Matching Perspective Views of Parallel Plane Structures

Within an invariance framework, the recognition of plane objects under general viewpoints and perspective projection calls for the extraction of two-dimensional projective invariants. If the possible poses of the object are constrained with respect to the camera, however, simpler groups than the projective transformations become relevant, and consequently, simpler invariants exist. Several such special types of pose constraints are discussed — all amount to the object plane remaining parallel to its original orientation — and the corresponding groups are outlined. For each group a number of invariants are derived to illustrate the gain in simplicity.

[1]  Hanspeter A. Mallot,et al.  Adapting Computer Vision Systems to the Visual Environment: Topographic Mapping , 1990, ECCV.

[2]  Erik L. Dagless,et al.  Road Following Algorithm Using A Panned Plan-View Transformation , 1990, ECCV.

[3]  Luc Van Gool,et al.  Recognition and semi-differential invariants , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[4]  P. M. Payton,et al.  Projective invariants for curves in two and three dimensions , 1992 .

[5]  L. Gool,et al.  Semi-differential invariants , 1992 .

[6]  Tieniu Tan,et al.  3D structure and motion estimation from 2D image sequences , 1993, Image Vis. Comput..

[7]  Robert T. Collins,et al.  Matching perspective views of coplanar structures using projective unwarping and similarity matching , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[8]  C. Coelho,et al.  Extraction of vanishing points from images of indoor and outdoor scenes , 1993, Image Vis. Comput..

[9]  Josef Kittler,et al.  Vanishing point detection , 1993, Image Vis. Comput..

[10]  J Wagemans,et al.  Invariance from the Euclidean Geometer's Perspective , 1994, Perception.

[11]  Luc Van Gool,et al.  The Characterization and Detection of Skewed Symmetry , 1995, Comput. Vis. Image Underst..