Learning Dynamics of Complex Motions from Image Sequences

The performance of Active Contours in tracking is highly dependent on the availability of an appropriate model of shape and motion, to use as a predictor. Models can be hand-built, but it is far more effective and less time-consuming to learn them from a training set. Techniques to do this exist both for shape, and for shape and motion jointly. This paper extends the range of shape and motion models in two significant ways. The first is to model jointly the random variations in shape arising within an object-class and those occuring during object motion. The resulting algorithm is applied to tracking of plants captured by a video camera mounted on an agricultural robot. The second addresses the tracking of coupled objects such as head and lips. In both cases, new algorithms are shown to make important contributions to tracking performance.

[1]  Timothy F. Cootes,et al.  Building and using flexible models incorporating grey-level information , 1993, 1993 (4th) International Conference on Computer Vision.

[2]  Y. Bar-Shalom.  Tracking and data association , 1988 .

[3]  Michael Isard,et al.  Learning to Track the Visual Motion of Contours , 1995, Artif. Intell..

[4]  David C. Hogg,et al.  Generating Spatiotemporal Models from Examples , 1995, BMVC.

[5]  Richard S. Stephens.  Real-Time 3D Object Tracking , 1989, Alvey Vision Conference.

[6]  Chris Harris,et al.  Tracking with rigid models , 1993 .

[7]  B. Brown.  Proceedings of the Society of Photo-optical Instrumentation Engineers , 1975 .

[8]  Graham C. Goodwin,et al.  Adaptive filtering prediction and control , 1984 .

[9]  Andrew Blake,et al.  Determining facial expressions in real time , 1995, Proceedings of IEEE International Conference on Computer Vision.

[10]  Alex Pentland,et al.  Recovery of Nonrigid Motion and Structure , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Richard Szeliski,et al.  Physically based and probabilistic models for computer vision , 1991, Optics & Photonics.

[12]  Michael Isard,et al.  3D position, attitude and shape input using video tracking of hands and lips , 1994, SIGGRAPH.

[13]  Richard Szeliski,et al.  Tracking with Kalman snakes , 1993 .

[14]  A.H. Haddad,et al.  Applied optimal estimation , 1976, Proceedings of the IEEE.