Recognizing activities

The recognition of repetitive movements characteristic of walking people, galloping horses, or flying birds is a routine function of the human visual system. It has been demonstrated that humans can recognize such activity solely on the basis of motion information. We demonstrate a general computational method for recognizing such movements in real image sequences using what is essentially template matching in a motion feature space coupled with a technique for detecting and normalizing periodic activities. This contrasts with earlier model-based approaches for recognizing such activities.

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

[2]  P. J. Burt,et al.  Change Detection and Tracking Using Pyramid Transform Techniques , 1985, Other Conferences.

[3]  Randal C. Nelson,et al.  Detecting activities , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

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

[5]  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.

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