Motion Estimation in Image Sequences Using the Deformation of Apparent Contours
(1998) International Conference on Computer Vision , 1998 In Proceedings of IEEE 6th International Conference on Computer Vision p.939942 Abstract
 The problem of determining the camera motion from apparent contours or silhouettes of curved threedimensional surfaces is considered. In a sequence of images is shown how to use the generalized epipolar constraint on apparent contours. One such constraint is obtained for each epipolar tangency point in each image pair. Thus in theory the motion can be calculated from the deformation of a single contour. A robust algorithm for computing the motion is presented based on the maximum likelihood estimate. It is shown how to generate initial estimates on the camera motion using only the tracked contours. It is also shown how to improve this estimate by maximizing the likelihood function. The algorithm has been tested on real image sequences.... (More)
 The problem of determining the camera motion from apparent contours or silhouettes of curved threedimensional surfaces is considered. In a sequence of images is shown how to use the generalized epipolar constraint on apparent contours. One such constraint is obtained for each epipolar tangency point in each image pair. Thus in theory the motion can be calculated from the deformation of a single contour. A robust algorithm for computing the motion is presented based on the maximum likelihood estimate. It is shown how to generate initial estimates on the camera motion using only the tracked contours. It is also shown how to improve this estimate by maximizing the likelihood function. The algorithm has been tested on real image sequences. The result is compared to that of using only point features. The statistical evaluation shows that the technique gives accurate and stable results (Less)
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/record/787347
 author
 Kahl, Fredrik ^{LU} and Åström, Karl ^{LU}
 organization
 publishing date
 1998
 type
 Chapter in Book/Report/Conference proceeding
 publication status
 published
 subject
 keywords
 computational geometry, image sequences, maximum likelihood estimation, motion estimation, apparent contours deformation, camera motion, silhouettes, eneralized epipolar constraint, epipolar tangency point, image pair, robust algorithm, maximum likelihood estimate, real image sequences
 in
 Proceedings of IEEE 6th International Conference on Computer Vision
 pages
 939  942
 publisher
 Narosa Publishing House
 conference name
 International Conference on Computer Vision , 1998
 external identifiers

 scopus:0032316966
 ISBN
 81 7319 221 9
 DOI
 language
 English
 LU publication?
 yes
 id
 106bc7a969e14e83bf5531e7feb13991 (old id 787347)
 date added to LUP
 20080916 13:49:23
 date last changed
 20180529 09:34:24
@inproceedings{106bc7a969e14e83bf5531e7feb13991, abstract = {The problem of determining the camera motion from apparent contours or silhouettes of curved threedimensional surfaces is considered. In a sequence of images is shown how to use the generalized epipolar constraint on apparent contours. One such constraint is obtained for each epipolar tangency point in each image pair. Thus in theory the motion can be calculated from the deformation of a single contour. A robust algorithm for computing the motion is presented based on the maximum likelihood estimate. It is shown how to generate initial estimates on the camera motion using only the tracked contours. It is also shown how to improve this estimate by maximizing the likelihood function. The algorithm has been tested on real image sequences. The result is compared to that of using only point features. The statistical evaluation shows that the technique gives accurate and stable results}, author = {Kahl, Fredrik and Åström, Karl}, booktitle = {Proceedings of IEEE 6th International Conference on Computer Vision}, isbn = {81 7319 221 9}, keyword = {computational geometry,image sequences,maximum likelihood estimation,motion estimation,apparent contours deformation,camera motion,silhouettes,eneralized epipolar constraint,epipolar tangency point,image pair,robust algorithm,maximum likelihood estimate,real image sequences}, language = {eng}, pages = {939942}, publisher = {Narosa Publishing House}, title = {Motion Estimation in Image Sequences Using the Deformation of Apparent Contours}, url = {http://dx.doi.org/}, year = {1998}, }