摘要: We discuss briefly a number of areas where epipolar geometry is currently central in carrying out visual tasks. In contrast we demonstrate configurations for which 3D projective invariants can be computed from perspective stereo pairs, but (and full structure) cannot. catalogue these generally involve isotropies under the group, and investigate connection with camera calibration. Examples are given recovered real images. also indicate other strong reliance on should avoided, particular image transfer.
springer.com
sci-hub.st 参考文章(26)
Roger Mohr, Projective geometry and computer vision Handbook of pattern recognition & computer vision. pp. 369- 393 ,(1993)
Q. -T. Luong, T. Viéville, Canonic representations for the geometries of multiple projective views european conference on computer vision. pp. 589- 599 ,(1994) , 10.1007/3-540-57956-7_66
Olivier D. Faugeras, What can be seen in three dimensions with an uncalibrated stereo rig european conference on computer vision. pp. 563- 578 ,(1992) , 10.1007/3-540-55426-2_61
P H S Torr, D W Murray, Stochastic Motion Clustering european conference on computer vision. pp. 328- 337 ,(1994) , 10.1007/BFB0028365
Joseph L. Mundy, Andrew Zisserman, Geometric invariance in computer vision MIT Press. ,(1992)
Larry S. Shapiro, Andrew Zisserman, Michael Brady, Motion From Point Matches Using Affine Epipolar Geometry european conference on computer vision. pp. 73- 84 ,(1994) , 10.1007/BFB0028336
Stephen Maybank, M. R. Schroeder, T. S. Huang, Teuvo Kohonen, Theory of Reconstruction from Image Motion ,(1992)
H. C. Longuet-Higgins, A computer algorithm for reconstructing a scene from two projections Nature. ,vol. 293, pp. 61- 62 ,(1987) , 10.1038/293133A0
Amnon Shashua, Trilinearity in visual recognition by alignment european conference on computer vision. pp. 479- 484 ,(1994) , 10.1007/3-540-57956-7_53
O. D. Faugeras, Q. -T. Luong, S. J. Maybank, Camera self-calibration: Theory and experiments Computer Vision — ECCV'92. pp. 321- 334 ,(1992) , 10.1007/3-540-55426-2_37