View-Class Representation and Matching of 3D Objects
Three-dimensional object recognition is difficult because an object looks different when viewed from different viewpoints. One solution to this problem is to represent the 3D object as a set of 2D models, one for each of a set of view classes. A view class is a set of viewpoints that all produce images with the same or similar features. View-class matching consists of determining the correspondence between the features extracted from an image of an unknown object and the features of a particular view class of a particular object model. View-class matching is used in object recognition, pose estimation, and inspection systems.
KeywordsLine Segment Line Drawing Vision Model View Class Template Model
Unable to display preview. Download preview PDF.
- 1.Buchanan, C. G., “Determining Surface Orientation from Specular Highlights”, M.S. thesis, Computer Science Department, University of Toronto, 1986.Google Scholar
- 2.Camps, O. I., L. G. Shapiro, and R. M. Haralick, “PREMIO: An Overview”, Proceedings of the IEEE Workshop on Automated CAD-Based Vision, June, 1991.Google Scholar
- 3.Chakravarty, I. and H. Freeman, “Characteristic Views as a Basis for Three-Dimensional Object Recognition”, Proceedings of SPIE 336 (Robot Vision), 1982, pp. 37-45.Google Scholar
- 5.Goad, C., “Special Purpose, Automatic Programming for 3D Model-Based Vision”, DARPA Image Understanding Workshop, 1983, pp. 94-104.Google Scholar
- 6.Hansen, C. and T. Henderson, “Toward the Automatic Generation of Recognition Strategies”, Proceedings of the 2nd International Conference on Computer Vision, 1988, pp. 275-279.Google Scholar
- 8.Henikoff, J. and L. G. Shapiro, “Interesting Patterns for Model-Based Vision”, Proceedings of the 3rd International Conference on Computer Vison, 1990, pp. 535-538.Google Scholar
- 12.Ponce, J. and D. Chelberg, “Finding the limbs and Cusps of Generalized Cylinders”, International Journal of Computer Vision, Vol. 3, 1987, pp. 195–210.Google Scholar
- 14.Yi, S., R. M. Haralick, and L. G. Shapiro, “Automatic Sensor and Light Source Positioning for Machine Vision”, Proceedings of the 10th International Conference on Pattern Recognition, June, 1990, pp. 55-59.Google Scholar