Reconstruction of a Scene with Multiple Linearly Moving Objects

We describe an algorithm for reconstructing a scene containing multiple moving objects. Given a monocular image sequence, we recover the scene structure, the trajectories of the moving objects and the camera motion simultaneously. The number of the moving objects is automatically detected without prior motion segmentation. Assuming that the objects are moving linearly with constant speeds, we propose a unified geometrical representation of the static scene and the moving objects. This representation enables the embedding of the motion constraints into the scene structure, which leads to a factorization-based algorithm. Experimental results on synthetic and real images are presented.

[1]  Takeo Kanade,et al.  A Paraperspective Factorization Method for Shape and Motion Recovery , 1994, ECCV.

[2]  Harpreet S. Sawhney,et al.  Independent motion detection in 3D scenes , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[3]  Michael Werman,et al.  Trajectory triangulation over conic section , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[4]  Lihi Zelnik-Manor,et al.  Multi-view subspace constraints on homographies , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[5]  Rakesh Kumar,et al.  Shape Recovery from Multiple Views: A Parallax Based Approach , 1994 .

[6]  Michal Irani,et al.  Multi-frame optical flow estimation using subspace constraints , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[7]  T. Boult,et al.  Factorization-based segmentation of motions , 1991, Proceedings of the IEEE Workshop on Visual Motion.

[8]  Amnon Shashua,et al.  On the synthesis of dynamic scenes from reference views , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

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

[10]  Mei Han,et al.  Homography-Based 3D Scene Analysis of Video Sequences * , 1999 .

[11]  P. Anandan,et al.  Direct recovery of shape from multiple views: a parallax based approach , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[12]  Stéphane Christy,et al.  Euclidean Reconstruction: From Paraperspective to Perspective , 1996, ECCV.

[13]  Lior Wolf,et al.  Homography Tensors: On Algebraic Entities that Represent Three Views of Static or Moving Planar Points , 2000, ECCV.

[14]  P. Anandan,et al.  Direct Recovery of Planar-Parallax from Multiple Frames , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Michal Irani,et al.  Detecting and Tracking Multiple Moving Objects Using Temporal Integration , 1992, ECCV.

[16]  Charles R. Dyer,et al.  Interpolating view and scene motion by dynamic view morphing , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[17]  Daphna Weinshall,et al.  From Reference Frames to Reference Planes: Multi-View Parallax Geometry and Applications , 1998, ECCV.

[18]  Philip H. S. Torr,et al.  Outlier detection and motion segmentation , 1993, Other Conferences.

[19]  Michal Irani,et al.  Recovery of Ego-Motion Using Region Alignment , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  Amnon Shashua,et al.  Trajectory triangulation of lines: reconstruction of a 3D point moving along a line from a monocular image sequence , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[21]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.