Computer Graphics Laboratory ETH Zurich


Efficient Salient Foreground Detection for Images and Video using Fiedler Vectors

F. Perazzi, O. Sorkine-Hornung, A. Sorkine-Hornung

Proceedings of Eurographics (Zurich,Switzerland,, May 4-8, 2015), Computer Graphics Forum, vol. 34, no. 2, pp. 21-29
[Abstract] [BibTeX] [PDF]


Automatic detection of salient image regions is a useful tool with applications in intelligent camera control, virtual cinematography, video summarization and editing, evaluation of viewer preferences, and many others. This paper presents an effective method for detecting potentially salient foreground regions. Salient regions are identified by eigenvalue analysis of a graph Laplacian that is defined over the color similarity of image superpixels, under the assumption that the majority of pixels on the image boundary show non-salient background. In contrast to previous methods based on graph-cuts or graph partitioning, our method provides continuously-valued saliency estimates with complementary properties to recently proposed color contrast-based approaches. Moreover, exploiting discriminative properties of the Fiedler vector, we devise an SVM-based classifier that allows us to determine whether an image contains any salient objects at all, a problem that has been largely neglected in previous works. We also describe how the per-frame saliency detection can be extended to improve its spatiotemporal coherence when computed on video sequences. Extensive evaluation on several datasets demonstrates and validates the state-of-the-art performance of the proposed method.

@inproceedings {wiced.20151074,
booktitle = {Eurographics Workshop on Intelligent Cinematography and Editing},
editor = {W. Bares and M. Christie and R. Ronfard},
title = {{Efficient Salient Foreground Detection for Images and Video using Fiedler Vectors}},
author = {Perazzi, Federico and Sorkine-Hornung, Olga and Sorkine-Hornung, Alexander},
year = {2015},
publisher = {The Eurographics Association},
DOI = {10.2312/wiced.20151074}
[Download BibTeX]



Download Paper