A. Zisserman, D. Liebowitz, and M. Armstrong. Resolving ambiguities in auto-calibration. Philosophical Transactions: Mathematical, Physical and Engineering Sciences (A), 356(1740):1193 -- 1211, May 1998. 28  Home/Search   Document Not in Database   Summary   Related Articles   Check

.... a tremendous amount of work [Faugeras et al. 1992, Hartley et al. 1992, Luong and Vieville, 1996, Triggs, 1997, Pollefeys et al. 1998 ] and effective methods to derive the epipolar geometry and the trifocal tensor from point correspondences have been devised [Zhang et al. 1995, Fitzgibbon and Zisserman, 1998] . However, most of these methods assume that it is possible to run an interest operator such as a corner detector [Pollefeys et al. 1998, Fitzgibbon and Zisserman, 1998] to extract from one of the images a sufficiently large number of points that can then be reliably matched in the other images. ....

.... the epipolar geometry and the trifocal tensor from point correspondences have been devised [Zhang et al. 1995, Fitzgibbon and Zisserman, 1998] However, most of these methods assume that it is possible to run an interest operator such as a corner detector [Pollefeys et al. 1998, Fitzgibbon and Zisserman, 1998] to extract from one of the images a sufficiently large number of points that can then be reliably matched in the other images. However, when using images such as the ones shown in Figure 1, we cannot depend on such interest points because faces exhibit too little texture. We must expect that ....

[Article contains additional citation context not shown here]

A. Zisserman, D. Liebowitz, and M. Armstrong. Resolving ambiguities in auto-calibration. Philosophical Transactions: Mathematical, Physical and Engineering Sciences (A), 356(1740):1193 -- 1211, May 1998. 28

.... tremendous amount of work [ Faugeras et al. 1992, Hartley et al. 1992, Luong and Vieville, 1996, Triggs, 1997, Pollefeys et al. 1998 ] and e#ective methods to derive the epipolar geometry and the trifocal tensor from point correspondences have been devised [ Zhang et al. 1995, Fitzgibbon and Zisserman, 1998 ] However, most of these methods assume that it is possible to run an interest operator such as a corner detector [ Pollefeys et al. 1998, Fitzgibbon and Zisserman, 1998 ] to extract from one of the images a su#ciently large number of points that can then be reliably matched in the other ....

.... epipolar geometry and the trifocal tensor from point correspondences have been devised [ Zhang et al. 1995, Fitzgibbon and Zisserman, 1998 ] However, most of these methods assume that it is possible to run an interest operator such as a corner detector [ Pollefeys et al. 1998, Fitzgibbon and Zisserman, 1998 ] to extract from one of the images a su#ciently large number of points that can then be reliably matched in the other images. However, when using images such as the ones shown in Figure 1, we cannot depend on such interest points because faces exhibit too little texture. We must expect that ....

[Article contains additional citation context not shown here]

A. Zisserman, D. Liebowitz, and M. Armstrong. Resolving ambiguities in auto-calibration. Philosophical Transactions: Mathematical, Physical and Engineering Sciences (A), 356(1740):1193 -- 1211, May 1998. 29

....precision and a high probability of error. Furthermore, typical sequences of moving faces often fail to exhibit rotational motion about two truly independent axes. As a result, the corresponding camera geometries are close to being degenerate for these methods, thereby compounding the problem [12, 16]. To overcome this difficulty, we have developed an approach based on bundle adjustment that takes advantage of our rough knowledge of the face s shape, in the form of a generic face model, to introduce regularization constraints. We will show that this allows us to robustly estimate the relative ....

.... can recover both intrinsic parameters and camera motion [1] The same holds true for recent auto calibration techniques but, as discussed in the introduction, typical video sequences of head images are close to exhibiting degenerate motions as far as these techniques are concerned [12, 16]. There again, extremely precise matches would be required. In practice, however, face images exhibit little texture and we must be prepared to deal with the potentially poor quality of the point matches. Therefore, we have chosen to roughly estimate the intrinsic parameters and to concentrate on ....

A. Zisserman, D. Liebowitz, and M. Armstrong. Resolving ambiguities in auto-calibration. Philosophical Transactions: Mathematical, Physical and Engineering Sciences (A), 356(1740):1193 -- 1211, May 1998. 8

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC