MDL-Based Segmentation and Motion Modeling in a Long Image Sequence of Scene with Multiple Independently Moving Objects

This paper presents a method for spatiotemporal segmentation of long image sequences of scenes which include multiple independently moving objects, based on the minimum description length (MDL) principle. First, a family of motion models is constructed, each of which corresponds to a physically meaningful motion such as translation with constant velocity or a combination of translation and rotation. Then, the motion description length is formulated. When an object changes the type of the motion or a new part of an object appears, the corresponding temporal or spatial segmentation is carried out. Ambiguous segmentation of two consecutive images can be resolved by minimizing the motion description length in a long sequence of images. Experiments on several real image sequences show the validity of our method.

[1]  Ramesh C. Jain,et al.  Qualitative motion analysis using a spatio-temporal approach , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[2]  Minoru Asada,et al.  The optimal partition of moving edge segments , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[3]  F. Restle.  Coding theory of the perception of motion configurations. , 1979, Psychological review.

[4]  David W. Murray,et al.  Scene Segmentation from Visual Motion Using Global Optimization , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Brian G. Schunck,et al.  Image Flow Segmentation and Estimation by Constraint Line Clustering , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Jorma Rissanen,et al.  Stochastic Complexity in Statistical Inquiry , 1989, World Scientific Series in Computer Science.

[7]  Edward H. Adelson,et al.  Analyzing and recognizing walking figures in XYT , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Gilad Adiv,et al.  Determining Three-Dimensional Motion and Structure from Optical Flow Generated by Several Moving Objects , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  顧 海松,et al.  MDL-based segmentation and motion modeling in scenes with multiple independently moving objects , 1994 .

[10]  Patrick Bouthemy,et al.  Motion segmentation and qualitative dynamic scene analysis from an image sequence , 1993, International Journal of Computer Vision.