Book contents
- Frontmatter
- Contents
- List of figures
- Notes on contributors
- Acknowledgments
- Introduction
- Part I Foundations
- Part II Architectures
- Part III Dimensions
- 7 Learning
- 8 Perception and computer vision
- 9 Reasoning and decision making
- 10 Language and communication
- 11 Actions and agents
- 12 Artificial emotions and machine consciousness
- Part IV Extensions
- Glossary
- Index
- References
8 - Perception and computer vision
Published online by Cambridge University Press: 05 July 2014
Book contents
- Frontmatter
- Contents
- List of figures
- Notes on contributors
- Acknowledgments
- Introduction
- Part I Foundations
- Part II Architectures
- Part III Dimensions
- 7 Learning
- 8 Perception and computer vision
- 9 Reasoning and decision making
- 10 Language and communication
- 11 Actions and agents
- 12 Artificial emotions and machine consciousness
- Part IV Extensions
- Glossary
- Index
- References
Summary
The wish to build artificial and intelligent systems leads to the expectation that they will operate in our typical environments. Hence, the expectations on their perceptual capabilities are high. Perception refers to the process of becoming aware of the elements of the environment through physical sensation, which can include sensory input from the eyes, ears, nose, tongue, or skin. In this chapter we focus on visual perception, which is the dominant sense in humans and has been used from the first days of building artificial machines. Two early examples are Shakey, a mobile robot with range finder and camera to enable it to reason about its actions in a room with a few objects (Nilsson 1969), and FREDDY, a fixed robot with a binocular vision system controlling a two-finger hand (e.g., Barrow and Salter 1969).
The goal of computer vision is to understand the scene or features in images of the real world (Ballard and Brown 1982; Forsyth and Ponce 2011). Important means to achieve this goal are the techniques of image processing and pattern recognition (Duda and Hart 1973; Gonzales and Woods 2002). The analysis of images is complicated by the fact that one and the same object may present many different appearances to the camera depending on the illumination cast onto the object, the angle from which it is viewed, the shadows it casts, the specific camera used, whether object parts are occluded, and so forth. Nevertheless, today computer vision is sufficiently well advanced to detect specific objects and object categories in a variety of conditions, to enable an autonomous vehicle to drive at moderate speeds on open roads, to steer a mobile robot through a suite of offices, and to observe and to understand human activities.
Keywords
- Type
- Chapter
- Information
- The Cambridge Handbook of Artificial Intelligence , pp. 168 - 190Publisher: Cambridge University PressPrint publication year: 2014
References
and (1982). Computer Vision. Englewood Cliffs, NJ: Prentice Hall. The basic book on methods in computer vision. Available online: .Google Scholar
, , , and (2009). Object Cat-egorization: Computer and Human Vision Perspectives. Cambridge University Press. Excellent overview of approaches to object recognition, including a historical perspective. A must to get started in this direction.CrossRefGoogle Scholar
and (2011). Computer Vision: A Modern Approach (2nd edn.). Upper Saddle River, NJ: Prentice Hall. A broad collection of computer vision techniques that is a very good reference for the advanced study of computer vision.Google Scholar
and (2003). Multiple View Geometry in Computer Vision (2nd edn.). Cambridge University Press. Provides deep coverage of geometrical aspects in computer vision for the advanced reader.Google Scholar
and (2009). Vision for robotics, Foundations and Trends in Robotics, 1: 1–78. An overview of the specific needs of robotics to computer vision methods plus a survey of applications.CrossRefGoogle Scholar
(2010). Computer Vision: Algorithms and Applications, London: Springer. An excellent textbook for the introduction and more in-depth study of computer vision. It has an emphasis on techniques that combine computer vision and graphics, but covers also modern techniques for object recognition, segmentation, and motion estimation. Available on-line: Google Scholar
Finally, two great open-source collections of vision methods are openCV () and the Point Cloud Library ().
, , , et al. (2008). Toward humanoid manipulation in human-centred environments, Robotics and Autonomous Systems 56: 54–65.CrossRefGoogle Scholar
(1981). Generalizing the Hough transform to detect arbitrary shapes, Pattern Recognition, 13: 111–22.CrossRefGoogle Scholar
and (1969). Design of low-cost equipment for cognitive robot research, in and (eds.), Machine Intelligence 5 (pp. 555–66). Edinburgh University Press.Google Scholar
(1971). Visual perception by a computer, in Proceedings of the IEEE Conference on Systems and Control (pp. 116–23). IEEE.Google Scholar
, , , et al. (1999). The kidsroom: A perceptually-based interactive and immersive story environment, PRESENCE: Teleoperators and Virtual Environments, 8: 369–93.CrossRefGoogle Scholar
(1980). “Put-that-there”: Voice and gesture at the graphics interface, ACM SIGGRAPH Computer Graphics, 14: 262–70.CrossRefGoogle Scholar
and (2000). Infant-like social interactions between a robot and a human caregiver, Adaptive Behavior, 8: 49–74.CrossRefGoogle Scholar
(1983). Model-based 3D interpretation of 2D images, IEEE Transactions on Pattern Analysis and Machine Intelligence, 5: 140–50.CrossRefGoogle Scholar
(2003). Learning and understanding dynamic scene activity: A review, Vision Computing, 21: 125–36.CrossRefGoogle Scholar
and (2006). Visual servo control I: Basic approaches, IEEE Robotics and Automation Magazine, 13(4): 82–90.CrossRefGoogle Scholar
and (eds.) (1995) Vision as Process: Basic Research on Computer Vision Systems. Berlin: Springer.CrossRefGoogle Scholar
, , and (2000). Perceptual user interfaces: Things that see, Communications of the ACM, 43(3): 54–64.CrossRefGoogle Scholar
, , , and (2002). Perceptual components for context aware computing, in and (eds.), UbiComp 2002: Ubiquitous Computing (Lecture Notes in Computer Science 2498) (pp. 117–34). Berlin: Springer.CrossRefGoogle Scholar
, , and (2003). Behaviour recognition for individuals, groups of people and crowds, IEE Symposium on Intelligent Distributed Surveillance Systems, 7: 1–5.Google Scholar
and (2011). Computer Vision: A Modern Approach (2nd edn.). Upper Saddle River, NJ: Prentice Hall.Google Scholar
and (2002). Digital Image Processing (2nd edn.). Upper Saddle River, NJ: Prentice Hall.Google Scholar
and (2003). Multiple View Geometry in Computer Vision (2nd edn.). Cambridge University Press.Google Scholar
, , and (2006). Putting objects in perspective, in Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), (pp. 2137–44). IEEE.Google Scholar
and (1990). Recognizing solid objects by alignment with an image, International Journal of Computer Vision, 5: 195–212.CrossRefGoogle Scholar
, , and (2000). Segmentation and Recovery of Superquadrics. Dordrecht: Kluwer Academic Publishers.CrossRefGoogle Scholar
, , and (2005). Real-Time Vision for Human–Computer Interaction. New York: Springer.CrossRefGoogle Scholar
. (1987). An internal representation for solid shape based on the topological properties of the apparent contour, in and (eds.), Image understanding 1985–86 (pp. 257–85). Norwood, NJ: Ablex.Google Scholar
(2004). Distinctive image features from scale-invariant keypoints, International Journal of Computer Vision, 60: 91–110.CrossRefGoogle Scholar
, ., and (1999). Exploiting human actions and object context for recognition tasks, in Proceedings of IEEE International Conference on Computer Vision (pp. 80–86). Corfu, Greece: IEEE.CrossRefGoogle Scholar
, , , , and (2010). BLORT – The blocks world robotic vision toolbox, in Proceedings of the ICRA 2010 Workshop on Best Practice in 3D Perception and Modeling for Mobile Manipulation.
(1969). Mobile automaton: An application of artificial intelligence techniques, Technical Note 40, AI Center, SRI International; also in Proceedings of the First International Joint Conference on Artificial Intelligence (pp. 509–20).
, , and (1997). Visual interpretation of hand gestures for human-computer interaction: A review, IEEE Transactions on Pattern Analysis and Machine Intelligence, 19: 677–95.CrossRefGoogle Scholar
(2004). Background subtraction techniques: A review, IEEE International Conference on Systems, Man and Cybernetics, 4: 3099–104).Google Scholar
, and (2005). Recognition of action, activity and behaviour in the ActIPret project, KI 19(2): 36–39.Google Scholar
, ., and (1994).Context aware computing applications, in Proceedings of the First International Workshop on Mobile Computing Systems and Applications (pp. 85–90).
and (eds.) (2001). From Fragments to Objects: Segmentation and Grouping in Vision. Amsterdam: Elsevier.Google Scholar
and (1990). Recovery of parametric models from range images: The case for superquadrics with global deformations, IEEE Transactions on Pattern Analysis and Machine Intelligence, 12: 131–47.CrossRefGoogle Scholar
. and (1991). Context-based vision: Recognizing objects using information from both 2D and 3D imagery, IEEE Transactions on Pattern Analysis and Machine Intelligence, 13: 1050–65.CrossRefGoogle Scholar
, , , et al. (2006) A real-time scene understanding system for airport apron monitoring, in Fourth IEEE International Conference on Computer Vision Systems (ICVS’06) (p. 26).
and (2005). Intelligent distributed surveillance systems: A review, IEE Proceedings: Vision, Image and Signal Processing 152: 192–204.Google Scholar
(2005). On the design and structure of artificial eyes for tracking tasks, Journal of Advanced Computational Intelligence and Intelligent Informatics, 9: 353–60.CrossRefGoogle Scholar
, , and (2007) Coordinating interactive vision behaviors for cognitive assistance, Computer Vision and Image Understanding 108: 135–49.CrossRefGoogle Scholar
and . (2010). 3D object classification for mobile robots in home-environments using web-data, in IEEE 19th International Workshop on Robotics in Alpe-Adria-Danube Region (RAAD) (pp. 247–52).
and (2006). Beyond tracking: Modelling activity and understanding behaviour, International Journal of Computer Vision, 67: 21–51.CrossRefGoogle Scholar
- 2
- Cited by