Three-dimensional model matching from an unconstrained viewpoint
- 23 March 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4, 208-220
- https://doi.org/10.1109/robot.1987.1088004
Abstract
It is demonstrated that the affine viewing transformation is a reasonable approximation to perspective. A group of image vertices and edges, called the vertex-pair, which fully determines the affine transformation between a three-dimensional model and a two-dimensional image is defined. A clustering approach, which produces a set of consistent assignments between vertex-pairs in the model and in the image is described. A number of experimental results on outdoor images are presented.Keywords
This publication has 6 references indexed in Scilit:
- Object recognition using oriented model pointsComputer Vision, Graphics, and Image Processing, 1986
- The Curvature Primal SketchPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1986
- Three-dimensional object recognitionACM Computing Surveys, 1985
- Perceptual Organization and Visual RecognitionPublished by Springer Nature ,1985
- Symbolic reasoning among 3-D models and 2-D imagesArtificial Intelligence, 1981
- Fleshing Out Wire FramesIBM Journal of Research and Development, 1980