Multiple Hypothesis Video Segmentation from Superpixel Flows

Amelio Vázquez Reina, Shai Avidan, Hanspeter Pfister, Eric L. Miller

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.
BibTeX
@inproceedings{reina2010multiple,
  author = {Amelio Vázquez Reina and Shai Avidan and Hanspeter Pfister and Eric L. Miller},
  title = {{Multiple Hypothesis Video Segmentation from Superpixel Flows}},
  booktitle = {European Conference on Computer Vision},
  year = {2010},
  doi = {10.1007/978-3-642-15555-0\_20},
}

Loading related content...

Figure