3D Motion Segmentation from Straight-Line Optical Flow

We present a closed form solution to the problem of segmenting multiple 3D motion models from straight-line optical flow. We introduce the multibody line optical flow constraint(MLOFC), a polynomial equation relating motion models and line parameters. We show that the motion models can be obtained analytically as the derivative of the MLOFC at the corresponding line measurement, without knowing the motion model associated with that line. Experiments on real and synthetic sequences are also presented.

[1]  René Vidal,et al.  A Unified Algebraic Approach to 2-D and 3-D Motion Segmentation , 2004, ECCV.

[2]  Jianhua Wang,et al.  Motion segmentation of multiple translating objects using line correspondences , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[3]  P. Torr.  Geometric motion segmentation and model selection , 1998, Philosophical Transactions of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[4]  Pietro Perona,et al.  Scene segmentation from 3D motion , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[5]  Yang Su-hua.  Reconstructing 3D rotation motion parameters from 2D image straight-line optical flow , 2005 .

[6]  Richard Szeliski,et al.  An Integrated Bayesian Approach to Layer Extraction from Image Sequences , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  René Vidal,et al.  A Bottom up Algebraic Approach to Motion Segmentation , 2006, ACCV.

[8]  René Vidal,et al.  A closed form solution to direct motion segmentation , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[9]  Rachid Deriche,et al.  Information contained in the motion field of lines and the cooperation between motion and stereo , 1990, Int. J. Imaging Syst. Technol..

[10]  Marc Pollefeys,et al.  Articulated Motion Segmentation Using RANSAC with Priors , 2006, WDV.

[11]  Jing Zhang,et al.  Motion Segmentation by Multibody Trifocal Tensor Using Line Correspondence , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[12]  René Vidal,et al.  The Space of Multibody Fundamental Matrices: Rank, Geometry and Projection , 2006, WDV.

[13]  Peter H. Tu,et al.  Simultaneous estimation of segmentation and shape , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[14]  Dmitry Chetverikov,et al.  Robust 3D Segmentation of Multiple Moving Objects Under Weak Perspective , 2006, WDV.

[15]  R. Vidal,et al.  The multibody trifocal tensor: motion segmentation from 3 perspective views , 2004, CVPR 2004.

[16]  S. Shankar Sastry,et al.  Generalized principal component analysis (GPCA) , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  René Vidal,et al.  Optical flow estimation & segmentation of multiple moving dynamic textures , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).