Implicit representation and scene reconstruction from probability density functions

A technique is presented for representing linear features as probability density functions in two or three dimensions. Three chief advantages of this approach are (1) a unified representation and algebra for manipulating points, lines, and planes, (2) seamless incorporation of uncertainty information, and (3) a very simple recursive solution for maximum likelihood shape estimation. Applications to uncalibrated affine scene reconstruction are presented, with results on images of an outdoor environment.

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

[2]  Long Quan.  Uncalibrated 1D projective camera and 3D affine reconstruction of lines , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[3]  Olivier D. Faugeras,et al.  Computing three dimensional project invariants from a pair of images using the Grassmann-Cayley algebra , 1998, Image Vis. Comput..

[4]  David W. Murray,et al.  A unifying framework for structure and motion recovery from image sequences , 1995, Proceedings of IEEE International Conference on Computer Vision.

[5]  Takeo Kanade,et al.  A unified factorization algorithm for points, line segments and planes with uncertainty models , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[6]  S. Ullman,et al.  The interpretation of visual motion , 1977 .

[7]  O. Faugeras.  Stratification of three-dimensional vision: projective, affine, and metric representations , 1995 .

[8]  Steven M. Seitz,et al.  Complete scene structure from four point correspondences , 1995, Proceedings of IEEE International Conference on Computer Vision.