Semi-supervised Video Object Segmentation Using Multiple Random Walkers

Won-Dong Jang and Chang-Su Kim

Abstract

A semi-supervised video object segmentation algorithm using multiple random walkers (MRW) is proposed in this work. We develop an initial probability estimation scheme that minimizes an objective function to roughly separate the foreground from the background. Then, we simulate MRW by employing the foreground and background agents. During the MRW process, we update restart distributions using a hybrid of inference restart rule and interactive restart rule. By performing these processes from the second to the last frames, we obtain a segment track of the target object. Furthermore, we optionally refine the segment track by performing Markov random field optimization. Experimental results demonstrate that the proposed algorithm significantly outperforms the state-of-the-art conventional algorithms on the SegTrack v2 dataset.

Session

Posters 1

Files

PDF iconExtended Abstract (PDF, 559K)
PDF iconPaper (PDF, 1M)
ZIP iconSupplemental Materials (ZIP, 28M)

DOI

10.5244/C.30.57
https://dx.doi.org/10.5244/C.30.57

Citation

Won-Dong Jang and Chang-Su Kim. Semi-supervised Video Object Segmentation Using Multiple Random Walkers. In Richard C. Wilson, Edwin R. Hancock and William A. P. Smith, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 57.1-57.13. BMVA Press, September 2016.

Bibtex

        @inproceedings{BMVC2016_57,
        	title={Semi-supervised Video Object Segmentation Using Multiple Random Walkers},
        	author={Won-Dong Jang and Chang-Su Kim},
        	year={2016},
        	month={September},
        	pages={57.1-57.13},
        	articleno={57},
        	numpages={13},
        	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
        	publisher={BMVA Press},
        	editor={Richard C. Wilson, Edwin R. Hancock and William A. P. Smith},
        	doi={10.5244/C.30.57},
        	isbn={1-901725-59-6},
        	url={https://dx.doi.org/10.5244/C.30.57}
        }