Active Rays: A New Approach to Contour Tracking

Abstract

In this paper we describe a new approach to contour extraction and tracking, which is based on the principles of active contour models, yet it overcomes its shortcomings. We formally introduce active rays, describe the contour extraction as an e nergy minimization problem and discuss what active contours and active rays have in common.

The main difference is that for active rays a unique ordering of the contour elements in the 2D image plane is given, which cannot be found for active conto urs. This is advantageous for pred icting the contour elements' position and prevents crossings in the contour. Furthermore, another advantage of this approach is that instead of an energy minimization in the 2D image plane the minimization is reduced to a 1D search problem. The approach a lso shows any-time behavior which is important with respect to real- time applications. Finally, the method allows for the management of multiple hypotheses of the object's boundary.

First results on real image sequences show the suitability of this approach for real- time object tracking. The contour tracking can be done within the image frame rate (25 fps) on standard Unix workstations (HP 735).