Adaptive Combination of Local Motion, Appearance, and Shape for Video Segmentation

Woo-Sung Shim, Se-hoon Kim, Soochahn Lee

Abstract

In this paper, we propose an accurate and robust video segmentation method. The main contributions are threefold: (1) multiple cues (appearance and shape) are explicitly used and adaptively combined to determine segment probability; (2) motion is implicitly used to compute the shape cue; and (3) the segment labeling is improved by utilizing geodesic graph cuts. Experimental results show the effectiveness of the proposed method.
BibTeX
@inproceedings{shim2017adaptive,
  author = {Woo-Sung Shim and Se-hoon Kim and Soochahn Lee},
  title = {{Adaptive Combination of Local Motion, Appearance, and Shape for Video Segmentation}},
  booktitle = {Visual Information Processing and Communication},
  year = {2017},
  doi = {10.2352/issn.2470-1173.2017.2.vipc-a},
}

Loading related content...

Figure