Combining Intensity and Motion for Incremental Segmentation and Tracking Over Long Image Sequences

This paper presents a method for incrementally segmenting images over time using both intensity and motion information. This is done by formulating a model of physically signi cant image resgions using local constraints on intensity and motion and then nding the optimal segmentation over time using an incremental stochastic minimization technique. The result is a robust and dynamic segmentation of the scene over a sequence of images. The approach has a number of bene ts. First, discontinuities are extracted and tracked simultaneously. Second, a segmentation is always available and it improves over time. Finally, by combining motion and intensity, the structural properties of discontinuities can be recovered; that is, discontinuities can be classi ed as surface markings or actual surface boundaries.

• Type: Conference
• Year: 1992
• Where: ECCV
• Authors: Michael J. Black
• Keywords: Actual Surface Boundaries, Computer Vision, Dynamic Segmentation, ECCV 1992, Incremental Stochastic Minimization, Optimal Segmentation