Interactive Media Systems, TU Vienna

Spatio-temporally Coherent Interactive Video Object Segmentation via Efficient Filtering

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

Abstract

In this paper we propose a fast, interactive object segmentation and matting framework for videos that allows users to extract objects from a video using only a few foreground scribbles. Our approach is based on recent work [12] that obtains high-quality image segmentations by smoothing the likelihood of a color model with a fast edge-preserving filter. The previous approach was originally intended for single static images and does not achieve temporally coherent segmentations for videos. Our main contribution is to extend the approach of [12] to the temporal domain. Our results are spatially and temporally coherent segmentations, in which the borders of the foreground object are aligned with spatio-temporal color edges in the video. The obtained binary segmentation can be further refined in a temporally coherent and equally efficient alpha matting step. Quantitative and qualitative evaluations show that our extension significantly reduces flickering in the video segmentations.

Reference

N. Brosch, A. Hosni, C. Rhemann, M. Gelautz: "Spatio-temporally Coherent Interactive Video Object Segmentation via Efficient Filtering"; Poster: Joint 34th DAGM and 36th OAGM Symposium, Graz; 08-28-2012 - 08-31-2012; in: "Proc. of the Joint 34th DAGM and 36th OAGM Symposium", Springer, LNCS 7476 (2012), ISSN: 0302-9743; 418 - 427.

Additional Information

  • Video Segmentation and Matting Result:

BibTeX

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.