth sciences 186: 181: 179:Bioinformatics 175: 170: 169: 166: 165: 162: 161: 156: 151: 146: 141: 136: 131: 125: 122: 121: 118: 117: 114: 113: 108: 103: 98: 93: 88: 83: 78: 73: 68: 62: 57: 56: 53: 52: 42: 41: 35: 34: 26: 24: 14: 13: 10: 9: 6: 4: 3: 2: 5979: 5968: 5965: 5963: 5960: 5958: 5955: 5954: 5952: 5935: 5932: 5930: 5927: 5926: 5919: 5915: 5912: 5910: 5907: 5906: 5903: 5899: 5898: 5895: 5889: 5886: 5884: 5881: 5879: 5876: 5874: 5871: 5869: 5866: 5864: 5861: 5859: 5856: 5854: 5851: 5849: 5846: 5844: 5841: 5839: 5836: 5834: 5831: 5829: 5826: 5824: 5821: 5819: 5816: 5815: 5813: 5811:Architectures 5809: 5803: 5800: 5798: 5795: 5793: 5790: 5788: 5785: 5783: 5780: 5778: 5775: 5773: 5770: 5768: 5765: 5763: 5760: 5759: 5757: 5755:Organizations 5753: 5747: 5744: 5742: 5739: 5737: 5734: 5732: 5729: 5727: 5724: 5722: 5719: 5717: 5714: 5712: 5709: 5707: 5704: 5702: 5699: 5697: 5694: 5692: 5691:Yoshua Bengio 5689: 5688: 5686: 5682: 5672: 5671:Robot control 5669: 5665: 5662: 5661: 5660: 5657: 5655: 5652: 5650: 5647: 5645: 5642: 5640: 5637: 5635: 5632: 5630: 5627: 5625: 5622: 5621: 5619: 5615: 5609: 5606: 5604: 5601: 5599: 5596: 5594: 5591: 5589: 5588:Chinchilla AI 5586: 5584: 5581: 5579: 5576: 5574: 5571: 5569: 5566: 5564: 5561: 5559: 5556: 5554: 5551: 5549: 5546: 5544: 5541: 5539: 5536: 5534: 5531: 5527: 5524: 5523: 5522: 5519: 5517: 5514: 5512: 5509: 5507: 5504: 5502: 5499: 5497: 5494: 5493: 5491: 5487: 5481: 5478: 5474: 5471: 5469: 5466: 5465: 5464: 5461: 5457: 5454: 5452: 5449: 5447: 5444: 5443: 5442: 5439: 5437: 5434: 5432: 5429: 5427: 5424: 5422: 5419: 5417: 5414: 5412: 5409: 5407: 5404: 5402: 5399: 5397: 5394: 5393: 5391: 5387: 5384: 5380: 5374: 5371: 5369: 5366: 5364: 5361: 5359: 5356: 5354: 5351: 5349: 5346: 5344: 5341: 5340: 5338: 5334: 5328: 5325: 5323: 5320: 5318: 5315: 5313: 5310: 5308: 5305: 5304: 5302: 5298: 5290: 5287: 5286: 5285: 5282: 5280: 5277: 5275: 5272: 5268: 5267:Deep learning 5265: 5264: 5263: 5260: 5256: 5253: 5252: 5251: 5248: 5247: 5245: 5241: 5235: 5232: 5230: 5227: 5223: 5220: 5219: 5218: 5215: 5213: 5210: 5206: 5203: 5201: 5198: 5196: 5193: 5192: 5191: 5188: 5186: 5183: 5181: 5178: 5176: 5173: 5171: 5168: 5166: 5163: 5161: 5158: 5156: 5155:Hallucination 5153: 5149: 5146: 5145: 5144: 5141: 5139: 5136: 5132: 5129: 5128: 5127: 5124: 5123: 5121: 5117: 5111: 5108: 5106: 5103: 5101: 5098: 5096: 5093: 5091: 5088: 5086: 5083: 5081: 5078: 5076: 5073: 5071: 5070: 5066: 5065: 5063: 5061: 5057: 5048: 5043: 5041: 5036: 5034: 5029: 5028: 5025: 5015: 5014: 5013:Main category 5008: 5002: 4999: 4997: 4994: 4992: 4989: 4987: 4984: 4982: 4979: 4977: 4974: 4972: 4969: 4967: 4966:Pose tracking 4964: 4962: 4959: 4955: 4952: 4950: 4947: 4946: 4945: 4942: 4940: 4937: 4935: 4932: 4930: 4927: 4925: 4922: 4920: 4917: 4915: 4912: 4910: 4907: 4905: 4902: 4898: 4895: 4894: 4893: 4890: 4888: 4885: 4883: 4880: 4878: 4875: 4873: 4870: 4868: 4865: 4863: 4860: 4858: 4855: 4853: 4850: 4848: 4845: 4843: 4840: 4839: 4828: 4825: 4823: 4820: 4819: 4818: 4815: 4813: 4810: 4808: 4805: 4803: 4800: 4798: 4795: 4793: 4790: 4788: 4785: 4783: 4780: 4778: 4775: 4774: 4772: 4770: 4766: 4763: 4761: 4757: 4749: 4746: 4745: 4744: 4741: 4739: 4736: 4734: 4731: 4730: 4728: 4724: 4718: 4715: 4713: 4710: 4708: 4705: 4703: 4700: 4698: 4695: 4693: 4690: 4688: 4685: 4683: 4680: 4678: 4675: 4673: 4670: 4668: 4665: 4663: 4660: 4658: 4655: 4653: 4650: 4648: 4645: 4644: 4642: 4638: 4634: 4627: 4622: 4620: 4615: 4613: 4608: 4607: 4604: 4597: 4594: 4591: 4587: 4586: 4580: 4576: 4573: 4570: 4567: 4564: 4560: 4557: 4554: 4551: 4548: 4546: 4543: 4542: 4538: 4532: 4526: 4522: 4517: 4513: 4507: 4503: 4498: 4494: 4488: 4484: 4479: 4475: 4469: 4465: 4464: 4458: 4454: 4448: 4444: 4443: 4437: 4427:on 2014-05-17 4426: 4422: 4416: 4412: 4408: 4407: 4401: 4397: 4391: 4387: 4386: 4381: 4377: 4373: 4369: 4363: 4359: 4354: 4350: 4344: 4340: 4336: 4331: 4327: 4321: 4317: 4313: 4308: 4304: 4298: 4294: 4289: 4285: 4279: 4275: 4274: 4268: 4264: 4258: 4254: 4253: 4247: 4243: 4237: 4233: 4228: 4224: 4218: 4214: 4209: 4205: 4199: 4195: 4194: 4188: 4184: 4178: 4175:. MIT Press. 4174: 4170: 4166: 4162: 4156: 4152: 4147: 4143: 4137: 4134:. MIT Press. 4132: 4131: 4125: 4121: 4117: 4111: 4106: 4105: 4098: 4094: 4088: 4084: 4079: 4075: 4069: 4065: 4064: 4059: 4055: 4051: 4045: 4041: 4040: 4034: 4033: 4029: 4013: 4009: 4005: 3998: 3995: 3990: 3986: 3982: 3976: 3972: 3968: 3964: 3957: 3954: 3949: 3943: 3939: 3932: 3929: 3921: 3917: 3913: 3908: 3903: 3899: 3895: 3890: 3885: 3881: 3877: 3873: 3869: 3862: 3855: 3852: 3841:on 2018-09-07 3837: 3833: 3829: 3825: 3821: 3817: 3813: 3809: 3805: 3801: 3797: 3793: 3789: 3782: 3775: 3772: 3768: 3764: 3761: 3755: 3752: 3746: 3741: 3734: 3731: 3726: 3722: 3717: 3712: 3708: 3704: 3700: 3696: 3692: 3688: 3684: 3677: 3674: 3662: 3658: 3654: 3647: 3644: 3632: 3628: 3624: 3620: 3616: 3611: 3610:1721.1/104944 3606: 3602: 3598: 3593: 3588: 3584: 3580: 3576: 3569: 3567: 3563: 3558: 3551: 3548: 3543: 3537: 3533: 3526: 3523: 3518: 3514: 3509: 3504: 3499: 3494: 3490: 3486: 3482: 3478: 3474: 3467: 3465: 3461: 3456: 3452: 3448: 3444: 3439: 3434: 3430: 3426: 3423:(2): 022005. 3422: 3418: 3414: 3407: 3404: 3392: 3388: 3384: 3380: 3374: 3370: 3366: 3362: 3358: 3351: 3348: 3336: 3332: 3328: 3324: 3318: 3314: 3310: 3306: 3302: 3295: 3292: 3287: 3283: 3278: 3273: 3269: 3265: 3261: 3254: 3251: 3246: 3242: 3237: 3232: 3228: 3224: 3220: 3213: 3210: 3205: 3199: 3195: 3188: 3186: 3184: 3182: 3180: 3178: 3174: 3162: 3158: 3152: 3149: 3144: 3140: 3135: 3130: 3126: 3122: 3117: 3112: 3108: 3104: 3100: 3093: 3090: 3085: 3081: 3076: 3071: 3067: 3063: 3059: 3055: 3051: 3047: 3043: 3036: 3033: 3029: 3024: 3020: 3016: 3012: 3008: 3004: 2996: 2993: 2988: 2984: 2979: 2974: 2970: 2966: 2962: 2958: 2954: 2950: 2946: 2939: 2936: 2924: 2920: 2914: 2911: 2905: 2901: 2894: 2891: 2886: 2882: 2878: 2872: 2867: 2866:1721.1/126644 2862: 2858: 2854: 2850: 2843: 2841: 2839: 2835: 2822: 2815: 2808: 2805: 2801: 2797: 2794: 2788: 2785: 2773: 2769: 2763: 2760:. p. 1. 2759: 2755: 2754: 2746: 2744: 2740: 2735: 2729: 2725: 2718: 2715: 2710: 2706: 2702: 2698: 2694: 2690: 2685: 2680: 2676: 2672: 2665: 2662: 2657: 2653: 2649: 2645: 2641: 2637: 2633: 2629: 2625: 2621: 2614: 2607: 2604: 2599: 2595: 2590: 2585: 2580: 2575: 2571: 2567: 2563: 2556: 2553: 2548: 2542: 2538: 2537: 2529: 2526: 2521: 2515: 2511: 2510: 2502: 2499: 2494: 2488: 2484: 2483: 2475: 2472: 2467: 2463: 2459: 2455: 2449: 2446: 2441: 2435: 2431: 2424: 2421: 2416: 2410: 2406: 2405: 2397: 2395: 2393: 2391: 2387: 2383: 2378: 2375: 2362: 2358: 2351: 2348: 2344: 2340: 2337: 2332: 2329: 2324: 2318: 2314: 2307: 2304: 2296: 2292: 2286: 2282: 2278: 2274: 2267: 2266: 2258: 2255: 2250: 2244: 2240: 2239: 2231: 2228: 2223: 2217: 2213: 2206: 2204: 2200: 2195: 2189: 2185: 2178: 2176: 2172: 2167: 2161: 2157: 2153: 2147: 2145: 2141: 2136: 2130: 2126: 2119: 2117: 2113: 2107: 2103: 2100: 2098: 2095: 2093: 2090: 2089: 2085: 2080: 2079:Visual system 2077: 2075: 2072: 2070: 2067: 2065: 2062: 2060: 2057: 2055: 2054:Space mapping 2052: 2050: 2047: 2045: 2042: 2040: 2037: 2035: 2032: 2030: 2027: 2025: 2022: 2021: 2016: 2014: 2012: 2008: 2003: 2001: 1997: 1994: 1990: 1985: 1983: 1979: 1975: 1971: 1967: 1966:radar imaging 1963: 1959: 1955: 1950: 1947: 1940: 1936: 1931: 1924: 1922: 1918: 1914: 1907: 1900: 1897: 1894: 1893: 1891: 1888: 1883: 1880: 1877: 1874: 1871: 1868: 1867: 1865: 1862: 1857: 1853: 1850: 1846: 1842: 1838: 1834: 1831: 1828: 1827: 1825: 1824: 1820: 1816: 1815: 1811: 1810: 1804: 1800: 1796: 1792: 1789: 1785: 1781: 1780: 1778: 1777: 1773: 1768: 1765: 1762: 1759: 1756: 1755: 1753: 1750: 1747: 1743: 1742:range sensors 1739: 1738:image sensors 1735: 1732: 1731: 1730: 1723: 1721: 1719: 1714: 1707: 1705: 1702: 1694: 1689: 1685: 1684: 1680: 1677: 1673: 1672: 1668: 1665: 1664: 1660: 1659: 1658: 1651: 1646: 1645: 1641: 1638: 1634: 1633: 1629: 1626: 1622: 1619: 1616: 1613: 1611: 1607: 1604: 1600: 1596: 1593: 1589: 1585: 1581: 1580: 1576: 1573: 1572:assembly line 1569: 1568: 1564: 1563: 1559: 1554: 1547: 1543: 1542: 1538: 1537: 1536: 1533: 1531: 1527: 1519: 1518: 1514: 1511: 1507: 1504: 1501: 1497: 1494:(also called 1493: 1492: 1488: 1487: 1486: 1484: 1476: 1474: 1472: 1468: 1464: 1460: 1456: 1451: 1445:Typical tasks 1444: 1439: 1437: 1434: 1431: 1428: 1425: 1421: 1417: 1413: 1412: 1411: 1408: 1399: 1391: 1384: 1382: 1380: 1379: 1374: 1370: 1369: 1364: 1360: 1356: 1352: 1348: 1344: 1340: 1332: 1331:stereo camera 1328: 1327: 1321: 1314: 1312: 1310: 1302: 1300: 1298: 1293: 1292:computer chip 1289: 1285: 1277: 1275: 1273: 1269: 1265: 1261: 1257: 1249: 1233: 1228: 1225: 1221: 1217: 1214: 1210: 1206: 1202: 1199: 1195: 1192: 1188: 1184: 1181: 1177: 1174:Interaction, 1173: 1170: 1166: 1162: 1158: 1154: 1151: 1148: 1144: 1140: 1137: 1133: 1130: 1126: 1125: 1121: 1117: 1116:deep learning 1112: 1108: 1105: 1097: 1095: 1093: 1089: 1085: 1078: 1074: 1070: 1066: 1062: 1058: 1055: 1051: 1046: 1043: 1040: 1036: 1033: 1029: 1025: 1022: 1021: 1020: 1017: 1015: 1011: 1007: 1003: 1001: 997: 993: 985: 983: 981: 977: 973: 964: 959: 955: 951: 947: 943: 939: 935: 931: 927: 923: 919: 915: 911: 907: 903: 899: 895: 891: 890:visualization 887: 883: 879: 875: 869: 860: 858: 856: 852: 851:path planning 848: 841: 839: 837: 829: 827: 825: 820: 818: 814: 810: 806: 805:deep learning 802: 799: 794: 782: 774: 765: 761: 757: 750: 738: 736: 734: 731:even require 730: 729:image sensors 726: 722: 718: 714: 710: 706: 702: 701:image sensors 698: 691: 686: 682: 675: 673: 671: 666: 664: 660: 656: 652: 648: 644: 640: 636: 632: 628: 624: 620: 616: 612: 609: 605: 601: 597: 593: 589: 584: 582: 578: 574: 570: 566: 562: 558: 553: 550: 546: 538: 536: 534: 530: 526: 521: 517: 513: 509: 505: 497: 495: 491: 489: 485: 481: 477: 473: 469: 465: 461: 457: 453: 448: 445: 440: 437: 432: 428: 424: 420: 416: 412: 401: 396: 394: 389: 387: 382: 381: 379: 378: 371: 368: 367: 361: 360: 353: 350: 348: 345: 343: 340: 338: 335: 334: 331: 326: 325: 318: 315: 313: 310: 308: 305: 303: 300: 298: 294: 291: 289: 286: 284: 281: 279: 276: 275: 272: 267: 266: 259: 256: 254: 251: 249: 246: 244: 241: 237: 236:Mental health 234: 233: 232: 229: 227: 224: 222: 219: 215: 212: 210: 207: 205: 202: 201: 200: 199:Generative AI 197: 195: 192: 190: 187: 185: 182: 180: 177: 176: 173: 168: 167: 160: 157: 155: 152: 150: 147: 145: 142: 140: 139:Deep learning 137: 135: 132: 130: 127: 126: 120: 119: 112: 109: 107: 104: 102: 99: 97: 94: 92: 89: 87: 84: 82: 79: 77: 74: 72: 69: 67: 64: 63: 60: 55: 54: 48: 44: 43: 40: 36: 32: 31: 19: 5777:Hugging Face 5741:David Silver 5389:Audio–visual 5243:Applications 5222:Augmentation 5067: 5011: 4904:Eye tracking 4760:Applications 4726:Technologies 4712:Segmentation 4632: 4582: 4520: 4501: 4482: 4462: 4441: 4429:. Retrieved 4425:the original 4405: 4388:. Springer. 4384: 4357: 4338: 4315: 4295:. Springer. 4292: 4272: 4251: 4231: 4212: 4196:. Springer. 4192: 4172: 4150: 4130:Robot Vision 4129: 4103: 4082: 4062: 4038: 4016:. Retrieved 4007: 3997: 3962: 3956: 3937: 3931: 3871: 3867: 3854: 3843:. Retrieved 3836:the original 3791: 3787: 3774: 3754: 3733: 3690: 3686: 3676: 3665:. Retrieved 3656: 3646: 3635:. Retrieved 3582: 3578: 3556: 3550: 3531: 3525: 3480: 3476: 3420: 3416: 3406: 3395:. Retrieved 3360: 3350: 3339:. Retrieved 3304: 3294: 3267: 3263: 3253: 3226: 3222: 3212: 3193: 3165:. Retrieved 3163:. 2024-09-13 3160: 3151: 3109:(12): 1869. 3106: 3102: 3092: 3049: 3045: 3035: 3026: 3006: 3002: 2995: 2952: 2948: 2938: 2927:. Retrieved 2913: 2903: 2899: 2893: 2848: 2825:. Retrieved 2820: 2807: 2787: 2776:. Retrieved 2752: 2723: 2717: 2674: 2670: 2664: 2623: 2619: 2606: 2569: 2565: 2555: 2535: 2528: 2508: 2501: 2481: 2474: 2457: 2448: 2429: 2423: 2403: 2381: 2377: 2365:. Retrieved 2350: 2331: 2312: 2306: 2264: 2257: 2237: 2230: 2211: 2183: 2155: 2127:. Springer. 2124: 2005:As of 2016, 2004: 1998: 1986: 1951: 1948: 1944: 1919: 1915: 1911: 1889: 1863: 1823:segmentation 1817: 1774: 1751: 1733: 1727: 1715: 1711: 1698: 1687: 1683:Optical flow 1681: 1675: 1669: 1661: 1655: 1642: 1630: 1620: 1608: 1591: 1577: 1565: 1539: 1534: 1523: 1515: 1505: 1495: 1489: 1480: 1470: 1452: 1448: 1430:Surveillance 1419: 1409: 1405: 1376: 1366: 1358: 1350: 1339:submersibles 1336: 1324: 1306: 1281: 1271: 1253: 1219: 1213:mobile robot 1204: 1203:Navigation, 1197: 1175: 1156: 1142: 1128: 1101: 1098:Applications 1082: 1049: 1038: 1031: 1018: 1009: 1004: 989: 986:Distinctions 976:optimization 968: 965:Other fields 944:that are in 845: 833: 821: 809:Neocognitron 797: 793:Neurobiology 791: 739:Neurobiology 695: 667: 585: 577:optical flow 554: 542: 501: 492: 449: 441: 410: 409: 283:Chinese room 172:Applications 85: 5925:Categories 5873:Autoencoder 5828:Transformer 5696:Alex Graves 5644:OpenAI Five 5548:IBM Watsonx 5170:Convolution 5148:Overfitting 4812:Visual hull 4707:Researchers 3874:(5): 1657. 3693:(1): 1–68. 3508:2066/184075 3009:: 439–453. 2908:pages 60–62 2671:IEEE Access 2466:1721.1/6125 2315:. Thomson. 1767:Scale space 1599:data matrix 1477:Recognition 1414:Support of 1054:bin picking 956:that's for 760:sea urchins 588:scale-space 516:engineering 312:Turing test 288:Friendly AI 59:Major goals 5951:Categories 5914:Technology 5767:EleutherAI 5726:Fei-Fei Li 5721:Yann LeCun 5634:Q-learning 5617:Decisional 5543:IBM Watson 5451:Midjourney 5343:TensorFlow 5190:Activation 5143:Regression 5138:Clustering 4682:Morphology 4640:Categories 4431:2007-06-13 4058:David Marr 3845:2018-09-14 3745:1511.02999 3667:2022-12-23 3637:2020-11-20 3559:. Pearson. 3397:2022-11-06 3341:2022-11-06 3167:2024-09-19 2929:2018-01-10 2778:2018-01-30 2684:1907.09408 2108:References 1972:scanners, 1805:or points. 1793:Localized 1718:inpainting 1584:characters 1459:processing 1120:depth maps 1068:radiology. 972:statistics 880:, such as 801:neural net 661:and early 608:projective 565:algorithms 498:Definition 419:processing 317:Regulation 271:Philosophy 226:Healthcare 221:Government 123:Approaches 5797:MIT CSAIL 5762:Anthropic 5731:Andrew Ng 5629:AlphaZero 5473:VideoPoet 5436:AlphaFold 5373:MindSpore 5327:SpiNNaker 5322:Memristor 5229:Diffusion 5205:Rectifier 5185:Batchnorm 5165:Attention 5160:Adversary 3898:1424-8220 3816:1057-7149 3707:1529-1006 3657:TopTen.ai 3619:0920-5691 3592:1409.0575 3517:2041-210X 3455:230639179 3447:1757-899X 3387:235207036 3331:218564267 3286:2197-4225 3270:(1): 14. 3245:2197-4225 3229:(1): 11. 3125:2304-8158 3066:1134-3060 3023:219470398 2969:2398-6352 2758:Wiley-VCH 2709:198147317 2598:1573-1405 1819:Detection 1663:Egomotion 1635:(SRT) in 1625:emotions. 1517:Detection 1463:analyzing 1455:acquiring 1368:Curiosity 1326:Curiosity 1071:Finally, 878:3D models 643:Eigenface 423:analyzing 415:acquiring 347:AI winter 248:Military 111:AI safety 5905:Portals 5664:Auto-GPT 5496:Word2vec 5300:Hardware 5217:Datasets 5119:Concepts 4717:Software 4677:Learning 4667:Geometry 4647:Datasets 4569:CVonline 4559:Archived 4411:Springer 4382:(2005). 4337:(2004). 4314:(2003). 4171:(1993). 4126:(1986). 4060:(1982). 4012:Archived 3989:14111100 3920:Archived 3916:29789447 3832:51867241 3824:30059300 3763:Archived 3725:31313636 3661:Archived 3631:Archived 3391:Archived 3335:Archived 3143:38928810 3134:11202458 3084:29962832 2987:33420381 2955:(1): 5. 2923:Archived 2885:31373273 2827:11 March 2796:Archived 2772:Archived 2648:26017442 2572:(1): 1. 2361:Archived 2339:Archived 2295:Archived 2017:See also 1925:Hardware 1797:such as 1671:Tracking 1588:indexing 1303:Military 1234:Medicine 1224:indexing 1207:, by an 980:geometry 922:robotics 764:features 756:starfish 713:infrared 370:Glossary 364:Glossary 342:Progress 337:Timeline 297:Takeover 258:Projects 231:Industry 194:Finance 184:Deepfake 134:Symbolic 106:Robotics 81:Planning 5787:Meta AI 5624:AlphaGo 5608:PanGu-Σ 5578:ChatGPT 5553:Granite 5501:Seq2seq 5480:Whisper 5401:WaveNet 5396:AlexNet 5368:Flux.jl 5348:PyTorch 5200:Sigmoid 5195:Softmax 5060:General 3907:5982167 3876:Bibcode 3868:Sensors 3796:Bibcode 3716:6640856 3627:2930547 3485:Bibcode 3425:Bibcode 3075:6003396 3028:others. 2978:7794558 2689:Bibcode 2656:3074096 2628:Bibcode 2367:18 July 1937:with a 1845:spatial 1837:salient 1799:corners 1782:Lines, 1381:rover. 1264:tumours 1138:system; 1061:imaging 709:visible 670:feature 592:shading 539:History 352:AI boom 330:History 253:Physics 5802:Huawei 5782:OpenAI 5684:People 5654:MuZero 5516:Gemini 5511:Claude 5446:DALL-E 5358:Theano 4527: 4508: 4489: 4470: 4449: 4417: 4392: 4364: 4345: 4322: 4299: 4280: 4259: 4238: 4219: 4200: 4179: 4157: 4138: 4112: 4089: 4070: 4063:Vision 4046: 4018:May 3, 3987: 3977: 3944: 3914: 3904: 3896: 3830: 3822: 3814: 3723: 3713: 3705: 3625: 3617: 3538: 3515: 3453: 3445: 3385: 3375: 3329: 3319: 3284: 3243: 3200: 3161:London 3141: 3131: 3123: 3082: 3072: 3064: 3021: 2985: 2975: 2967: 2883: 2873: 2764: 2730: 2707: 2654: 2646: 2620:Nature 2596: 2543: 2516: 2489: 2436: 2411: 2319: 2287: 2245: 2218: 2190: 2162: 2131: 1941:sensor 1788:ridges 1605:codes. 1378:Yutu-2 1222:, for 1159:, for 928:, and 900:, and 725:optics 579:, and 512:videos 436:retina 302:Ethics 5868:Mamba 5639:SARSA 5603:LLaMA 5598:BLOOM 5583:GPT-J 5573:GPT-4 5568:GPT-3 5563:GPT-2 5558:GPT-1 5521:LaMDA 5353:Keras 3985:S2CID 3923:(PDF) 3864:(PDF) 3839:(PDF) 3828:S2CID 3784:(PDF) 3740:arXiv 3623:S2CID 3587:arXiv 3451:S2CID 3383:S2CID 3327:S2CID 3103:Foods 3019:S2CID 2881:S2CID 2817:(PDF) 2705:S2CID 2679:arXiv 2652:S2CID 2616:(PDF) 2298:(PDF) 2269:(PDF) 2086:Lists 1970:lidar 1939:LiDAR 1803:blobs 1784:edges 1595:ASCII 1288:Wafer 1248:DARPA 1145:, an 214:Music 209:Audio 5792:Mila 5593:PaLM 5526:Bard 5506:BERT 5489:Text 5468:Sora 4585:BMVA 4525:ISBN 4506:ISBN 4487:ISBN 4468:ISBN 4447:ISBN 4415:ISBN 4390:ISBN 4362:ISBN 4343:ISBN 4320:ISBN 4297:ISBN 4278:ISBN 4257:ISBN 4236:ISBN 4217:ISBN 4198:ISBN 4177:ISBN 4155:ISBN 4136:ISBN 4110:ISBN 4087:ISBN 4068:ISBN 4044:ISBN 4020:2016 3975:ISBN 3942:ISBN 3912:PMID 3894:ISSN 3820:PMID 3812:ISSN 3721:PMID 3703:ISSN 3615:ISSN 3536:ISBN 3513:ISSN 3443:ISSN 3373:ISBN 3317:ISBN 3282:ISSN 3241:ISSN 3198:ISBN 3139:PMID 3121:ISSN 3080:PMID 3062:ISSN 2983:PMID 2965:ISSN 2906:(6). 2871:ISBN 2829:2024 2762:ISBN 2728:ISBN 2644:PMID 2594:ISSN 2541:ISBN 2514:ISBN 2487:ISBN 2434:ISBN 2409:ISBN 2369:2017 2317:ISBN 2285:ISBN 2243:ISBN 2216:ISBN 2188:ISBN 2160:ISBN 2129:ISBN 1991:and 1847:and 1786:and 1688:i.e. 1676:e.g. 1601:and 1592:e.g. 1471:e.g. 1420:e.g. 1373:CNSA 1371:and 1363:NASA 1359:e.g. 1351:e.g. 1347:SLAM 1272:e.g. 1220:e.g. 1205:e.g. 1198:e.g. 1176:e.g. 1157:e.g. 1143:e.g. 1129:e.g. 1090:vs. 1050:e.g. 1039:e.g. 1032:e.g. 1026:and 1010:e.g. 998:and 952:and 803:and 798:e.g. 758:and 602:and 442:The 5533:NMT 5416:OCR 5411:HWR 5363:JAX 5317:VPU 5312:TPU 5307:IPU 5131:SGD 3967:doi 3902:PMC 3884:doi 3804:doi 3711:PMC 3695:doi 3605:hdl 3597:doi 3583:115 3503:hdl 3493:doi 3433:doi 3421:981 3365:doi 3309:doi 3272:doi 3231:doi 3129:PMC 3111:doi 3070:PMC 3054:doi 3011:doi 3007:407 2973:PMC 2957:doi 2861:hdl 2853:doi 2697:doi 2636:doi 2624:521 2584:hdl 2574:doi 2462:hdl 2277:doi 1375:'s 1365:'s 1343:UAV 1211:or 1163:or 978:or 715:or 510:or 204:Art 5953:: 4581:, 4413:. 4409:. 4010:. 4006:. 3983:. 3973:. 3918:. 3910:. 3900:. 3892:. 3882:. 3872:18 3870:. 3866:. 3826:. 3818:. 3810:. 3802:. 3792:27 3790:. 3786:. 3719:. 3709:. 3701:. 3691:20 3689:. 3685:. 3659:. 3655:. 3629:. 3621:. 3613:. 3603:. 3595:. 3581:. 3577:. 3565:^ 3511:. 3501:. 3491:. 3479:. 3475:. 3463:^ 3449:. 3441:. 3431:. 3419:. 3415:. 3389:. 3381:. 3371:. 3359:. 3333:. 3325:. 3315:. 3303:. 3280:. 3266:. 3262:. 3239:. 3225:. 3221:. 3176:^ 3159:. 3137:. 3127:. 3119:. 3107:13 3105:. 3101:. 3078:. 3068:. 3060:. 3050:25 3048:. 3044:. 3025:. 3017:. 3005:. 2981:. 2971:. 2963:. 2951:. 2947:. 2921:. 2904:35 2902:. 2879:. 2869:. 2859:. 2837:^ 2819:. 2770:. 2742:^ 2703:. 2695:. 2687:. 2673:. 2650:. 2642:. 2634:. 2622:. 2618:. 2592:. 2582:. 2570:77 2568:. 2564:. 2460:. 2389:^ 2359:. 2293:. 2283:. 2271:. 2202:^ 2174:^ 2143:^ 2115:^ 1980:, 1976:, 1968:, 1964:, 1960:, 1956:, 1933:A 1801:, 1720:. 1603:QR 1461:, 1457:, 1422:, 1361:, 1299:. 1266:, 1155:, 1094:. 1016:. 994:, 974:, 924:, 920:, 916:, 912:, 896:, 888:, 884:, 819:. 711:, 665:. 653:, 583:. 490:. 482:, 474:, 470:, 466:, 462:, 458:, 454:, 421:, 417:, 5046:e 5039:t 5032:v 4625:e 4618:t 4611:v 4533:. 4514:. 4495:. 4476:. 4455:. 4434:. 4398:. 4370:. 4351:. 4328:. 4305:. 4286:. 4265:. 4244:. 4225:. 4206:. 4185:. 4163:. 4144:. 4118:. 4095:. 4076:. 4052:. 4022:. 3991:. 3969:: 3950:. 3886:: 3878:: 3848:. 3806:: 3798:: 3748:. 3742:: 3727:. 3697:: 3670:. 3640:. 3607:: 3599:: 3589:: 3544:. 3519:. 3505:: 3495:: 3487:: 3481:9 3457:. 3435:: 3427:: 3400:. 3367:: 3344:. 3311:: 3288:. 3274:: 3268:7 3247:. 3233:: 3227:7 3206:. 3170:. 3145:. 3113:: 3086:. 3056:: 3013:: 2989:. 2959:: 2953:4 2932:. 2887:. 2863:: 2855:: 2831:. 2781:. 2736:. 2711:. 2699:: 2691:: 2681:: 2675:7 2658:. 2638:: 2630:: 2600:. 2586:: 2576:: 2549:. 2522:. 2495:. 2468:. 2464:: 2442:. 2417:. 2371:. 2325:. 2279:: 2251:. 2224:. 2196:. 2168:. 2137:. 1851:. 1821:/ 1790:. 1748:. 1590:( 1432:. 1215:; 1182:; 1171:; 1149:; 960:. 870:. 399:e 392:t 385:v 295:/ 20:)

Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.

Index