Structure from motion: sparse versus dense correspondence methods

Researchers in image processing and computer vision fields have agonized over the last twenty-five years, to come up with robust methods for the structure from motion (SFM) problem. Two dominant approaches, based on flow and feature correspondences have been pursued. Despite tremendous efforts, only limited success in special cases can be claimed. We feel that with the availability of newer, general, robust methods for computing optical flow, fast methods for estimating the focus of expansion (FOE), inexpensive cameras, and inertial information, robust, real-time solutions to this problem may be possible in the near future. Some of our recent work in these areas is presented.

[1]  R Chellappa,et al.  Noise-resilient estimation of optical flow by use of overlapped basis functions. , 1999, Journal of the Optical Society of America. A, Optics, image science, and vision.

[2]  Rama Chellappa,et al.  Model-based temporal object verification using video , 2001, IEEE Trans. Image Process..

[3]  Takeo Kanade,et al.  Constructing virtual worlds using dense stereo , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[4]  Bernd Girod,et al.  Data-driven structure from motion using the epipolar corridor constraint , 1997, Electronic Imaging.

[5]  Ramesh C. Jain,et al.  Structure from motion-a critical analysis of methods , 1991, IEEE Trans. Syst. Man Cybern..

[6]  Gilad Adiv,et al.  Determining Three-Dimensional Motion and Structure from Optical Flow Generated by Several Moving Objects , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Rama Chellappa,et al.  Statistical Analysis of Inherent Ambiguities in Recovering 3-D Motion from a Noisy Flow Field , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  John Oliensis,et al.  A Critique of Structure-from-Motion Algorithms , 2000, Comput. Vis. Image Underst..

[9]  Olivier Faugeras,et al.  Computation of inertial information on a Robot , 1991 .

[10]  Thomas S. Huang,et al.  Estimating three-dimensional motion parameters of a rigid planar patch , 1981 .

[11]  Alex Pentland,et al.  3D structure from 2D motion , 1999, IEEE Signal Process. Mag..

[12]  R. Chellappa,et al.  Recursive 3-D motion estimation from a monocular image sequence , 1990 .

[13]  A. Mitiche.  Computational Analysis of Visual Motion , 1994, Advances in Computer Vision and Machine Intelligence.

[14]  Harry Shum,et al.  Construction and refinement of panoramic mosaics with global and local alignment , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[15]  Ingemar J. Cox,et al.  A maximum-flow formulation of the N-camera stereo correspondence problem , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[16]  Shahriar Negahdaripour,et al.  IEEE Transactions on Pattern Analysis and Machine Intelligence , 2004 .

[17]  Alex Pentland,et al.  3 D Structure from 2 D Motion , 2001 .

[18]  Rama Chellappa,et al.  Estimation of Object Motion Parameters from Noisy Images , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Olivier D. Faugeras,et al.  Autonomous navigation of a mobile robot using inertial and visual cues , 1993, Proceedings of 1993 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS '93).

[20]  Amnon Shashua,et al.  Novel view synthesis in tensor space , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[21]  K. Hanna.  Direct multi-resolution estimation of ego-motion and structure from motion , 1991, Proceedings of the IEEE Workshop on Visual Motion.