Establishing Motion Correspondence
Abstract
A proximal uniformity constraint is proposed to solve the correspondence problem. According to this constraint, most objects in the real world follow smooth paths and cover a small distance in a small time. An efficient, noniterative polynomial time approximation algorithm which minimizes the proximal uniformity cost function and establishes correspondence over n frames is proposed. Any method using smoothness of motion alone cannot operate correctly without assuming correct initial correspondence, the correspondence in the first two frames. Therefore, the authors propose the use of gradient-based optical flow for establishing the initial correspondence. This way the proposed approach combines the qualities of the gradient- and token-based methods for motion correspondence. The algorithm is then extended to take care of restricted cases of occlusion. Experimental results for real and synthetic sequences are presented.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>
Cite
Text
Rangarajan and Shah. "Establishing Motion Correspondence." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1991. doi:10.1109/CVPR.1991.139669Markdown
[Rangarajan and Shah. "Establishing Motion Correspondence." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1991.](https://mlanthology.org/cvpr/1991/rangarajan1991cvpr-establishing/) doi:10.1109/CVPR.1991.139669BibTeX
@inproceedings{rangarajan1991cvpr-establishing,
title = {{Establishing Motion Correspondence}},
author = {Rangarajan, Krishnan and Shah, Mubarak},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {1991},
pages = {103-108},
doi = {10.1109/CVPR.1991.139669},
url = {https://mlanthology.org/cvpr/1991/rangarajan1991cvpr-establishing/}
}