Abstract

Model-based recognition and motion tracking depends upon the ability to solve for projection and model parameters that will best fit a 3-D model to matching 2-D image features. This paper extends current methods of parameter solving to handle objects with arbitrary curved surfaces and with any number of internal parameters representing articulations, variable dimensions, or surface deformations. Numerical

Citations

2224	Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography - Fischler, Bolles - 1981
779	Theory of edge detection - Marr, Hildreth - 1980
633	An algorithm for Least-Squares estimation of nonlinear parameters - Marquardt - 1963
431	Perceptual Organization and Visual Recognition - Lowe - 1985
364	Three-dimensional object recognition from single two-dimensional images - Lowe - 1987
237	Machine perception of three-dimensional solids - Roberts - 1965
232	Computational vision and regularization theory - Poggio, Torre, et al. - 1985
209	The representation, recognition, and locating of 3d objects - Faugeras, Hebert - 1986
202	Indirect perception - Rock - 1997
189	Amethod for the solution of certain nonlinear problems in least squares - Levenberg - 1944
181	Symbolic reasoning among 3d models and 2d images - Brooks - 1981
164	Object recognition using alignment - Huttenlocher, Ullman - 1987
162	Visual perception by computer - Binford - 1971
148	Perceptual organization and the representation of natural form - Pentland - 1986
146	M.: Pose estimation from corresponding point data - Haralick, Joo, et al. - 1989
106	Determination of the Attitude of 3-D objects from a single perspective view - Dhome, Richetin, et al. - 1989
91	recognizing and positioning curved 3D objects from image contours,” Trans - Kriegman, Ponce - 1990
84	An analytic solution for the perspective 4-point problem - Horaud, Conio, et al. - 1989
70	Organization of smooth image curves at multiple scales - Lowe - 1988
62	The viewpoint consistency constraint - Lowe - 1987
59	Determination of camera location from 2-D to 3-D line and point correspondences - Liu, Huang, et al. - 1990
41	Special Purpose Automatic Programming for 3D Model-Based Vision - Goad
29	Solving for the parameters of object models from image descriptions - Lowe - 1980
13	Determination of Camera Location and Orientation - Kumar - 1989
11	Tracking objects using image disparities - Bray - 1990
8	A 3-D sensor system for teaching robot paths and environments - Ishii, Sakane, et al. - 1987
6	Motion-based motion analysis: Motion from motion - Thompson, Mundy - 1988
6	Model based perspective inversion - Worrall, Baker, et al. - 1988
5	An Analysis of Lowe’s Model-based Vision System - McIvor - 1968
4	Verification of 3D parametric models in 2D image data - Goldberg, Lowe - 1987
2	Thomás Lozano-Pérez, “Model-based recognition and localization from sparse range or tactile data,” Int - Grimson - 1984