Interactive Video Segmentation via Efficient Filtering

By Nicole Brosch, Asmaa Hosni, Christoph Rhemann, and Margrit Gelautz

Abstract

In [2], we present a fast, interactive segmentation and matting framework for videos. It is based on recent work [5] that recovers high-quality segmentations by smoothing cost maps. Our main contribution is to extend [5] to the temporal domain, as [5] was intended for single images and does not achieve temporally coherent results for videos. Our results are temporally coherent. The binary segmentation can be further refined in a fast, tempo- rally coherent alpha matting step.

Reference

N. Brosch, A. Hosni, C. Rhemann, M. Gelautz: "Interactive Video Segmentation via Efficient Filtering"; Poster: International Computer Vision Summer School 2012, Sicily, Italy; 07-15-2012 - 07-21-2012.

Additional Information

[2]: Spatio-temporally Coherent Interactive Video Object Segmentation via Efficient Filtering

BibTeX

@unpublished{TUW-208899,     author = {Brosch, Nicole and Hosni, Asmaa and Rhemann, Christoph and Gelautz, Margrit},     title = {Interactive Video Segmentation via Efficient Filtering},     year = {2012},     keywords = {interactive video segmentation},     note = {poster presentation: International Computer Vision Summer School 2012, Sicily, Italy; 2012-07-15 -- 2012-07-21} } Click into the text area and press Ctrl+A/Ctrl+C or ⌘+A/⌘+C to copy the BibTeX into your clipboard… or download the BibTeX.