Reconstructing 3D independent motions using non-accidentalness

Reconstructing 3D scenes with independently moving objects from uncalibrated monocular image sequences still poses serious challenges. One important problem is to find the relative scales between these different reconstructed objects. The perspective reconstruction of a single object can only be known up to a certain scale which results in a one-parameter family of relative scales and trajectories per moving object. The paper formulates this ambiguity and proposes solutions in the vein of "non-accidentalness". Two instantiations of its use are analyzed: planar motion and the 'heading constraint'.

[1]  Andrew Zisserman,et al.  Multiple View Geometry , 1999 .

[2]  Takeo Kanade,et al.  Shape and motion from image streams under orthography: a factorization method , 1992, International Journal of Computer Vision.

[3]  S. Shankar Sastry,et al.  Two-View Segmentation of Dynamic Scenes from the Multibody Fundamental Matrix , 2002 .

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

[5]  Mei Han,et al.  Multiple motion scene reconstruction from uncalibrated views , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

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

[7]  T. Kanade,et al.  A multi-body factorization method for motion analysis , 1995, ICCV 1995.

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

[9]  Luc Van Gool,et al.  Reconstructing 3D trajectories of independently moving objects using generic constraints , 2004, Comput. Vis. Image Underst..

[10]  Andrew W. Fitzgibbon,et al.  Multibody Structure and Motion: 3-D Reconstruction of Independently Moving Objects , 2000, ECCV.

[11]  Peter F. Sturm.  Structure and Motion for Dynamic Scenes - The Case of Points Moving in Planes , 2002, ECCV.

[12]  Henning Biermann,et al.  Recovering non-rigid 3D shape from image streams , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[13]  M. Brand.  Morphable 3 D models from video , 2001 .

[14]  A. Shashua,et al.  On projection matrices P/sup k//spl rarr/P/sup 2/, k=3,...,6, and their applications in computer vision , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[15]  Amnon Shashua,et al.  Trajectory Triangulation: 3D Reconstruction of Moving Points from a Monocular Image Sequence , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  René Vidal.  A Factorization Method for 3 D Multi-body Motion Estimation and Segmentation ∗ , 2002 .

[17]  Matthew Brand,et al.  Morphable 3D models from video , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[18]  Lior Wolf,et al.  Two-body segmentation from two perspective views , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.