ML Anthology

A Region-Based MRF Model for Unsupervised Segmentation of Moving Objects in Image Sequences

Yaakov Tsaig, Amir Averbuch
CVPR 2001 pp. I:889-896
doi:10.1109/CVPR.2001.990611 /cvpr/2001/tsaig2001cvpr-region/

Abstract

This paper addresses the problem of segmentation of moving objects in image sequences, which is of key importance in content-based applications. We transform the problem into a graph labeling problem over a region adjacency graph (RAG), by introducing a Markov random field (MRF) model based on spatio-temporal information. The initial partition is obtained by fast, color-based watershed segmentation. The motion of each region is estimated and validated in a hierarchical framework. A dynamic memory, based on object tracking, is incorporated into the segmentation process to maintain temporal coherence. The performance of the algorithm is evaluated on several real-world image sequences.

CVPR Semantic Scholar

Cite

Text

Tsaig and Averbuch. "A Region-Based MRF Model for Unsupervised Segmentation of Moving Objects in Image Sequences." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2001. doi:10.1109/CVPR.2001.990611

Markdown

[Tsaig and Averbuch. "A Region-Based MRF Model for Unsupervised Segmentation of Moving Objects in Image Sequences." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2001.](https://mlanthology.org/cvpr/2001/tsaig2001cvpr-region/) doi:10.1109/CVPR.2001.990611

BibTeX

@inproceedings{tsaig2001cvpr-region,
  title     = {{A Region-Based MRF Model for Unsupervised Segmentation of Moving Objects in Image Sequences}},
  author    = {Tsaig, Yaakov and Averbuch, Amir},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2001},
  pages     = {I:889-896},
  doi       = {10.1109/CVPR.2001.990611},
  url       = {https://mlanthology.org/cvpr/2001/tsaig2001cvpr-region/}
}