This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
MDL-Based Segmentation and Motion Modeling in a Long Image Sequence of Scene with Multiple Independently Moving Objects
January 1996 (vol. 18 no. 1)
pp. 58-64

Abstract—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] G. Adiv, "Determining three-dimensional motion and structure form optical flow generated by several moving objects," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 7, pp. 384-401, 1985.
[2] P. Bouthemy and E. Francois, "Motion segmentation and qualitative dynamic scene analysis from an image sequence," Int'l J. Computer Vision, vol. 10, no. 2, pp. 157-182, 1993.
[3] H. Gu, M. Asada, and Y. Shirai, "The optimal partition of moving edge segments," Proc. CVPR'93,New York, pp. 367-372, 1993.
[4] H. Gu, "MDL-based segmentation and motion modeling in scenes with multiple independently moving objects," PhD dissertation, Osaka Univ., 1994.
[5] M. Irani, B. Rousso, and S. Peleg, “Computing Occluding and Transparent Motions,” Int'l J. Computer Vision, vol. 12, no. 1, pp. 5-16, Jan. 1994.
[6] S.P. Liou and R.C. Jain, "Qualitative motion analysis using a spatio-temporal approach," Proc. CVPR'91,Lahaina, Maui, Hawaii, pp. 726-727, 1991.
[7] D. Murray and B. Buxton, Scene Segmentation from Visual Motion Using Global Optimization IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 9, no. 2, pp. 220-228, Feb. 1987.
[8] S. Niyogi and E. Adelson, Analyzing and Recognizing Walking Figures in XYT Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, pp. 469-474, 1994.
[9] F. Restle, "Coding theory of the perception of motion configurations," Psychological Review, vol. 86, no. 1, pp. 1-24, 1979.
[10] J. Rissanen, Stochastic Complexity in Statistical Inquiry. World Scientific Series in Computer Science, vol. 15, 1989.
[11] B. Schunck, Image Flow Segmentation and Estimation by Constraint Line Clustering IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 11, no. 10, pp. 1010-1027, Oct. 1989.

Index Terms:
Long image sequence, spatiotemporal segmentation, motion estimation, MDL principle.
Citation:
Haisong Gu, Yoshiaki Shirai, Minoru Asada, "MDL-Based Segmentation and Motion Modeling in a Long Image Sequence of Scene with Multiple Independently Moving Objects," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 18, no. 1, pp. 58-64, Jan. 1996, doi:10.1109/34.476012
Usage of this product signifies your acceptance of the Terms of Use.