Motion Segmentation at Any Speed

We present an incremental approach to motion segmentation. Feature points are detected and tracked throughout an image sequence, and the features are grouped using a region-growing algorithm with an affine moti on model. The primary parameter used by the algorithm is the amount of evidence that must accumulate before features are grouped. Contrasted with previous work, the algorithm allows for a variable number of image frames to affect the decision process, thus enabling objects to be detected independently of their velocity in the image. Procedures are presented for grouping features, measuring the consistency of the resulting groups, assimilating new feat ures into existing groups, and splitting groups over time. Experimental results on a number of challenging image sequences demonstrate the effectiveness of the technique.

[1]  Jitendra Malik,et al.  Motion segmentation and tracking using normalized cuts , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[2]  S. Shankar Sastry,et al.  Optimal segmentation of dynamic scenes from two perspective views , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[3]  Lihi Zelnik-Manor,et al.  Multi-body Factorization with Uncertainty: Revisiting Motion Consistency , 2005, International Journal of Computer Vision.

[4]  Daniel Cremers,et al.  Motion Competition: A Variational Approach to Piecewise Parametric Motion Segmentation , 2005, International Journal of Computer Vision.

[5]  Brendan J. Frey,et al.  Learning flexible sprites in video layers , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[6]  Edward H. Adelson,et al.  Representing moving images with layers , 1994, IEEE Trans. Image Process..

[7]  Andrew Zisserman,et al.  Object Level Grouping for Video Shots , 2004, International Journal of Computer Vision.

[8]  Cordelia Schmid,et al.  Segmenting, modeling, and matching video clips containing multiple moving objects , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[9]  Harpreet S. Sawhney,et al.  Layered representation of motion video using robust maximum-likelihood estimation of mixture models and MDL encoding , 1995, Proceedings of IEEE International Conference on Computer Vision.

[10]  Edward H. Adelson,et al.  A unified mixture framework for motion segmentation: incorporating spatial coherence and estimating the number of models , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[11]  Mubarak Shah,et al.  Accurate motion layer segmentation and matting , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[12]  Serge J. Belongie,et al.  What went where , 2003, CVPR 2003.

[13]  M. Irani,et al.  Multi-body Segmentation : Revisiting Motion Consistency , 2002 .

[14]  Takeo Kanade,et al.  A subspace approach to layer extraction , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[15]  Pascal Fua,et al.  Combining Stereo and Monocular Information to Compute Dense Depth Maps that Preserve Depth Discontinuities , 1991, IJCAI.

[16]  Carlo Tomasi,et al.  Good features to track , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.