Structure and Motion Estimation from Dynamic Silhouettes under Perspective Projection

Addresses the problem of estimating the structure and motion of a smooth curved object from its silhouettes observed over time by a trinocular stereo rig under perspective projection. We first construct a model for the local structure along the silhouette for each frame in the temporal sequence. Successive local models are then integrated into a global surface description by estimating the motion between successive time instants. The algorithm tracks certain surface features (parabolic points) and image features (silhouette inflections and frontier points) which are used to bootstrap the motion estimation process. The entire silhouette along with the reconstructed local structure are then used to refine the initial motion estimate. We have implemented the proposed approach and report results on real images.<<ETX>>

[1]  David J. Kriegman,et al.  HOT curves for modelling and recognition of smooth curved 3D objects , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Kiriakos N. Kutulakos,et al.  Global surface reconstruction by purposive control of observer motion , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Manfredo P. do Carmo,et al.  Differential geometry of curves and surfaces , 1976 .

[4]  Olivier D. Faugeras,et al.  Using Extremal Boundaries for 3-D Object Modeling , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Richard S. Weiss,et al.  Reconstruction of Surfaces from Profiles , 1987, ICCV 1987.

[6]  Olivier Faugeras,et al.  Disambiguating stereo matches with spatio-temporal surfaces , 1992 .

[7]  J J Koenderink,et al.  What Does the Occluding Contour Tell Us about Solid Shape? , 1984, Perception.

[8]  Jan J. Koenderink,et al.  Solid shape , 1990 .

[9]  Richard Szeliski,et al.  Robust Shape Recovery from Occluding Contours Using a Linear Smoother , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Peter J. Giblin,et al.  Epipolar curves on surfaces , 1995, Image Vis. Comput..

[11]  P. Giblin,et al.  Recovery of an unknown axis of rotation from the profiles of a rotating surface , 1994 .

[12]  Jiang Yu Zheng,et al.  Acquiring 3-D Models from Sequences of Contours , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Andrew Blake,et al.  Robust Estimation of Surface Curvature from Deformation of Apparent Contours , 1990, ECCV.

[14]  Roger Y. Tsai,et al.  A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses , 1987, IEEE J. Robotics Autom..

[15]  J. H. Rieger.  Three-dimensional motion from fixed points of a deforming profile curve. , 1986, Optics letters.

[16]  Roger Mohr,et al.  Relative 3D Regularized B-spline Surface Reconstruction Through Image Sequences , 1994, ECCV.

[17]  Roger Mohr,et al.  An Egomotion Algorithm Based on the Tracking of Arbitrary Curves , 1992, ECCV.

[18]  Frank E. Pollick,et al.  Moving Surfaces , 1992, IMA Conference on the Mathematics of Surfaces.

[19]  O. D. Faugeras,et al.  Building three-dimensional CAD/CAM models from image sequences , 1994, Proceedings of 1994 IEEE 2nd CAD-Based Vision Workshop.

[20]  Roberto Cipolla,et al.  Motion from the frontier of curved surfaces , 1995, Proceedings of IEEE International Conference on Computer Vision.