Computing spatiotemporal relations for dynamic perceptual organization

Abstract To date, the overwhelming use of motion in computational vision has been to recover the three-dimensional structure of the scene. We propose that there are other, more powerful, uses for motion. Toward this end, we define dynamic perceptual organization as an extension of the traditional (static) perceptual organization approach. Just as static perceptual organization groups coherent features in an image, dynamic perceptual organization groups coherent motions through an image sequence. Using dynamic perceptual organization, we propose a new paradigm for motion understanding and show why it can be done independently of the recovery of scene structure and scene motion. The paradigm starts with a spatiotemporal cube of image data and organizes the paths of points so that interactions between the paths, and perceptual motions such as common , relative , and cyclic are made explicit. The results of this can then be used for high-level motion recognition tasks.

[1]  Charles R. Dyer,et al.  Cyclic motion detection using spatiotemporal surfaces and curves , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[2]  David G. Lowe,et al.  Perceptual Organization and Visual Recognition , 2012 .

[3]  Charles R. Dyer,et al.  Computing spatiotemporal surface flow , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[4]  R. Baron,et al.  Toward an Ecological Theory of Social Perception , 1983 .

[5]  G. Johansson.  Visual perception of biological motion and a model for its analysis , 1973 .

[6]  Randal C. Nelson,et al.  Recognition of motion from temporal texture , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[7]  M. Allmen.  Image sequence description using spatiotemporal flow curves: toward motion-based recognition , 1992 .

[8]  S. Ullman,et al.  The interpretation of visual motion , 1977 .

[9]  D. Marr,et al.  Representation and recognition of the movements of shapes , 1982, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[10]  J HOCHBERG,et al.  The psychophysics of form: reversible-perspective drawings of spatial objects. , 1960, The American journal of psychology.

[11]  J. Cutting,et al.  Gait Perception as an Example of How We May Perceive Events , 1981 .

[12]  Junji Yamato,et al.  Recognizing human action in time-sequential images using hidden Markov model , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[13]  Y. Aloimonos,et al.  Visual shape computation , 1988, Proc. IEEE.

[14]  Thomas O. Binford,et al.  Perceptual Organization as a Basis for Visual Recognition , 1983, AAAI.

[15]  Gyorgy Kepes.  The Nature and Art of Motion , 1965 .

[16]  Koichiro Akita,et al.  Image sequence analysis of real world human motion , 1984, Pattern Recognit..

[17]  E. Spelke.  Origins of visual knowledge , 1990 .

[18]  J. Hochberg.  Effects of the Gestalt revolution: the Cornell symposium on perception. , 1957, Psychology Review.

[19]  J. Cutting,et al.  The minimum principle and the perception of absolute, common, and relative motions , 1982, Cognitive Psychology.

[20]  J. M. Watt.  Numerical Initial Value Problems in Ordinary Differential Equations , 1972 .

[21]  David C. Hogg.  Model-based vision: a program to see a walking person , 1983, Image Vis. Comput..

[22]  A. Witkin,et al.  On the Role of Structure in Vision , 1983 .

[23]  S. Runeson,et al.  Visual perception of lifted weight. , 1981, Journal of experimental psychology. Human perception and performance.

[24]  Charles R. Dyer,et al.  Long-range spatiotemporal motion understanding using spatiotemporal flow curves , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[25]  Yiannis Aloimonos,et al.  Purposive and qualitative active vision , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[26]  Ramesh C. Jain,et al.  Invariant surface characteristics for 3D object recognition in range images , 1985, Comput. Vis. Graph. Image Process..

[27]  Mubarak Shah,et al.  The trajectory primal sketch: a multi-scale scheme for representing motion characteristics , 1989, Proceedings CVPR '89: IEEE Computer Society Conference on Computer Vision and Pattern Recognition.