Projective alignment with regions

We consider a recent approach to recognition that uses regions to determine the pose of objects while allowing for partial occlusion of the regions. We further analyze properties of the method for planar objects undergoing projective transformations. We prove that three visible regions are sufficient to determine the transformation uniquely, and that for a large class of objects two regions are insufficient. However, we show that when several regions are available, the pose of the object can generally be recovered even when all but two regions are significantly occluded. Our analysis is based on investigating the flow patterns of points under projective transformations in the presence of fixed points.

[1]  R. Stephenson.  A and V , 1962, The British journal of ophthalmology.

[2]  Ronen Basri,et al.  3-D to 2-D recognition with regions , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[3]  Luc Van Gool,et al.  A stratified approach to metric self-calibration , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[4]  Louis Brand,et al.  Differential and Difference Equations , 1968 .

[5]  David A. Forsyth,et al.  Invariant Descriptors for 3D Object Recognition and Pose , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Radu Horaud,et al.  New Methods for Matching 3-D Objects with Single Perspective Views , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  A. Verri,et al.  Mathematical properties of the two-dimensional motion field: from singular points to motion parameters , 1989 .

[8]  H. Coxeter,et al.  The Real Projective Plane , 1992 .

[9]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[10]  Audra E. Kosh,et al.  Linear Algebra and its Applications , 1992 .

[11]  K. Kanatani.  3D recovery of polyhedra by rectangularity heuristics , 1989, International Workshop on Industrial Applications of Machine Intelligence and Vision,.

[12]  Stefan Carlsson.  Information In The Geometric Structure Of Retinal Flow Fields , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[13]  Andrew Zisserman,et al.  Geometric Grouping of Repeated Elements within Images , 1999, Shape, Contour and Grouping in Computer Vision.

[14]  Raimund Seidel,et al.  Linear programming and convex hulls made easy , 1990, SCG '90.

[15]  D. Whittaker,et al.  A Course in Functional Analysis , 1991, The Mathematical Gazette.

[16]  Kenichi Kanatani,et al.  Geometric computation for machine vision , 1993 .

[17]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.