Computer vision - Knowledge (XXG)

1083: 974:. 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. 1379:

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.

1504:; 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. 1685:

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.

688: 47: 1902: 833:—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. 1283:. 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. 756: 1292: 1492: – 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. 780: 845:. 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. 1525: 1079:

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:

1028:). 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. 1445:, 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. 1716:, 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 954:. 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. 5894: 5874: 1701:

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.

679:-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. 1370: 1362: 803:

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 (

1918:

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.

1211: 1006:, 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. 1317:). 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 ( 1917:

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

785:

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

1675:

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

802:

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

1684:

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

1378:

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

2999:

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

1892:

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

1967:

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

1078:

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

1373:

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

1700:

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

1884:

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

1266:

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

1421:

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.

1258:, 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 864:. 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 1246:, 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. 1726:– 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: 1516: – 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 1039:

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

1628:

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:

1325:, 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 1019:

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,

1888:

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.

1215: 1212: 773:. 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. 558:

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 1893:

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.

1329:. 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, 1542: – 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 3891: 1214: 2972:

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".

941:

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

1838:– 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: 3752: 927:

and digital libraries. The core challenges are the acquisition, processing, analysis and rendering of visual information (mainly images and video). Application areas include industrial quality control,

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

1013:, 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. 1242:

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.

1082: 1470:) – 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, 5768: 3545:

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).

742:

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.

2819:

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".

2332: 1457:

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.

1586:

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: 3832: 4643: 4550: 538:

AI and computer vision are closely linked, with AI enabling machines to interpret and understand visual data. Through techniques like image recognition and object detection,

5610: 5016: 1520:

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).

1213: 397: 2767: 4673: 4595: 4570:

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.

1650:, 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. 980:

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,

3983: 4967: 4668: 1132: 3807: 1662:, 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. 4900: 4633: 570:

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

2894: 4628: 158: 2915:

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

1798:– 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: 1279:

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

3128: 4663: 1921:

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).

2641:

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

1956:, etc. Such hardware captures "images" that are then processed often using the same computer vision algorithms used to process visible-light images. 4731: 1676:

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: 3734: 786:

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

593:

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

5126: 1140: 193: 171: 1480: – 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.

5009: 4748: 633: 95: 1035:

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

4768: 4481: 4422: 4390: 4365: 4337: 4318: 4295: 4272: 4253: 4232: 4211: 4192: 4173: 4152: 4130: 4111: 4085: 4062: 4043: 4019: 3950: 3917: 3511: 3348: 3292: 3173: 2846: 2737: 2516: 2489: 2462: 2409: 2384: 2328: 2292: 2218: 2191: 2163: 2135: 2104: 1924:

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

1318: 390: 316: 270: 225: 220: 5799: 4678: 4648: 4638: 4618: 4588: 932:

and visualization, surveying, robotics, multimedia systems, virtual heritage, special effects in movies and television, and computer games.

653: 3602: 1968:

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

1638: – 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. 5900: 5451: 5188: 1747: 1344: 761:

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: 792:

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

4833: 4658: 4500: 4462: 4443: 2703: 2260: 2073: 687: 329: 198: 188: 178: 5712: 5339: 5146: 5002: 4688: 301: 247: 213: 80: 624:. With the advent of optimization methods for camera calibration, it was realized that a lot of the ideas were already explored in 4382: 5667: 4838: 1107: 648:. This decade also marked the first time statistical learning techniques were used in practice to recognize faces in images (see 383: 287: 133: 3071:"Optimizing Strawberry Disease and Quality Detection with Vision Transformers and Attention-Based Convolutional Neural Networks" 2356:

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

2030: 1047:

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

605:. Researchers also realized that many of these mathematical concepts could be treated within the same optimization framework as 4823: 4581: 1619:- deals with recognizing the activity from a series of video frames, such as, if the person is picking up an object or walking. 65: 5854: 5794: 5392: 2764: 2266: 487: 3741:." Information Processing and Management of Uncertainty in Knowledge-Based Systems. Springer International Publishing, 2014. 2743: 1901: 3362: 3306: 1751:– Image features at various levels of complexity are extracted from the image data. Typical examples of such features are: 1558:

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

46: 5387: 5076: 4932: 4863: 4714: 2068: 1550: 1512: 641: 1830:

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

5938: 5829: 5183: 5136: 5131: 3975: 1497: 606: 1090:

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

542:

powers computer vision to automate tasks such as facial recognition, autonomous driving, and medical imaging analysis.

5880: 5176: 5102: 4683: 4029: 1925: 1407: 1231: 1162: 1009:

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

252: 203: 100: 3632: 652:). Toward the end of the 1990s, a significant change came about with the increased interaction between the fields of 3277:

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

5504: 5439: 5040: 4828: 3732:

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

2063: 1717: 1658: – to determine, for each point in the image, how that point is moving relative to the image plane, 1151: 1048: 947: 920: 75: 4567: 4530: 1313:, land-based vehicles (small robots with wheels, cars, or trucks), aerial vehicles, and unmanned aerial vehicles ( 755: 730:. The process by which light interacts with surfaces is explained using physics. Physics explains the behavior of 5933: 5905: 5763: 5402: 5233: 5056: 4880: 4793: 2890: 2005: 1982: 1960: 1906: 1820: 1581: 807: 770: 711: 676: 153: 3383:

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

2310: 5928: 5804: 5061: 4984: 4858: 1964: 1953: 1945: 1816: 1766: 929: 896: 563: 277: 4009: 1959:

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

1374:

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

1365:

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

1262:

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

1807:

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

5849: 5834: 5487: 5482: 5382: 5250: 5031: 4920: 4910: 4653: 4222: 3069:

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

2020: 1974:

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

1812: 1808: 1481: 1314: 1227: 551: 58: 38: 3445:"trackdem: Automated particle tracking to obtain population counts and size distributions from videos in r" 1291: 5809: 5569: 5288: 5283: 4957: 4925: 4704: 1978: 1827: 1538: 1195: 1063: 637: 148: 3933:

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

3653:

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

5839: 5824: 5789: 5477: 5377: 5245: 4962: 4773: 4719: 3731: 3191:"Rubber artificial skin layer with flexible structure for shape estimation of micro-undulation surfaces" 2000: 1555: 900: 657: 524: 443: 5707: 4355: 822:, is an early example of computer vision taking direct inspiration from neurobiology, specifically the 3232:"Dexterous object manipulation by a multi-fingered robotic hand with visual-tactile fingertip sensors" 2786:"Computational Vision and Business Intelligence in the Beauty Segment - An Analysis through Instagram" 2317:

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

779: 5859: 5814: 5260: 5205: 5051: 5046: 4885: 4868: 4848: 4818: 4376: 3847: 3767: 3456: 3443:

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

3396: 2660: 2599: 1995: 1933: 1929: 1615: 1517: 1124: 1059: 602: 463: 90: 1646: – following the movements of a (usually) smaller set of interest points or objects ( 1524: 5434: 5412: 5161: 5156: 5114: 5066: 4890: 4753: 3833:"Segment-Tube: Spatio-Temporal Action Localization in Untrimmed Videos with Per-Frame Segmentation" 1603: 1589: 1259: 1044: 916: 703: 621: 614: 610: 555: 519: 503: 242: 5873: 706:

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

5819: 5397: 5226: 4905: 4813: 4798: 4758: 4561: 4095: 3956: 3799: 3711: 3655:"Emotional Expressions Reconsidered: Challenges to Inferring Emotion From Human Facial Movements" 3594: 3558: 3422: 3354: 3298: 2990: 2852: 2785: 2676: 2650: 2623: 1853: 1794: 1713: 1462: 1263: 1230:, or medical image processing, characterized by the extraction of information from image data to 1180: 1158: 991:

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

861: 819: 814:

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

645: 613:. By the 1990s, some of the previous research topics became more active than others. Research in 475: 471: 292: 1024:, vision-based robots and systems for vision-based inspection, measurement, or picking (such as 3014:"Plant Species Identification Using Computer Vision Techniques: A Systematic Literature Review" 1595:

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

5885: 5677: 5329: 5200: 5193: 4843: 4788: 4740: 4496: 4477: 4458: 4439: 4418: 4386: 4361: 4333: 4314: 4291: 4268: 4249: 4228: 4207: 4188: 4169: 4148: 4126: 4107: 4081: 4058: 4039: 4015: 3946: 3913: 3883: 3865: 3791: 3783: 3751:

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

3692: 3674: 3586: 3507: 3484: 3414: 3344: 3329:"State-of-the-Art Analysis of Modern Drowsiness Detection Algorithms Based on Computer Vision" 3288: 3253: 3212: 3169: 3110: 3092: 3051: 3033: 2954: 2936: 2842: 2733: 2699: 2615: 2565: 2512: 2485: 2479: 2458: 2405: 2380: 2288: 2256: 2214: 2187: 2159: 2131: 2100: 2045: 2015: 2010: 1971: 1847: 1672: 1599:

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

1339: 1297: 1118: 985: 977: 908: 888: 842: 830: 739: 723: 625: 617: 587: 567: 479: 451: 70: 3831:

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

5630: 5620: 5427: 5221: 5171: 5166: 5109: 5097: 4952: 4915: 4763: 4623: 4351: 4283: 4140: 3938: 3935:

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

3873: 3855: 3775: 3682: 3666: 3576: 3568: 3474: 3464: 3404: 3400: 3336: 3280: 3243: 3202: 3100: 3082: 3041: 3025: 2982: 2944: 2928: 2832: 2824: 2668: 2607: 2555: 2545: 2433: 2248: 1790: 1770: 1488: 1438: 1430: 1321:), for detecting obstacles. It can also be used for detecting certain task-specific events, 1280: 1239: 995: 963: 924: 912: 892: 880: 874: 853: 691: 579: 455: 430: 418: 208: 143: 128: 5743: 5687: 5509: 5151: 5071: 4947: 4895: 4556: 4534: 3738: 2774:." Proceedings of International Conference on Robotics and Automation. Vol. 2. IEEE, 1997. 2771: 2314: 1949: 1873:

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

1759: 1671:

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

1395: 1268: 1036: 1032: 904: 727: 665: 528: 483: 459: 17: 3409: 3384: 1804:

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

1201:

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

3851: 3771: 3460: 3105: 3070: 2664: 2603: 5717: 5682: 5672: 5497: 5255: 5081: 4972: 4942: 4853: 4778: 4709: 4347: 4306: 4243: 3878: 3687: 3654: 3046: 3013: 2949: 2916: 2425: 2040: 2035: 1774: 1755: 1642: 1608: 1529: 1471: 1454: 1434: 1387: 1326: 1255: 1136: 1075: 1055: 1016: 999: 971: 967: 787: 719: 629: 575: 532: 467: 422: 2584: 1841:

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

1086:

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

1051:. A significant part of this field is devoted to applying these methods to image data. 5922: 5662: 5642: 5559: 5238: 4937: 4546: 3546: 3426: 3358: 3340: 3302: 2994: 2680: 2560: 2208: 2123: 2050: 2025: 1937: 1543: 1302: 1087: 857: 823: 811: 735: 715: 707: 507: 426: 138: 3960: 3803: 2856: 5748: 5579: 4875: 3598: 3129:"New AI model developed at Western detects strawberry diseases, takes aim at waste" 2627: 1709: 1654: 1559: 1426: 1401: 1184: 815: 799: 583: 414: 282: 4100: 4074: 3753:"Joint Video Object Discovery and Segmentation by Coupled Dynamic Markov Networks" 3284: 2235: 1844:

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

3273:"Drowsiness Detection of a Driver using Conventional Computer Vision Application" 2986: 2723: 2506: 2452: 2374: 1732:

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

5844: 5615: 5524: 5519: 5141: 5119: 4783: 2870:

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

2672: 1738: 1570: 1441:

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

1310: 1025: 669: 594: 515: 506:

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

311: 296: 3942: 3328: 3272: 3248: 3231: 3207: 3190: 2932: 2329:"Star Trek's "tricorder" medical scanner just got closer to becoming a reality" 1611:

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

1474:, and LikeThat provide stand-alone programs that illustrate this functionality. 883:

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

5738: 5697: 5692: 5605: 5514: 5422: 5334: 5314: 4540: 3572: 3029: 2550: 2533: 1689: 1369: 1254:

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

943: 766: 550:

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

4524:– a complete list of papers of the most relevant computer vision conferences. 3869: 3787: 3779: 3678: 3670: 3590: 3488: 3418: 3257: 3216: 3096: 3037: 2940: 2569: 2252: 829:

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

5733: 5702: 5600: 5444: 5407: 5344: 5298: 5293: 5278: 3469: 3444: 2729: 1811:

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

1634: 1361: 1091: 649: 571: 346: 110: 4994: 4033: 3887: 3795: 3696: 3114: 3055: 2958: 2619: 3624: 3087: 2828: 5635: 5467: 4328:

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

4163: 3710:

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

3581: 2837: 1741:

representation to enhance image structures at locally appropriate scales.

1735:

Contrast enhancement to ensure that relevant information can be detected.

1501: 1309:

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

951: 884: 762: 661: 183: 105: 2611: 2184:

Computer Vision and Applications, A Guide for Students and Practitioners

5758: 5595: 5549: 5472: 5372: 5367: 5319: 4537:– news, source code, datasets and job offers related to computer vision 4527: 4412: 3479: 2437: 2404:. Cambridge, Massachusetts London, England: The MIT Press. p. 28. 1596: 1574: 598: 582:, representation of objects as interconnections of smaller structures, 351: 3860: 2821:

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

5773: 5753: 5625: 5417: 4549:– supporting computer vision research within the UK via the BMVC and 4521: 2307: 1864:

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

1349: 1235: 731: 435: 4516: 2505:

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

2244: 3716: 3189:

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

2655: 1712:, which, besides various types of light-sensitive cameras, include 1002:

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

5574: 5554: 5544: 5539: 5534: 5529: 5492: 5324: 4573: 3563: 1941: 1910: 1900: 1784:

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

1729:

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

1566: 1523: 1368: 1360: 1290: 1219: 1209: 1081: 686: 511: 3385:"Computer vision based fatigue detection using facial parameters" 1981:

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

1856:– comparing and combining two different views of the same object. 5564: 1453:

The classical problem in computer vision, image processing, and

1334: 4998: 4577: 3625:"AI Image Recognition: Inevitable Trending of Modern Lifestyle" 1507:

Several specialized tasks based on recognition exist, such as:

1161:

model has been developed to help farmers automatically detect

562:

What distinguished computer vision from the prevalent field of

4396: 3976:"A Third Type Of Processor For VR/AR: Movidius' Myriad 2 VPU" 734:

which are a core part of most imaging systems. Sophisticated

4433: 4378:

Digital Image Processing: An Algorithmic Approach Using Java

3333:

2021 29th Conference of Open Innovations Association (FRUCT)

2765:

Stereo vision-based mapping and navigation for mobile robots

2722:

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

640:

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

45: 4493:

Feature Extraction and Image Processing for Computer Vision

4221:

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

2532:

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

1496:

Currently, the best algorithms for such tasks are based on

3912:. New York: John Wiley & Sons, Inc. pp. 643–646. 1850:– classifying a detected object into different categories. 1412:

Tracking and counting organisms in the biological sciences

769:, which are correlated with "nodes" that represent visual 2379:. Springer Science & Business Media. pp. 10–16. 4145:

Three-Dimensional Computer Vision, A Geometric Viewpoint

3389:

IOP Conference Series: Materials Science and Engineering

1500:. An illustration of their capabilities is given by the 2534:"Guest Editorial: Machine Learning for Computer Vision" 2177: 2175: 2118: 2116: 1885:

requirements are entirely topics for further research.

962:

The fields most closely related to computer vision are

4183:

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

3438: 3436: 2583:

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

539: 4224:

Computer Vision – Three-Dimensional Data from Images

2795:. American Research Institute for Policy Development 1437:

and understanding digital images, and extraction of

1301:, an example of an uncrewed land-based vehicle. The 5782: 5726: 5655: 5588: 5460: 5360: 5353: 5307: 5271: 5214: 5090: 5030: 4739: 4730: 4697: 4611: 4455:

Algorithms for Image Processing and Computer Vision

4411:Pedram Azad; Tilo Gockel; Rüdiger Dillmann (2008). 3547:"ImageNet Large Scale Visual Recognition Challenge" 1172:, medical image analysis or topographical modeling; 1157:monitoring agricultural crops, e.g. an open-source 597:, the inference of shape from various cues such as 578:from images, labeling of lines, non-polyhedral and 4357:Handbook of Mathematical Models in Computer Vision 4330:Dictionary of Computer Vision and Image Processing 4099: 4073: 3166:Machine Vision: Theory, Algorithms, Practicalities 1532:purposes in public places, malls, shopping centers 1106:Assisting humans in identification tasks, e.g., a 634:3-D reconstructions of scenes from multiple images 3910:Encyclopedia of Artificial Intelligence, Volume 1 1569:). A related task is reading of 2D codes such as 1502:ImageNet Large Scale Visual Recognition Challenge 1074:Applications range from tasks such as industrial 3018:Archives of Computational Methods in Engineering 2283:Milan Sonka; Vaclav Hlavac; Roger Boyle (2008). 2234:Huang, T. (1996-11-19). Vandoni, Carlo E (ed.). 1708:– A digital image is produced by one or several 1226:One of the most prominent application fields is 841:Yet another field related to computer vision is 4245:Introductory Techniques for 3-D Computer Vision 3327:Hasan, Fudail; Kashevnik, Alexey (2021-05-14). 2917:"Deep learning-enabled medical computer vision" 2454:Mind as Machine: A History of Cognitive Science 2368: 2366: 2364: 2362: 1867:Pass/fail on automatic inspection applications. 1801:Selection of a specific set of interest points. 27:Computerized information extraction from images 4568:Computer Vision Container, Joe Hoeller GitHub: 3230:Choi, Seung-hyun; Tahara, Kenji (2020-03-12). 3159: 3157: 3155: 3153: 3151: 3149: 2285:Image Processing, Analysis, and Machine Vision 2207:Dana H. Ballard; Christopher M. Brown (1982). 1484:, or the identification of a specific vehicle. 5010: 4589: 4543:– Bob Fisher's Compendium of Computer Vision. 3012:Wäldchen, Jana; Mäder, Patrick (2017-01-07). 2717: 2715: 2149: 2147: 2090: 2088: 818:, a neural network developed in the 1970s by 391: 8: 4435:Computer Vision: Algorithms and Applications 3659:Psychological Science in the Public Interest 2891:"The Future of Automated Random Bin Picking" 2376:Computer Vision: Algorithms and Applications 2237:Computer Vision : Evolution And Promise 915:. Visual computing also includes aspects of 2428:(1966-07-01). "The Summer Vision Project". 1870:Match/no-match in recognition applications. 714:, which is typically in the form of either 5357: 5017: 5003: 4995: 4736: 4596: 4582: 4574: 4242:Emanuele Trucco; Alessandro Verri (1998). 4072:Barghout, Lauren; Lawrence W. Lee (2003). 2725:Machine Vision Algorithms and Applications 1425:Computer vision tasks include methods for 1094:or silhouettes seamlessly and efficiently. 1058:also overlaps with computer vision, e.g., 398: 384: 29: 4414:Computer Vision – Principles and Practice 4288:Multiple View Geometry in Computer Vision 4202:Gösta H. Granlund; Hans Knutsson (1995). 3877: 3859: 3715: 3686: 3580: 3562: 3478: 3468: 3408: 3247: 3206: 3104: 3086: 3045: 2948: 2836: 2654: 2559: 2549: 2511:. Springer Science & Business Media. 2484:. Springer Science & Business Media. 1234:. An example of this is the detection of 4517:USC Iris computer vision conference list 4076:Perceptual information processing system 3551:International Journal of Computer Vision 2814: 2812: 2810: 2538:International Journal of Computer Vision 1198:databases of images and image sequences. 636:. Progress was made on the dense stereo 2084: 1222:'s Visual Media Reasoning concept video 860:or deliberation for robotic systems to 675:Recent work has seen the resurgence of 450:Sub-domains of computer vision include 37: 4749:3D reconstruction from multiple images 4375:Wilhelm Burger; Mark J. Burge (2007). 4080:. U.S. Patent Application 10/618,543. 4053:Azriel Rosenfeld; Avinash Kak (1982). 2373:Richard Szeliski (30 September 2010). 1546:situation or picking parts from a bin. 518:, it seeks to automate tasks that the 4769:Simultaneous localization and mapping 4491:Nixon, Mark; Aguado, Alberto (2019). 4204:Signal Processing for Computer Vision 4165:Scale-Space Theory in Computer Vision 3760:IEEE Transactions on Image Processing 3540: 3538: 3502:David A. Forsyth; Jean Ponce (2003). 2182:Bernd Jähne; Horst Haußecker (2000). 566:at that time was a desire to extract 7: 5855:Generative adversarial network (GAN) 3937:. Vol. 2010. pp. 100–107. 3527:Forsyth, David; Ponce, Jean (2012). 2156:Computer Vision and Image Processing 1482:identification of handwritten digits 4123:Computer Vision for robotic systems 3986:from the original on March 15, 2023 2763:Murray, Don, and Cullen Jennings. " 2508:Machine Learning in Computer Vision 1554:(OCR) – identifying 1390:creation for cinema and broadcast, 656:and computer vision. This included 4834:Automatic number-plate recognition 4547:British Machine Vision Association 4474:Computer Vision for Visual Effects 4417:. Elektor International Media BV. 4311:Emerging Topics in Computer Vision 3529:Computer vision: a modern approach 3504:Computer Vision, A Modern Approach 2308:http://www.bmva.org/visionoverview 2074:Outline of artificial intelligence 1168:Modeling objects or environments, 25: 4522:Computer vision papers on the web 4014:. University of Minnesota Press. 1382:Other application areas include: 726:. The sensors are designed using 632:. This led to methods for sparse 5893: 5892: 5872: 4839:Automated species identification 4495:(4th ed.). Academic Press. 3974:Seth Colaner (January 3, 2016). 3897:from the original on 2018-09-07. 3449:Methods in Ecology and Evolution 3341:10.23919/FRUCT52173.2021.9435480 2481:Three-Dimensional Machine Vision 2478:Takeo Kanade (6 December 2012). 2457:. Clarendon Press. p. 781. 2335:from the original on 2 July 2017 2272:from the original on 2018-02-07. 2247:. Geneva: CERN. pp. 21–25. 1103:, in manufacturing applications; 873:This section is an excerpt from 856:sometimes deals with autonomous 778: 754: 4824:Audio-visual speech recognition 3635:from the original on 2022-12-02 3605:from the original on 2023-03-15 3365:from the original on 2022-06-27 3309:from the original on 2022-06-27 2897:from the original on 2018-01-11 2793:Journal of Marketing Management 2746:from the original on 2023-03-15 2694:Ferrie, C.; Kaiser, S. (2019). 2400:Sejnowski, Terrence J. (2018). 1305:is mounted on top of the rover. 1150:, as the input to a device for 862:navigate through an environment 620:led to better understanding of 66:Artificial general intelligence 5805:Recurrent neural network (RNN) 5795:Differentiable neural computer 4669:Recognition and categorization 4476:. Cambridge University Press. 4290:. Cambridge University Press. 3410:10.1088/1757-899x/981/2/022005 2327:Murphy, Mike (13 April 2017). 603:contour models known as snakes 1: 5850:Variational autoencoder (VAE) 5810:Long short-term memory (LSTM) 5077:Computational learning theory 4933:Optical character recognition 4864:Content-based image retrieval 4206:. Kluwer Academic Publisher. 4121:Michael C. Fairhurst (1988). 4038:. W. H. Freeman and Company. 3285:10.1109/PARC49193.2020.236556 3271:Garg, Hitendra (2020-02-29). 2245:19th CERN School of Computing 2126:; George C. Stockman (2001). 2069:List of emerging technologies 1551:Optical character recognition 1513:Content-based image retrieval 1498:convolutional neural networks 1031:There is also a field called 5830:Convolutional neural network 4011:The Birth of Computer Vision 3623:Quinn, Arthur (2022-10-09). 2987:10.1016/j.neucom.2020.04.018 2402:The deep learning revolution 1926:structured-light 3D scanners 1688:An example in this field is 1604:Shape Recognition Technology 574:that exist today, including 554:. It was meant to mimic the 5825:Multilayer perceptron (MLP) 3908:Shapiro, Stuart C. (1992). 2784:Andrade, Norberto Almeida. 2673:10.1109/ACCESS.2019.2939201 2451:Margaret Ann Boden (2006). 2031:Teknomo–Fernandez algorithm 1880:Image-understanding systems 1408:Driver drowsiness detection 101:Natural language processing 5955: 5901:Artificial neural networks 5815:Gated recurrent unit (GRU) 5041:Differentiable programming 4829:Automatic image annotation 4664:Noise reduction techniques 4055:Digital Picture Processing 3943:10.1109/CVPRW.2010.5543776 3249:10.1186/s40648-020-00162-5 3208:10.1186/s40648-020-00159-0 2933:10.1038/s41746-020-00376-2 2728:(2nd ed.). Weinheim: 2696:Neural Networks for Babies 2430:MIT AI Memos (1959 - 2004) 2064:Outline of computer vision 1965:consumer graphics hardware 1718:magnetic resonance imaging 1616:Human activity recognition 1327:autonomous driving of cars 1152:computer-human interaction 1049:artificial neural networks 921:human-computer interaction 872: 514:. From the perspective of 486:, 3D scene modeling, and 413:tasks include methods for 154:Hybrid intelligent systems 76:Recursive self-improvement 18:History of computer vision 5868: 5234:Artificial neural network 5057:Automatic differentiation 4981: 4794:Free viewpoint television 4472:Richard J. Radke (2013). 4432:Richard Szeliski (2010). 3573:10.1007/s11263-015-0816-y 3030:10.1007/s11831-016-9206-z 2872:NASA Tech Briefs Magazine 2561:21.11116/0000-0003-30FB-C 2551:10.1007/s11263-008-0127-7 2006:Computational photography 1983:graphics processing units 1961:digital signal processing 1946:magnetic resonance images 712:electromagnetic radiation 666:panoramic image stitching 628:theory from the field of 601:, texture and focus, and 5062:Neuromorphic engineering 5025:Differentiable computing 4859:Computer-aided diagnosis 4265:Digital Image Processing 4008:James E. Dobson (2023). 3780:10.1109/tip.2018.2859622 3671:10.1177/1529100619832930 2253:10.5170/CERN-1996-008.21 2095:Reinhard Klette (2014). 1954:synthetic aperture sonar 1815:is often implemented as 1190:Organizing information, 930:medical image processing 564:digital image processing 278:Artificial consciousness 5835:Residual neural network 5251:Artificial Intelligence 4921:Moving object detection 4911:Medical image computing 4674:Research infrastructure 4644:Image sensor technology 4560:(open-source journal), 4457:(2nd ed.). Wiley. 4227:. Springer, Singapore. 4162:Tony Lindeberg (1994). 3470:10.1111/2041-210X.12975 3401:2020MS&E..981b2005B 2097:Concise Computer Vision 2021:Machine vision glossary 1979:vision processing units 1228:medical computer vision 1113:Controlling processes, 642:variations of graph cut 552:artificial intelligence 504:interdisciplinary field 149:Evolutionary algorithms 39:Artificial intelligence 4958:Video content analysis 4926:Small object detection 4705:Computer stereo vision 4528:Computer Vision Online 3164:E. Roy Davies (2005). 2823:. pp. 1511–1519. 2158:. Palgrave Macmillan. 1914: 1533: 1375: 1366: 1306: 1223: 1108:species identification 1099:Automatic inspection, 1095: 1064:computer stereo vision 790:result for sea urchin. 695: 664:, view interpolation, 638:correspondence problem 502:Computer vision is an 478:, learning, indexing, 50: 5790:Neural Turing machine 5378:Human image synthesis 4963:Video motion analysis 4774:Structure from motion 4720:3D object recognition 4453:J. R. Parker (2011). 3088:10.3390/foods13121869 2829:10.1109/CVPR.2017.269 2001:Computational imaging 1985:(GPUs) in this role. 1934:hyperspectral imagers 1930:thermographic cameras 1904: 1836:High-level processing 1527: 1468:object classification 1372: 1364: 1294: 1218: 1085: 901:computational imaging 824:primary visual cortex 690: 670:light-field rendering 658:image-based rendering 525:scientific discipline 444:scientific discipline 49: 5881:Computer programming 5860:Graph neural network 5435:Text-to-video models 5413:Text-to-image models 5261:Large language model 5246:Scientific computing 5052:Statistical manifold 5047:Information geometry 4886:Foreground detection 4869:Reverse image search 4849:Bioimage informatics 4819:Activity recognition 4564:and one-day meetings 4350:and Yunmei Chen and 4282:Richard Hartley and 4263:Bernd Jähne (2002). 3980:www.tomshardware.com 3335:. pp. 141–149. 2921:npj Digital Medicine 1996:Chessboard detection 1673:computing a 3D model 1667:Scene reconstruction 1528:Computer vision for 1518:reverse image search 1295:Artist's concept of 1165:with 98.4% accuracy. 1060:stereophotogrammetry 611:Markov random fields 464:activity recognition 452:scene reconstruction 429:, and extraction of 91:General game playing 5939:Packaging machinery 5227:In-context learning 5067:Pattern recognition 4953:Autonomous vehicles 4891:Gesture recognition 4754:2D to 3D conversion 4438:. Springer-Verlag. 4187:. Springer-Verlag. 3852:2018Senso..18.1657W 3772:2018ITIP...27.5840L 3730:Barghout, Lauren. " 3461:2018MEcEv...9..965B 3168:. Morgan Kaufmann. 2665:2019IEEEA...7l8837J 2612:10.1038/nature14539 2604:2015Natur.521..436L 2154:Tim Morris (2004). 1907:2020 model iPad Pro 1590:Emotion recognition 1287:Autonomous vehicles 1163:strawberry diseases 1159:vision transformers 1141:restaurant industry 1133:visual surveillance 1045:pattern recognition 917:pattern recognition 899:, computer vision, 704:Solid-state physics 699:Solid-state physics 644:were used to solve 618:3-D reconstructions 580:polyhedral modeling 576:extraction of edges 556:human visual system 520:human visual system 243:Machine translation 159:Systems integration 96:Knowledge reasoning 33:Part of a series on 5820:Echo state network 5708:Jürgen Schmidhuber 5403:Facial recognition 5398:Speech recognition 5308:Software libraries 4968:Video surveillance 4906:Landmark detection 4814:3D pose estimation 4799:Volumetric capture 4759:Gaussian splatting 4715:Object recognition 4629:Commercial systems 4562:BMVA Summer School 4533:2011-11-30 at the 4096:Berthold K.P. Horn 4057:. Academic Press. 3737:2018-11-14 at the 3279:. pp. 50–53. 2770:2020-10-31 at the 2313:2017-02-16 at the 2186:. Academic Press. 1915: 1854:Image registration 1821:temporal attention 1748:Feature extraction 1593: – 1584: – 1582:Facial recognition 1534: 1463:Object recognition 1376: 1367: 1307: 1232:diagnose a patient 1224: 1181:autonomous vehicle 1096: 849:Robotic navigation 820:Kunihiko Fukushima 696: 646:image segmentation 622:camera calibration 476:3D pose estimation 472:object recognition 425:and understanding 51: 5916: 5915: 5678:Stephen Grossberg 5651: 5650: 4992: 4991: 4901:Image restoration 4844:Augmented reality 4809: 4808: 4789:4D reconstruction 4741:3D reconstruction 4634:Feature detection 4483:978-0-521-76687-6 4424:978-0-905705-71-2 4392:978-1-84628-379-6 4367:978-0-387-26371-7 4339:978-0-470-01526-1 4320:978-0-13-101366-7 4313:. Prentice Hall. 4297:978-0-521-54051-3 4274:978-3-540-67754-3 4255:978-0-13-261108-4 4248:. Prentice Hall. 4234:978-981-3083-71-4 4213:978-0-7923-9530-0 4194:978-3-540-58143-7 4185:Vision as Process 4175:978-0-7923-9418-1 4154:978-0-262-06158-2 4132:978-0-13-166919-2 4125:. Prentice Hall. 4113:978-0-262-08159-7 4087:978-0-262-08159-7 4064:978-0-12-597301-4 4045:978-0-7167-1284-8 4021:978-1-5179-1421-9 3952:978-1-4244-7029-7 3919:978-0-471-50306-4 3861:10.3390/s18051657 3766:(12): 5840–5853. 3513:978-0-13-085198-7 3506:. Prentice Hall. 3350:978-952-69244-5-8 3294:978-1-7281-6575-2 3175:978-0-12-206093-9 2848:978-1-5386-0457-1 2739:978-3-527-41365-2 2649:: 128837–128868. 2598:(7553): 436–444. 2518:978-1-4020-3274-5 2491:978-1-4613-1981-8 2464:978-0-19-954316-8 2411:978-0-262-03803-4 2386:978-1-84882-935-0 2294:978-0-495-08252-1 2220:978-0-13-165316-0 2213:. Prentice Hall. 2193:978-0-13-085198-7 2165:978-0-333-99451-1 2137:978-0-13-030796-5 2130:. Prentice Hall. 2106:978-1-4471-6320-6 2046:Visual perception 2016:Egocentric vision 2011:Computer audition 1972:Egocentric vision 1848:Image recognition 1706:Image acquisition 1680:Image restoration 1216: 986:augmented reality 984:, as explored in 978:Computer graphics 909:augmented reality 889:computer graphics 843:signal processing 837:Signal processing 831:biological vision 740:quantum mechanics 724:ultraviolet light 654:computer graphics 626:bundle adjustment 588:motion estimation 568:three-dimensional 488:image restoration 480:motion estimation 439:learning theory. 408: 407: 144:Bayesian networks 71:Intelligent agent 16:(Redirected from 5946: 5934:Image processing 5906:Machine learning 5896: 5895: 5876: 5631:Action selection 5621:Self-driving car 5428:Stable Diffusion 5393:Speech synthesis 5358: 5222:Machine learning 5098:Gradient descent 5019: 5012: 5005: 4996: 4916:Object detection 4881:Face recognition 4764:Shape from focus 4737: 4624:Digital geometry 4598: 4591: 4584: 4575: 4551:MIUA conferences 4506: 4487: 4468: 4449: 4428: 4407: 4405: 4404: 4395:. Archived from 4371: 4352:Olivier Faugeras 4343: 4324: 4305:Gérard Medioni; 4301: 4284:Andrew Zisserman 4278: 4259: 4238: 4217: 4198: 4179: 4158: 4141:Olivier Faugeras 4136: 4117: 4105: 4091: 4079: 4068: 4049: 4025: 3996: 3995: 3993: 3991: 3971: 3965: 3964: 3930: 3924: 3923: 3905: 3899: 3898: 3896: 3881: 3863: 3837: 3828: 3822: 3821: 3819: 3818: 3812: 3806:. Archived from 3757: 3748: 3742: 3728: 3722: 3721: 3719: 3707: 3701: 3700: 3690: 3650: 3644: 3643: 3641: 3640: 3620: 3614: 3613: 3611: 3610: 3584: 3566: 3542: 3533: 3532: 3524: 3518: 3517: 3499: 3493: 3492: 3482: 3472: 3440: 3431: 3430: 3412: 3380: 3374: 3373: 3371: 3370: 3324: 3318: 3317: 3315: 3314: 3268: 3262: 3261: 3251: 3236:ROBOMECH Journal 3227: 3221: 3220: 3210: 3195:ROBOMECH Journal 3186: 3180: 3179: 3161: 3144: 3143: 3141: 3140: 3125: 3119: 3118: 3108: 3090: 3066: 3060: 3059: 3049: 3009: 3003: 3002: 2969: 2963: 2962: 2952: 2912: 2906: 2905: 2903: 2902: 2887: 2881: 2879: 2867: 2861: 2860: 2840: 2816: 2805: 2804: 2802: 2800: 2790: 2781: 2775: 2761: 2755: 2754: 2752: 2751: 2719: 2710: 2709: 2691: 2685: 2684: 2658: 2638: 2632: 2631: 2589: 2580: 2574: 2573: 2563: 2553: 2529: 2523: 2522: 2502: 2496: 2495: 2475: 2469: 2468: 2448: 2442: 2441: 2422: 2416: 2415: 2397: 2391: 2390: 2370: 2357: 2351: 2345: 2344: 2342: 2340: 2324: 2318: 2305: 2299: 2298: 2280: 2274: 2273: 2271: 2242: 2231: 2225: 2224: 2204: 2198: 2197: 2179: 2170: 2169: 2151: 2142: 2141: 2124:Linda G. Shapiro 2120: 2111: 2110: 2092: 1826:Segmentation or 1439:high-dimensional 1357:Tactile feedback 1281:missile guidance 1240:arteriosclerosis 1217: 1125:Detecting events 1119:industrial robot 996:Image processing 964:image processing 925:machine learning 913:video processing 893:image processing 881:Visual computing 875:Visual computing 868:Visual computing 854:Robot navigation 782: 758: 692:Object detection 456:object detection 431:high-dimensional 400: 393: 386: 307:Existential risk 129:Machine learning 30: 21: 5954: 5953: 5949: 5948: 5947: 5945: 5944: 5943: 5929:Computer vision 5919: 5918: 5917: 5912: 5864: 5778: 5744:Google DeepMind 5722: 5688:Geoffrey Hinton 5647: 5584: 5510:Project Debater 5456: 5354:Implementations 5349: 5303: 5267: 5210: 5152:Backpropagation 5086: 5072:Tensor calculus 5026: 5023: 4993: 4988: 4977: 4948:Robotic mapping 4896:Image denoising 4805: 4726: 4693: 4659:Motion analysis 4607: 4605:Computer vision 4602: 4535:Wayback Machine 4513: 4503: 4490: 4484: 4471: 4465: 4452: 4446: 4431: 4425: 4410: 4402: 4400: 4393: 4374: 4368: 4346: 4340: 4327: 4321: 4304: 4298: 4281: 4275: 4262: 4256: 4241: 4235: 4220: 4214: 4201: 4195: 4182: 4176: 4161: 4155: 4139: 4133: 4120: 4114: 4094: 4088: 4071: 4065: 4052: 4046: 4028: 4022: 4007: 4004: 4002:Further reading 3999: 3989: 3987: 3973: 3972: 3968: 3953: 3932: 3931: 3927: 3920: 3907: 3906: 3902: 3894: 3835: 3830: 3829: 3825: 3816: 3814: 3810: 3755: 3750: 3749: 3745: 3739:Wayback Machine 3729: 3725: 3709: 3708: 3704: 3652: 3651: 3647: 3638: 3636: 3622: 3621: 3617: 3608: 3606: 3544: 3543: 3536: 3526: 3525: 3521: 3514: 3501: 3500: 3496: 3442: 3441: 3434: 3382: 3381: 3377: 3368: 3366: 3351: 3326: 3325: 3321: 3312: 3310: 3295: 3270: 3269: 3265: 3229: 3228: 3224: 3188: 3187: 3183: 3176: 3163: 3162: 3147: 3138: 3136: 3127: 3126: 3122: 3068: 3067: 3063: 3011: 3010: 3006: 2971: 2970: 2966: 2914: 2913: 2909: 2900: 2898: 2889: 2888: 2884: 2869: 2868: 2864: 2849: 2818: 2817: 2808: 2798: 2796: 2788: 2783: 2782: 2778: 2772:Wayback Machine 2762: 2758: 2749: 2747: 2740: 2721: 2720: 2713: 2706: 2698:. Sourcebooks. 2693: 2692: 2688: 2640: 2639: 2635: 2587: 2585:"Deep Learning" 2582: 2581: 2577: 2531: 2530: 2526: 2519: 2504: 2503: 2499: 2492: 2477: 2476: 2472: 2465: 2450: 2449: 2445: 2426:Papert, Seymour 2424: 2423: 2419: 2412: 2399: 2398: 2394: 2387: 2372: 2371: 2360: 2354:Computer Vision 2352: 2348: 2338: 2336: 2326: 2325: 2321: 2315:Wayback Machine 2306: 2302: 2295: 2282: 2281: 2277: 2269: 2263: 2240: 2233: 2232: 2228: 2221: 2210:Computer Vision 2206: 2205: 2201: 2194: 2181: 2180: 2173: 2166: 2153: 2152: 2145: 2138: 2128:Computer Vision 2122: 2121: 2114: 2107: 2094: 2093: 2086: 2082: 2060: 2055: 1991: 1950:side-scan sonar 1899: 1882: 1862:Decision making 1828:co-segmentation 1813:visual salience 1767:interest points 1698: 1682: 1669: 1626: 1624:Motion analysis 1539:Pose estimation 1451: 1419: 1398:(match moving). 1396:camera tracking 1359: 1289: 1277: 1269:optical sorting 1252: 1210: 1208: 1139:, e.g., in the 1137:people counting 1072: 1037:medical imaging 960: 939: 934: 933: 878: 870: 851: 839: 797: 796: 795: 794: 793: 791: 783: 775: 774: 759: 748: 728:quantum physics 710:, which detect 701: 694:in a photograph 685: 548: 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: 5952: 5950: 5942: 5941: 5936: 5931: 5921: 5920: 5914: 5913: 5911: 5910: 5909: 5908: 5903: 5890: 5889: 5888: 5883: 5869: 5866: 5865: 5863: 5862: 5857: 5852: 5847: 5842: 5837: 5832: 5827: 5822: 5817: 5812: 5807: 5802: 5797: 5792: 5786: 5784: 5780: 5779: 5777: 5776: 5771: 5766: 5761: 5756: 5751: 5746: 5741: 5736: 5730: 5728: 5724: 5723: 5721: 5720: 5718:Ilya Sutskever 5715: 5710: 5705: 5700: 5695: 5690: 5685: 5683:Demis Hassabis 5680: 5675: 5673:Ian Goodfellow 5670: 5665: 5659: 5657: 5653: 5652: 5649: 5648: 5646: 5645: 5640: 5639: 5638: 5628: 5623: 5618: 5613: 5608: 5603: 5598: 5592: 5590: 5586: 5585: 5583: 5582: 5577: 5572: 5567: 5562: 5557: 5552: 5547: 5542: 5537: 5532: 5527: 5522: 5517: 5512: 5507: 5502: 5501: 5500: 5490: 5485: 5480: 5475: 5470: 5464: 5462: 5458: 5457: 5455: 5454: 5449: 5448: 5447: 5442: 5432: 5431: 5430: 5425: 5420: 5410: 5405: 5400: 5395: 5390: 5385: 5380: 5375: 5370: 5364: 5362: 5355: 5351: 5350: 5348: 5347: 5342: 5337: 5332: 5327: 5322: 5317: 5311: 5309: 5305: 5304: 5302: 5301: 5296: 5291: 5286: 5281: 5275: 5273: 5269: 5268: 5266: 5265: 5264: 5263: 5256:Language model 5253: 5248: 5243: 5242: 5241: 5231: 5230: 5229: 5218: 5216: 5212: 5211: 5209: 5208: 5206:Autoregression 5203: 5198: 5197: 5196: 5186: 5184:Regularization 5181: 5180: 5179: 5174: 5169: 5159: 5154: 5149: 5147:Loss functions 5144: 5139: 5134: 5129: 5124: 5123: 5122: 5112: 5107: 5106: 5105: 5094: 5092: 5088: 5087: 5085: 5084: 5082:Inductive bias 5079: 5074: 5069: 5064: 5059: 5054: 5049: 5044: 5036: 5034: 5028: 5027: 5024: 5022: 5021: 5014: 5007: 4999: 4990: 4989: 4982: 4979: 4978: 4976: 4975: 4973:Video tracking 4970: 4965: 4960: 4955: 4950: 4945: 4943:Remote sensing 4940: 4935: 4930: 4929: 4928: 4923: 4913: 4908: 4903: 4898: 4893: 4888: 4883: 4878: 4873: 4872: 4871: 4861: 4856: 4854:Blob detection 4851: 4846: 4841: 4836: 4831: 4826: 4821: 4816: 4810: 4807: 4806: 4804: 4803: 4802: 4801: 4796: 4786: 4781: 4779:View synthesis 4776: 4771: 4766: 4761: 4756: 4751: 4745: 4743: 4734: 4728: 4727: 4725: 4724: 4723: 4722: 4712: 4710:Motion capture 4707: 4701: 4699: 4695: 4694: 4692: 4691: 4686: 4681: 4676: 4671: 4666: 4661: 4656: 4651: 4646: 4641: 4636: 4631: 4626: 4621: 4615: 4613: 4609: 4608: 4603: 4601: 4600: 4593: 4586: 4578: 4572: 4571: 4565: 4555:Annals of the 4544: 4538: 4525: 4519: 4512: 4511:External links 4509: 4508: 4507: 4502:978-0128149768 4501: 4488: 4482: 4469: 4464:978-0470643853 4463: 4450: 4445:978-1848829343 4444: 4429: 4423: 4408: 4391: 4372: 4366: 4348:Nikos Paragios 4344: 4338: 4332:. John Wiley. 4325: 4319: 4307:Sing Bing Kang 4302: 4296: 4279: 4273: 4260: 4254: 4239: 4233: 4218: 4212: 4199: 4193: 4180: 4174: 4159: 4153: 4137: 4131: 4118: 4112: 4092: 4086: 4069: 4063: 4050: 4044: 4026: 4020: 4003: 4000: 3998: 3997: 3966: 3951: 3925: 3918: 3900: 3823: 3743: 3723: 3702: 3645: 3615: 3557:(3): 211–252. 3534: 3519: 3512: 3494: 3455:(4): 965–973. 3432: 3375: 3349: 3319: 3293: 3263: 3222: 3181: 3174: 3145: 3120: 3061: 3024:(2): 507–543. 3004: 2975:Neurocomputing 2964: 2907: 2882: 2862: 2847: 2806: 2776: 2756: 2738: 2711: 2705:978-1492671206 2704: 2686: 2633: 2575: 2524: 2517: 2497: 2490: 2470: 2463: 2443: 2417: 2410: 2392: 2385: 2358: 2346: 2319: 2300: 2293: 2275: 2262:978-9290830955 2261: 2226: 2219: 2199: 2192: 2171: 2164: 2143: 2136: 2112: 2105: 2083: 2081: 2078: 2077: 2076: 2071: 2066: 2059: 2056: 2054: 2053: 2048: 2043: 2041:Visual agnosia 2038: 2036:Vision science 2033: 2028: 2023: 2018: 2013: 2008: 2003: 1998: 1992: 1990: 1987: 1898: 1895: 1881: 1878: 1877: 1876: 1875: 1874: 1871: 1868: 1859: 1858: 1857: 1851: 1845: 1842: 1833: 1832: 1831: 1824: 1805: 1802: 1786: 1785: 1781: 1780: 1779: 1778: 1763: 1744: 1743: 1742: 1736: 1733: 1730: 1724:Pre-processing 1721: 1697: 1696:System methods 1694: 1681: 1678: 1668: 1665: 1664: 1663: 1651: 1639: 1625: 1622: 1621: 1620: 1612: 1609:people counter 1600: 1587: 1578: 1547: 1530:people counter 1522: 1521: 1494: 1493: 1485: 1478:Identification 1475: 1472:Google Goggles 1455:machine vision 1450: 1447: 1418: 1415: 1414: 1413: 1410: 1405: 1399: 1388:visual effects 1358: 1355: 1288: 1285: 1276: 1273: 1256:machine vision 1251: 1250:Machine vision 1248: 1207: 1204: 1203: 1202: 1199: 1188: 1173: 1166: 1155: 1144: 1122: 1111: 1104: 1076:machine vision 1071: 1068: 1056:Photogrammetry 1053: 1052: 1041: 1029: 1017:Machine vision 1014: 1007: 1000:image analysis 972:machine vision 968:image analysis 959: 956: 938: 935: 879: 871: 869: 866: 850: 847: 838: 835: 788:false positive 784: 777: 776: 760: 753: 752: 751: 750: 749: 747: 744: 700: 697: 684: 683:Related fields 681: 662:image morphing 630:photogrammetry 607:regularization 547: 544: 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: 5951: 5940: 5937: 5935: 5932: 5930: 5927: 5926: 5924: 5907: 5904: 5902: 5899: 5898: 5891: 5887: 5884: 5882: 5879: 5878: 5875: 5871: 5870: 5867: 5861: 5858: 5856: 5853: 5851: 5848: 5846: 5843: 5841: 5838: 5836: 5833: 5831: 5828: 5826: 5823: 5821: 5818: 5816: 5813: 5811: 5808: 5806: 5803: 5801: 5798: 5796: 5793: 5791: 5788: 5787: 5785: 5783:Architectures 5781: 5775: 5772: 5770: 5767: 5765: 5762: 5760: 5757: 5755: 5752: 5750: 5747: 5745: 5742: 5740: 5737: 5735: 5732: 5731: 5729: 5727:Organizations 5725: 5719: 5716: 5714: 5711: 5709: 5706: 5704: 5701: 5699: 5696: 5694: 5691: 5689: 5686: 5684: 5681: 5679: 5676: 5674: 5671: 5669: 5666: 5664: 5663:Yoshua Bengio 5661: 5660: 5658: 5654: 5644: 5643:Robot control 5641: 5637: 5634: 5633: 5632: 5629: 5627: 5624: 5622: 5619: 5617: 5614: 5612: 5609: 5607: 5604: 5602: 5599: 5597: 5594: 5593: 5591: 5587: 5581: 5578: 5576: 5573: 5571: 5568: 5566: 5563: 5561: 5560:Chinchilla AI 5558: 5556: 5553: 5551: 5548: 5546: 5543: 5541: 5538: 5536: 5533: 5531: 5528: 5526: 5523: 5521: 5518: 5516: 5513: 5511: 5508: 5506: 5503: 5499: 5496: 5495: 5494: 5491: 5489: 5486: 5484: 5481: 5479: 5476: 5474: 5471: 5469: 5466: 5465: 5463: 5459: 5453: 5450: 5446: 5443: 5441: 5438: 5437: 5436: 5433: 5429: 5426: 5424: 5421: 5419: 5416: 5415: 5414: 5411: 5409: 5406: 5404: 5401: 5399: 5396: 5394: 5391: 5389: 5386: 5384: 5381: 5379: 5376: 5374: 5371: 5369: 5366: 5365: 5363: 5359: 5356: 5352: 5346: 5343: 5341: 5338: 5336: 5333: 5331: 5328: 5326: 5323: 5321: 5318: 5316: 5313: 5312: 5310: 5306: 5300: 5297: 5295: 5292: 5290: 5287: 5285: 5282: 5280: 5277: 5276: 5274: 5270: 5262: 5259: 5258: 5257: 5254: 5252: 5249: 5247: 5244: 5240: 5239:Deep learning 5237: 5236: 5235: 5232: 5228: 5225: 5224: 5223: 5220: 5219: 5217: 5213: 5207: 5204: 5202: 5199: 5195: 5192: 5191: 5190: 5187: 5185: 5182: 5178: 5175: 5173: 5170: 5168: 5165: 5164: 5163: 5160: 5158: 5155: 5153: 5150: 5148: 5145: 5143: 5140: 5138: 5135: 5133: 5130: 5128: 5127:Hallucination 5125: 5121: 5118: 5117: 5116: 5113: 5111: 5108: 5104: 5101: 5100: 5099: 5096: 5095: 5093: 5089: 5083: 5080: 5078: 5075: 5073: 5070: 5068: 5065: 5063: 5060: 5058: 5055: 5053: 5050: 5048: 5045: 5043: 5042: 5038: 5037: 5035: 5033: 5029: 5020: 5015: 5013: 5008: 5006: 5001: 5000: 4997: 4987: 4986: 4985:Main category 4980: 4974: 4971: 4969: 4966: 4964: 4961: 4959: 4956: 4954: 4951: 4949: 4946: 4944: 4941: 4939: 4938:Pose tracking 4936: 4934: 4931: 4927: 4924: 4922: 4919: 4918: 4917: 4914: 4912: 4909: 4907: 4904: 4902: 4899: 4897: 4894: 4892: 4889: 4887: 4884: 4882: 4879: 4877: 4874: 4870: 4867: 4866: 4865: 4862: 4860: 4857: 4855: 4852: 4850: 4847: 4845: 4842: 4840: 4837: 4835: 4832: 4830: 4827: 4825: 4822: 4820: 4817: 4815: 4812: 4811: 4800: 4797: 4795: 4792: 4791: 4790: 4787: 4785: 4782: 4780: 4777: 4775: 4772: 4770: 4767: 4765: 4762: 4760: 4757: 4755: 4752: 4750: 4747: 4746: 4744: 4742: 4738: 4735: 4733: 4729: 4721: 4718: 4717: 4716: 4713: 4711: 4708: 4706: 4703: 4702: 4700: 4696: 4690: 4687: 4685: 4682: 4680: 4677: 4675: 4672: 4670: 4667: 4665: 4662: 4660: 4657: 4655: 4652: 4650: 4647: 4645: 4642: 4640: 4637: 4635: 4632: 4630: 4627: 4625: 4622: 4620: 4617: 4616: 4614: 4610: 4606: 4599: 4594: 4592: 4587: 4585: 4580: 4579: 4576: 4569: 4566: 4563: 4559: 4558: 4552: 4548: 4545: 4542: 4539: 4536: 4532: 4529: 4526: 4523: 4520: 4518: 4515: 4514: 4510: 4504: 4498: 4494: 4489: 4485: 4479: 4475: 4470: 4466: 4460: 4456: 4451: 4447: 4441: 4437: 4436: 4430: 4426: 4420: 4416: 4415: 4409: 4399:on 2014-05-17 4398: 4394: 4388: 4384: 4380: 4379: 4373: 4369: 4363: 4359: 4358: 4353: 4349: 4345: 4341: 4335: 4331: 4326: 4322: 4316: 4312: 4308: 4303: 4299: 4293: 4289: 4285: 4280: 4276: 4270: 4266: 4261: 4257: 4251: 4247: 4246: 4240: 4236: 4230: 4226: 4225: 4219: 4215: 4209: 4205: 4200: 4196: 4190: 4186: 4181: 4177: 4171: 4167: 4166: 4160: 4156: 4150: 4147:. MIT Press. 4146: 4142: 4138: 4134: 4128: 4124: 4119: 4115: 4109: 4106:. MIT Press. 4104: 4103: 4097: 4093: 4089: 4083: 4078: 4077: 4070: 4066: 4060: 4056: 4051: 4047: 4041: 4037: 4036: 4031: 4027: 4023: 4017: 4013: 4012: 4006: 4005: 4001: 3985: 3981: 3977: 3970: 3967: 3962: 3958: 3954: 3948: 3944: 3940: 3936: 3929: 3926: 3921: 3915: 3911: 3904: 3901: 3893: 3889: 3885: 3880: 3875: 3871: 3867: 3862: 3857: 3853: 3849: 3845: 3841: 3834: 3827: 3824: 3813:on 2018-09-07 3809: 3805: 3801: 3797: 3793: 3789: 3785: 3781: 3777: 3773: 3769: 3765: 3761: 3754: 3747: 3744: 3740: 3736: 3733: 3727: 3724: 3718: 3713: 3706: 3703: 3698: 3694: 3689: 3684: 3680: 3676: 3672: 3668: 3664: 3660: 3656: 3649: 3646: 3634: 3630: 3626: 3619: 3616: 3604: 3600: 3596: 3592: 3588: 3583: 3582:1721.1/104944 3578: 3574: 3570: 3565: 3560: 3556: 3552: 3548: 3541: 3539: 3535: 3530: 3523: 3520: 3515: 3509: 3505: 3498: 3495: 3490: 3486: 3481: 3476: 3471: 3466: 3462: 3458: 3454: 3450: 3446: 3439: 3437: 3433: 3428: 3424: 3420: 3416: 3411: 3406: 3402: 3398: 3395:(2): 022005. 3394: 3390: 3386: 3379: 3376: 3364: 3360: 3356: 3352: 3346: 3342: 3338: 3334: 3330: 3323: 3320: 3308: 3304: 3300: 3296: 3290: 3286: 3282: 3278: 3274: 3267: 3264: 3259: 3255: 3250: 3245: 3241: 3237: 3233: 3226: 3223: 3218: 3214: 3209: 3204: 3200: 3196: 3192: 3185: 3182: 3177: 3171: 3167: 3160: 3158: 3156: 3154: 3152: 3150: 3146: 3134: 3130: 3124: 3121: 3116: 3112: 3107: 3102: 3098: 3094: 3089: 3084: 3080: 3076: 3072: 3065: 3062: 3057: 3053: 3048: 3043: 3039: 3035: 3031: 3027: 3023: 3019: 3015: 3008: 3005: 3001: 2996: 2992: 2988: 2984: 2980: 2976: 2968: 2965: 2960: 2956: 2951: 2946: 2942: 2938: 2934: 2930: 2926: 2922: 2918: 2911: 2908: 2896: 2892: 2886: 2883: 2877: 2873: 2866: 2863: 2858: 2854: 2850: 2844: 2839: 2838:1721.1/126644 2834: 2830: 2826: 2822: 2815: 2813: 2811: 2807: 2794: 2787: 2780: 2777: 2773: 2769: 2766: 2760: 2757: 2745: 2741: 2735: 2732:. p. 1. 2731: 2727: 2726: 2718: 2716: 2712: 2707: 2701: 2697: 2690: 2687: 2682: 2678: 2674: 2670: 2666: 2662: 2657: 2652: 2648: 2644: 2637: 2634: 2629: 2625: 2621: 2617: 2613: 2609: 2605: 2601: 2597: 2593: 2586: 2579: 2576: 2571: 2567: 2562: 2557: 2552: 2547: 2543: 2539: 2535: 2528: 2525: 2520: 2514: 2510: 2509: 2501: 2498: 2493: 2487: 2483: 2482: 2474: 2471: 2466: 2460: 2456: 2455: 2447: 2444: 2439: 2435: 2431: 2427: 2421: 2418: 2413: 2407: 2403: 2396: 2393: 2388: 2382: 2378: 2377: 2369: 2367: 2365: 2363: 2359: 2355: 2350: 2347: 2334: 2330: 2323: 2320: 2316: 2312: 2309: 2304: 2301: 2296: 2290: 2286: 2279: 2276: 2268: 2264: 2258: 2254: 2250: 2246: 2239: 2238: 2230: 2227: 2222: 2216: 2212: 2211: 2203: 2200: 2195: 2189: 2185: 2178: 2176: 2172: 2167: 2161: 2157: 2150: 2148: 2144: 2139: 2133: 2129: 2125: 2119: 2117: 2113: 2108: 2102: 2098: 2091: 2089: 2085: 2079: 2075: 2072: 2070: 2067: 2065: 2062: 2061: 2057: 2052: 2051:Visual system 2049: 2047: 2044: 2042: 2039: 2037: 2034: 2032: 2029: 2027: 2026:Space mapping 2024: 2022: 2019: 2017: 2014: 2012: 2009: 2007: 2004: 2002: 1999: 1997: 1994: 1993: 1988: 1986: 1984: 1980: 1975: 1973: 1969: 1966: 1962: 1957: 1955: 1951: 1947: 1943: 1939: 1938:radar imaging 1935: 1931: 1927: 1922: 1919: 1912: 1908: 1903: 1896: 1894: 1890: 1886: 1879: 1872: 1869: 1866: 1865: 1863: 1860: 1855: 1852: 1849: 1846: 1843: 1840: 1839: 1837: 1834: 1829: 1825: 1822: 1818: 1814: 1810: 1806: 1803: 1800: 1799: 1797: 1796: 1792: 1788: 1787: 1783: 1782: 1776: 1772: 1768: 1764: 1761: 1757: 1753: 1752: 1750: 1749: 1745: 1740: 1737: 1734: 1731: 1728: 1727: 1725: 1722: 1719: 1715: 1714:range sensors 1711: 1710:image sensors 1707: 1704: 1703: 1702: 1695: 1693: 1691: 1686: 1679: 1677: 1674: 1666: 1661: 1657: 1656: 1652: 1649: 1645: 1644: 1640: 1637: 1636: 1632: 1631: 1630: 1623: 1618: 1617: 1613: 1610: 1606: 1605: 1601: 1598: 1594: 1591: 1588: 1585: 1583: 1579: 1576: 1572: 1568: 1565: 1561: 1557: 1553: 1552: 1548: 1545: 1544:assembly line 1541: 1540: 1536: 1535: 1531: 1526: 1519: 1515: 1514: 1510: 1509: 1508: 1505: 1503: 1499: 1491: 1490: 1486: 1483: 1479: 1476: 1473: 1469: 1466:(also called 1465: 1464: 1460: 1459: 1458: 1456: 1448: 1446: 1444: 1440: 1436: 1432: 1428: 1423: 1417:Typical tasks 1416: 1411: 1409: 1406: 1403: 1400: 1397: 1393: 1389: 1385: 1384: 1383: 1380: 1371: 1363: 1356: 1354: 1352: 1351: 1346: 1342: 1341: 1336: 1332: 1328: 1324: 1320: 1316: 1312: 1304: 1303:stereo camera 1300: 1299: 1293: 1286: 1284: 1282: 1274: 1272: 1270: 1265: 1264:computer chip 1261: 1257: 1249: 1247: 1245: 1241: 1237: 1233: 1229: 1221: 1205: 1200: 1197: 1193: 1189: 1186: 1182: 1178: 1174: 1171: 1167: 1164: 1160: 1156: 1153: 1149: 1146:Interaction, 1145: 1142: 1138: 1134: 1130: 1126: 1123: 1120: 1116: 1112: 1109: 1105: 1102: 1098: 1097: 1093: 1089: 1088:deep learning 1084: 1080: 1077: 1069: 1067: 1065: 1061: 1057: 1050: 1046: 1042: 1038: 1034: 1030: 1027: 1023: 1018: 1015: 1012: 1008: 1005: 1001: 997: 994: 993: 992: 989: 987: 983: 979: 975: 973: 969: 965: 957: 955: 953: 949: 945: 936: 931: 926: 922: 918: 914: 910: 906: 902: 898: 897:visualization 894: 890: 886: 882: 876: 867: 865: 863: 859: 858:path planning 855: 848: 846: 844: 836: 834: 832: 827: 825: 821: 817: 813: 812:deep learning 809: 806: 801: 789: 781: 772: 768: 764: 757: 745: 743: 741: 738:even require 737: 736:image sensors 733: 729: 725: 721: 717: 713: 709: 708:image sensors 705: 698: 693: 689: 682: 680: 678: 673: 671: 667: 663: 659: 655: 651: 647: 643: 639: 635: 631: 627: 623: 619: 616: 612: 608: 604: 600: 596: 591: 589: 585: 581: 577: 573: 569: 565: 560: 557: 553: 545: 543: 541: 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: 5749:Hugging Face 5713:David Silver 5361:Audio–visual 5215:Applications 5194:Augmentation 5039: 4983: 4876:Eye tracking 4732:Applications 4698:Technologies 4684:Segmentation 4604: 4554: 4492: 4473: 4454: 4434: 4413: 4401:. Retrieved 4397:the original 4377: 4360:. Springer. 4356: 4329: 4310: 4287: 4267:. Springer. 4264: 4244: 4223: 4203: 4184: 4168:. Springer. 4164: 4144: 4122: 4102:Robot Vision 4101: 4075: 4054: 4034: 4010: 3988:. Retrieved 3979: 3969: 3934: 3928: 3909: 3903: 3843: 3839: 3826: 3815:. Retrieved 3808:the original 3763: 3759: 3746: 3726: 3705: 3662: 3658: 3648: 3637:. Retrieved 3628: 3618: 3607:. Retrieved 3554: 3550: 3528: 3522: 3503: 3497: 3452: 3448: 3392: 3388: 3378: 3367:. Retrieved 3332: 3322: 3311:. Retrieved 3276: 3266: 3239: 3235: 3225: 3198: 3194: 3184: 3165: 3137:. Retrieved 3135:. 2024-09-13 3132: 3123: 3081:(12): 1869. 3078: 3074: 3064: 3021: 3017: 3007: 2998: 2978: 2974: 2967: 2924: 2920: 2910: 2899:. Retrieved 2885: 2875: 2871: 2865: 2820: 2797:. Retrieved 2792: 2779: 2759: 2748:. Retrieved 2724: 2695: 2689: 2646: 2642: 2636: 2595: 2591: 2578: 2541: 2537: 2527: 2507: 2500: 2480: 2473: 2453: 2446: 2429: 2420: 2401: 2395: 2375: 2353: 2349: 2337:. Retrieved 2322: 2303: 2284: 2278: 2236: 2229: 2209: 2202: 2183: 2155: 2127: 2099:. Springer. 2096: 1977:As of 2016, 1976: 1970: 1958: 1923: 1920: 1916: 1891: 1887: 1883: 1861: 1835: 1795:segmentation 1789: 1746: 1723: 1705: 1699: 1687: 1683: 1670: 1659: 1655:Optical flow 1653: 1647: 1641: 1633: 1627: 1614: 1602: 1592: 1580: 1563: 1549: 1537: 1511: 1506: 1495: 1487: 1477: 1467: 1461: 1452: 1442: 1424: 1420: 1402:Surveillance 1391: 1381: 1377: 1348: 1338: 1330: 1322: 1311:submersibles 1308: 1296: 1278: 1253: 1243: 1225: 1191: 1185:mobile robot 1176: 1175:Navigation, 1169: 1147: 1128: 1114: 1100: 1073: 1070:Applications 1054: 1021: 1010: 1003: 990: 981: 976: 961: 958:Distinctions 948:optimization 940: 937:Other fields 852: 840: 828: 816:Neocognitron 804: 800:Neurobiology 798: 746:Neurobiology 702: 674: 592: 584:optical flow 561: 549: 537: 501: 492: 449: 441: 410: 409: 283:Chinese room 172:Applications 85: 5897:Categories 5845:Autoencoder 5800:Transformer 5668:Alex Graves 5616:OpenAI Five 5520:IBM Watsonx 5142:Convolution 5120:Overfitting 4784:Visual hull 4679:Researchers 3846:(5): 1657. 3665:(1): 1–68. 3480:2066/184075 2981:: 439–453. 2880:pages 60–62 2643:IEEE Access 2438:1721.1/6125 2287:. Thomson. 1739:Scale space 1571:data matrix 1449:Recognition 1386:Support of 1026:bin picking 767:sea urchins 595:scale-space 516:engineering 312:Turing test 288:Friendly AI 59:Major goals 5923:Categories 5886:Technology 5739:EleutherAI 5698:Fei-Fei Li 5693:Yann LeCun 5606:Q-learning 5589:Decisional 5515:IBM Watson 5423:Midjourney 5315:TensorFlow 5162:Activation 5115:Regression 5110:Clustering 4654:Morphology 4612:Categories 4403:2007-06-13 4030:David Marr 3817:2018-09-14 3717:1511.02999 3639:2022-12-23 3609:2020-11-20 3531:. Pearson. 3369:2022-11-06 3313:2022-11-06 3139:2024-09-19 2901:2018-01-10 2750:2018-01-30 2656:1907.09408 2080:References 1944:scanners, 1777:or points. 1765:Localized 1690:inpainting 1556:characters 1431:processing 1092:depth maps 1040:radiology. 944:statistics 887:, such as 808:neural net 668:and early 615:projective 572:algorithms 498:Definition 419:processing 317:Regulation 271:Philosophy 226:Healthcare 221:Government 123:Approaches 5769:MIT CSAIL 5734:Anthropic 5703:Andrew Ng 5601:AlphaZero 5445:VideoPoet 5408:AlphaFold 5345:MindSpore 5299:SpiNNaker 5294:Memristor 5201:Diffusion 5177:Rectifier 5157:Batchnorm 5137:Attention 5132:Adversary 3870:1424-8220 3788:1057-7149 3679:1529-1006 3629:TopTen.ai 3591:0920-5691 3564:1409.0575 3489:2041-210X 3427:230639179 3419:1757-899X 3359:235207036 3303:218564267 3258:2197-4225 3242:(1): 14. 3217:2197-4225 3201:(1): 11. 3097:2304-8158 3038:1134-3060 2995:219470398 2941:2398-6352 2730:Wiley-VCH 2681:198147317 2570:1573-1405 1791:Detection 1635:Egomotion 1607:(SRT) in 1597:emotions. 1489:Detection 1435:analyzing 1427:acquiring 1340:Curiosity 1298:Curiosity 1043:Finally, 885:3D models 650:Eigenface 423:analyzing 415:acquiring 347:AI winter 248:Military 111:AI safety 5877:Portals 5636:Auto-GPT 5468:Word2vec 5272:Hardware 5189:Datasets 5091:Concepts 4689:Software 4649:Learning 4639:Geometry 4619:Datasets 4541:CVonline 4531:Archived 4383:Springer 4354:(2005). 4309:(2004). 4286:(2003). 4143:(1993). 4098:(1986). 4032:(1982). 3984:Archived 3961:14111100 3892:Archived 3888:29789447 3804:51867241 3796:30059300 3735:Archived 3697:31313636 3633:Archived 3603:Archived 3363:Archived 3307:Archived 3115:38928810 3106:11202458 3056:29962832 2959:33420381 2927:(1): 5. 2895:Archived 2857:31373273 2799:11 March 2768:Archived 2744:Archived 2620:26017442 2544:(1): 1. 2333:Archived 2311:Archived 2267:Archived 1989:See also 1897:Hardware 1769:such as 1643:Tracking 1560:indexing 1275:Military 1206:Medicine 1196:indexing 1179:, by an 952:geometry 771:features 763:starfish 720: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 5759:Meta AI 5596:AlphaGo 5580:PanGu-Σ 5550:ChatGPT 5525:Granite 5473:Seq2seq 5452:Whisper 5373:WaveNet 5368:AlexNet 5340:Flux.jl 5320:PyTorch 5172:Sigmoid 5167:Softmax 5032:General 3879:5982167 3848:Bibcode 3840:Sensors 3768:Bibcode 3688:6640856 3599:2930547 3457:Bibcode 3397:Bibcode 3047:6003396 3000:others. 2950:7794558 2661:Bibcode 2628:3074096 2600:Bibcode 2339:18 July 1909:with a 1817:spatial 1809:salient 1771:corners 1754:Lines, 1353:rover. 1236:tumours 1110:system; 1033:imaging 905:virtual 716:visible 677:feature 599:shading 546:History 352:AI boom 330:History 253:Physics 5774:Huawei 5754:OpenAI 5656:People 5626:MuZero 5488:Gemini 5483:Claude 5418:DALL-E 5330:Theano 4499: 4480: 4461: 4442: 4421: 4389: 4364: 4336: 4317: 4294: 4271: 4252: 4231: 4210: 4191: 4172: 4151: 4129: 4110: 4084: 4061: 4042: 4035:Vision 4018: 3990:May 3, 3959: 3949: 3916: 3886: 3876: 3868: 3802: 3794: 3786: 3695: 3685: 3677: 3597: 3589: 3510: 3487: 3425: 3417: 3357: 3347: 3301: 3291: 3256: 3215: 3172: 3133:London 3113: 3103: 3095: 3054: 3044: 3036: 2993: 2957: 2947: 2939: 2855: 2845: 2736: 2702: 2679: 2626: 2618: 2592:Nature 2568: 2515: 2488: 2461: 2408: 2383: 2291: 2259: 2217: 2190: 2162: 2134: 2103: 1913:sensor 1760:ridges 1577:codes. 1350:Yutu-2 1194:, for 1131:, for 911:, and 732:optics 586:, and 512:videos 436:retina 302:Ethics 5840:Mamba 5611:SARSA 5575:LLaMA 5570:BLOOM 5555:GPT-J 5545:GPT-4 5540:GPT-3 5535:GPT-2 5530:GPT-1 5493:LaMDA 5325:Keras 3957:S2CID 3895:(PDF) 3836:(PDF) 3811:(PDF) 3800:S2CID 3756:(PDF) 3712:arXiv 3595:S2CID 3559:arXiv 3423:S2CID 3355:S2CID 3299:S2CID 3075:Foods 2991:S2CID 2853:S2CID 2789:(PDF) 2677:S2CID 2651:arXiv 2624:S2CID 2588:(PDF) 2270:(PDF) 2241:(PDF) 2058:Lists 1942:lidar 1911:LiDAR 1775:blobs 1756:edges 1567:ASCII 1260:Wafer 1220:DARPA 1117:, an 214:Music 209:Audio 5764:Mila 5565:PaLM 5498:Bard 5478:BERT 5461:Text 5440:Sora 4557:BMVA 4497:ISBN 4478:ISBN 4459:ISBN 4440:ISBN 4419:ISBN 4387:ISBN 4362:ISBN 4334:ISBN 4315:ISBN 4292:ISBN 4269:ISBN 4250:ISBN 4229:ISBN 4208:ISBN 4189:ISBN 4170:ISBN 4149:ISBN 4127:ISBN 4108:ISBN 4082:ISBN 4059:ISBN 4040:ISBN 4016:ISBN 3992:2016 3947:ISBN 3914:ISBN 3884:PMID 3866:ISSN 3792:PMID 3784:ISSN 3693:PMID 3675:ISSN 3587:ISSN 3508:ISBN 3485:ISSN 3415:ISSN 3345:ISBN 3289:ISBN 3254:ISSN 3213:ISSN 3170:ISBN 3111:PMID 3093:ISSN 3052:PMID 3034:ISSN 2955:PMID 2937:ISSN 2878:(6). 2843:ISBN 2801:2024 2734:ISBN 2700:ISBN 2616:PMID 2566:ISSN 2513:ISBN 2486:ISBN 2459:ISBN 2406:ISBN 2381:ISBN 2341:2017 2289:ISBN 2257:ISBN 2215:ISBN 2188:ISBN 2160:ISBN 2132:ISBN 2101:ISBN 1963:and 1819:and 1758:and 1660:i.e. 1648:e.g. 1573:and 1564:e.g. 1443:e.g. 1392:e.g. 1345:CNSA 1343:and 1335:NASA 1331:e.g. 1323:e.g. 1319:SLAM 1244:e.g. 1192:e.g. 1177:e.g. 1170:e.g. 1148:e.g. 1129:e.g. 1115:e.g. 1101:e.g. 1062:vs. 1022:e.g. 1011:e.g. 1004:e.g. 998:and 982:e.g. 970:and 907:and 810:and 805:e.g. 765:and 609:and 442:The 5505:NMT 5388:OCR 5383:HWR 5335:JAX 5289:VPU 5284:TPU 5279:IPU 5103:SGD 3939:doi 3874:PMC 3856:doi 3776:doi 3683:PMC 3667:doi 3577:hdl 3569:doi 3555:115 3475:hdl 3465:doi 3405:doi 3393:981 3337:doi 3281:doi 3244:doi 3203:doi 3101:PMC 3083:doi 3042:PMC 3026:doi 2983:doi 2979:407 2945:PMC 2929:doi 2833:hdl 2825:doi 2669:doi 2608:doi 2596:521 2556:hdl 2546:doi 2434:hdl 2249:doi 1347:'s 1337:'s 1315:UAV 1183:or 1135:or 950:or 722:or 510:or 204:Art 5925:: 4553:, 4385:. 4381:. 3982:. 3978:. 3955:. 3945:. 3890:. 3882:. 3872:. 3864:. 3854:. 3844:18 3842:. 3838:. 3798:. 3790:. 3782:. 3774:. 3764:27 3762:. 3758:. 3691:. 3681:. 3673:. 3663:20 3661:. 3657:. 3631:. 3627:. 3601:. 3593:. 3585:. 3575:. 3567:. 3553:. 3549:. 3537:^ 3483:. 3473:. 3463:. 3451:. 3447:. 3435:^ 3421:. 3413:. 3403:. 3391:. 3387:. 3361:. 3353:. 3343:. 3331:. 3305:. 3297:. 3287:. 3275:. 3252:. 3238:. 3234:. 3211:. 3197:. 3193:. 3148:^ 3131:. 3109:. 3099:. 3091:. 3079:13 3077:. 3073:. 3050:. 3040:. 3032:. 3022:25 3020:. 3016:. 2997:. 2989:. 2977:. 2953:. 2943:. 2935:. 2923:. 2919:. 2893:. 2876:35 2874:. 2851:. 2841:. 2831:. 2809:^ 2791:. 2742:. 2714:^ 2675:. 2667:. 2659:. 2645:. 2622:. 2614:. 2606:. 2594:. 2590:. 2564:. 2554:. 2542:77 2540:. 2536:. 2432:. 2361:^ 2331:. 2265:. 2255:. 2243:. 2174:^ 2146:^ 2115:^ 2087:^ 1952:, 1948:, 1940:, 1936:, 1932:, 1928:, 1905:A 1773:, 1692:. 1575:QR 1433:, 1429:, 1394:, 1333:, 1271:. 1238:, 1127:, 1066:. 988:. 966:, 946:, 923:, 919:, 903:, 895:, 891:, 826:. 718:, 672:. 660:, 590:. 540:AI 490:. 482:, 474:, 470:, 466:, 462:, 458:, 454:, 421:, 417:, 5018:e 5011:t 5004:v 4597:e 4590:t 4583:v 4505:. 4486:. 4467:. 4448:. 4427:. 4406:. 4370:. 4342:. 4323:. 4300:. 4277:. 4258:. 4237:. 4216:. 4197:. 4178:. 4157:. 4135:. 4116:. 4090:. 4067:. 4048:. 4024:. 3994:. 3963:. 3941:: 3922:. 3858:: 3850:: 3820:. 3778:: 3770:: 3720:. 3714:: 3699:. 3669:: 3642:. 3612:. 3579:: 3571:: 3561:: 3516:. 3491:. 3477:: 3467:: 3459:: 3453:9 3429:. 3407:: 3399:: 3372:. 3339:: 3316:. 3283:: 3260:. 3246:: 3240:7 3219:. 3205:: 3199:7 3178:. 3142:. 3117:. 3085:: 3058:. 3028:: 2985:: 2961:. 2931:: 2925:4 2904:. 2859:. 2835:: 2827:: 2803:. 2753:. 2708:. 2683:. 2671:: 2663:: 2653:: 2647:7 2630:. 2610:: 2602:: 2572:. 2558:: 2548:: 2521:. 2494:. 2467:. 2440:. 2436:: 2414:. 2389:. 2343:. 2297:. 2251:: 2223:. 2196:. 2168:. 2140:. 2109:. 1823:. 1793:/ 1762:. 1720:. 1562:( 1404:. 1187:; 1154:; 1143:; 1121:; 877:. 399:e 392:t 385:v 295:/ 20:)

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

Index