A Variational Framework for Image Segmentation Combining Motion Estimation and Shape Regularization
Abstract
Based on a geometric interpretation of the optic flow constraint equation, we propose a conditional probability on the spatio-temporal image gradient. We consistently derive a variational approach for the segmentation of the image domain into regions of homogeneous motion. The proposed energy functional extends the Mumford-Shah functional from gray value segmentation to motion segmentation. It depends on the spatio-temporal image gradient calculated from only two consecutive images of an image sequence. Moreover, it depends on motion vectors for a set of regions and a boundary separating these regions. In contrast to most alternative approaches, the problems of motion estimation and motion segmentation are jointly solved by minimizing a single functional. Numerical evaluation with both explicit and implicit (level set based) representations of the boundary shows the strengths and limitations of our approach.
Cite
Text
Cremers. "A Variational Framework for Image Segmentation Combining Motion Estimation and Shape Regularization." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003. doi:10.1109/CVPR.2003.1211337Markdown
[Cremers. "A Variational Framework for Image Segmentation Combining Motion Estimation and Shape Regularization." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003.](https://mlanthology.org/cvpr/2003/cremers2003cvpr-variational/) doi:10.1109/CVPR.2003.1211337BibTeX
@inproceedings{cremers2003cvpr-variational,
title = {{A Variational Framework for Image Segmentation Combining Motion Estimation and Shape Regularization}},
author = {Cremers, Daniel},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2003},
pages = {53-58},
doi = {10.1109/CVPR.2003.1211337},
url = {https://mlanthology.org/cvpr/2003/cremers2003cvpr-variational/}
}