Rocky Mountain College * Department of Computer Science * 406 208 3193 * turn on javascript to see my email

Learning Dynamics of Complex Motions from Image Sequences

D. Reynard, A. Wildenberg, A. Blake and J. Marchant 4th European Conference on Computer Vision, Cambridge, England, April 1996.



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 with 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.
You know we're constantly taking. We don't make most of the food we eat, we don't grow it, anyway. We wear clothes other people make, we speak a language other people developed, we use a mathematics other people evolved and spent their lives building. I mean we're constantly taking things. It's a wonderful ecstatic feeling to create something and put it into the pool of human experience and knowledge. -- Steve Jobs, Rolling Stone, November 1983.