Automatic extraction and tracking of contours

This paper considers the problem of extracting and tracking complex contours without user interaction. We assume that a complex contour consists of contour segments whose spatial coordinates and intensity gradient vary smoothly in the direction normal to themselves. In our algorithm, digital curves that could correspond to contour segments are extracted by connecting edge pixels using a B-spline based contour segment model. The extracted curves trace the contour segments at the next frame by using the active contour model technique. Experimental results show even occluded contours can be tracked automatically.

[1]  Olof Henricsson,et al.  Controlling growing snakes by using key-points , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[2]  J. O'Rourke,et al.  Model-based image analysis of human motion using constraint propagation , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Tsutomu Miyasato,et al.  Virtual space teleconferencing "Communication with realistic sensations" , 1995, Proceedings 4th IEEE International Workshop on Robot and Human Communication.

[4]  Marie-Odile Berger Snake growing , 1990, ECCV.

[5]  Ramesh C. Jain,et al.  Using Dynamic Programming for Solving Variational Problems in Vision , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Pascal Fua,et al.  Initializing snakes [object delineation] , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.