Multiple Hypothesis Video Segmentation from Superpixel Flows
Abstract
Multiple Hypothesis Video Segmentation (MHVS) is a method for the unsupervised photometric segmentation of video sequences. MHVS segments arbitrarily long video streams by considering only a few frames at a time, and handles the automatic creation, continuation and termination of labels with no user initialization or supervision. The process begins by generating several pre-segmentations per frame and enumerating multiple possible trajectories of pixel regions within a short time window. After assigning each trajectory a score, we let the trajectories compete with each other to segment the sequence. We determine the solution of this segmentation problem as the MAP labeling of a higher-order random field. This framework allows MHVS to achieve spatial and temporal long-range label consistency while operating in an on-line manner. We test MHVS on several videos of natural scenes with arbitrary camera and object motion.
Cite
Text
Reina et al. "Multiple Hypothesis Video Segmentation from Superpixel Flows." European Conference on Computer Vision, 2010. doi:10.1007/978-3-642-15555-0_20Markdown
[Reina et al. "Multiple Hypothesis Video Segmentation from Superpixel Flows." European Conference on Computer Vision, 2010.](https://mlanthology.org/eccv/2010/reina2010eccv-multiple/) doi:10.1007/978-3-642-15555-0_20BibTeX
@inproceedings{reina2010eccv-multiple,
title = {{Multiple Hypothesis Video Segmentation from Superpixel Flows}},
author = {Reina, Amelio Vázquez and Avidan, Shai and Pfister, Hanspeter and Miller, Eric L.},
booktitle = {European Conference on Computer Vision},
year = {2010},
pages = {268-281},
doi = {10.1007/978-3-642-15555-0_20},
url = {https://mlanthology.org/eccv/2010/reina2010eccv-multiple/}
}