A unifying framework for structure and motion recovery from image sequences

The paper proposes a statistical framework that enables 3D structure and motion to be computed optimally from an image sequence, on the assumption that feature measurement errors are independent and Gaussian distributed. The analysis and results demonstrate that computing both camera/scene motion and 3D structure is essential to computing either with any accuracy. Having computed optimal estimates of structure and motion over a small number of initial images, a recursive version of the algorithm (previously reported) recomputes sub optimal estimates given new image data. The algorithm is designed explicitly for real time implementation, and the complexity is proportional to the number of tracked features. 3D projective, affine and Euclidean models of structure and motion recovery have been implemented, incorporating both point and line features into the computation. The framework can handle any feature type and camera model that may be encapsulated as a projection equation from scene to image.<<ETX>>

[1]  C. A. HART,et al.  Manual of Photogrammetry , 1947, Nature.

[2]  J. Canny.  Finding Edges and Lines in Images , 1983 .

[3]  Christopher G. Harris,et al.  3D positional integration from image sequences , 1988, Image Vis. Comput..

[4]  Narendra Ahuja,et al.  Motion and Structure From Two Perspective Views: Algorithms, Error Analysis, and Error Estimation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Olivier D. Faugeras,et al.  Tracking and grouping 3D line segments , 1990, [1990] Proceedings Third International Conference on Computer Vision.

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

[7]  J J Koenderink,et al.  Affine structure from motion. , 1991, Journal of the Optical Society of America. A, Optics and image science.

[8]  Olivier D. Faugeras,et al.  What can be seen in three dimensions with an uncalibrated stereo rig , 1992, ECCV.

[9]  Rajiv Gupta,et al.  Stereo from uncalibrated cameras , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[10]  S. B. Kang,et al.  Recovering 3 D Shape and Motion from Image Streams using Non-Linear Least Squares , 1993 .

[11]  Richard I. Hartley,et al.  Euclidean Reconstruction from Uncalibrated Views , 1993, Applications of Invariance in Computer Vision.

[12]  Narendra Ahuja,et al.  Optimal Motion and Structure Estimation , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Alex Pentland,et al.  Recursive estimation of structure and motion using relative orientation constraints , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[14]  Paul A. Beardsley,et al.  Navigation using Affine Structure from Motion , 1994, ECCV.

[15]  Narendra Ahuja,et al.  Integrated 3D Analysis of Flight Image Sequences , 1994, ECCV.

[16]  Ian D. Reid,et al.  Recursive Affine Structure and Motion from Image Sequences , 1994, ECCV.

[17]  Richard Szeliski,et al.  Recovering 3D Shape and Motion from Image Streams Using Nonlinear Least Squares , 1994, J. Vis. Commun. Image Represent..

[18]  Thierry Viéville,et al.  Canonic Representations for the Geometries of Multiple Projective Views , 1994, ECCV.

[19]  Pietro Perona,et al.  Motion Estimation on the Essential Manifold , 1994, ECCV.

[20]  David W. Murray,et al.  Active Camera Calibration for a Head-Eye Platform Using the Variable State-Dimension Filter , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  David W. Murray,et al.  Dynamic Updating of Planar Structure and Motion: The Case of Constant Motion , 1996, Comput. Vis. Image Underst..

[22]  Takeo Kanade,et al.  A Paraperspective Factorization Method for Shape and Motion Recovery , 1994, IEEE Trans. Pattern Anal. Mach. Intell..