Proceedings: 1993 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, June 15-18, 1993, New York City, New York |
From inside the book
Results 1-3 of 82
Page 228
... scene to its corresponding geometric shape in these image spaces . First , we consider scenes of five or more simple point features : P1 , P2 , P3 , P4 , Pj . Then we can show that the set of all affine coordinates that such a model can ...
... scene to its corresponding geometric shape in these image spaces . First , we consider scenes of five or more simple point features : P1 , P2 , P3 , P4 , Pj . Then we can show that the set of all affine coordinates that such a model can ...
Page 229
... scene can produce an image which is described by the affine invariant parameters : a4 4 , am + 1 B4 ' B5 ' " Bm + 1 ... scene's manifold in this space . First some notation . We can describe a " with a parameterized equation : a * = a + ...
... scene can produce an image which is described by the affine invariant parameters : a4 4 , am + 1 B4 ' B5 ' " Bm + 1 ... scene's manifold in this space . First some notation . We can describe a " with a parameterized equation : a * = a + ...
Page 586
... scene point . The Fresnel coefficients are determined by the material prop- erties of the scene point as well as the angle of incidence . Neither of these factors are known . To constrain the problem , [ Wolff and Boult , 91 ] use all ...
... scene point . The Fresnel coefficients are determined by the material prop- erties of the scene point as well as the angle of incidence . Neither of these factors are known . To constrain the problem , [ Wolff and Boult , 91 ] use all ...
Contents
Detecting Activities | 2 |
ModelBased Recognition | 12 |
Reconstruction of HOT Curves from Image Sequences | 20 |
Copyright | |
73 other sections not shown
Common terms and phrases
affine affine transformation algorithm analysis angle applied approach axis bitangent calibration camera color component Computer Vision constraint contour corresponding curvature curve defined denote depth derived described detection determine diffusion direction discontinuities disparity distance edge epipolar equation error essential matrix estimation filter frame function Gaussian geometric geometric hashing given global hash IEEE IEEE Trans image plane image points image sequence implementation iterations Kalman filter label linear matching matrix mean curvature measure method minimization motion noise normal object obtained occlusion optical flow orientation pair parallel parameters part-lines particles Pattern pixel position problem Proc projection range recognition reconstruction region robot rotation scale scale space scene segmentation sensor shape shown in Figure shows solution space stereo stereopsis structure superquadrics surface surface normal surface reconstruction tangent technique tion transformation translation values vector velocity vergence visual hull