Incremental motion segmentation in low texture

The paper studies segmentation of moving objects with low texture in a low textured background. We describe an algorithm that resolves the difficulties associated with other approaches by integrating over time the information in the video sequence. We motivate and demonstrate our approach by building the background and moving object world images, important constructs in generative video.

[1]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[2]  Anil K. Jain,et al.  Contour extraction of moving objects in complex outdoor scenes , 1995, International Journal of Computer Vision.

[3]  José M. F. Moura,et al.  Content-based video sequence representation , 1995, Proceedings., International Conference on Image Processing.

[4]  Michal Irani,et al.  Motion Analysis for Image Enhancement: Resolution, Occlusion, and Transparency , 1993, J. Vis. Commun. Image Represent..

[5]  Serge Ayer,et al.  Sequential and competitive methods for estimation of multiple motions , 1995 .