Share Email Print

Proceedings Paper

Multi-feature based visual saliency detection in surveillance video
Author(s): Yubing Tong; Hubert Konik; Faouzi Alaya Cheikh; Fahad Fazal Elahi Guraya; Alain Tremeau
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The perception of video is different from that of image because of the motion information in video. Motion objects lead to the difference between two neighboring frames which is usually focused on. By far, most papers have contributed to image saliency but seldom to video saliency. Based on scene understanding, a new video saliency detection model with multi-features is proposed in this paper. First, background is extracted based on binary tree searching, then main features in the foreground is analyzed using a multi-scale perception model. The perception model integrates faces as a high level feature, as a supplement to other low-level features such as color, intensity and orientation. Motion saliency map is calculated using the statistic of the motion vector field. Finally, multi-feature conspicuities are merged with different weights. Compared with the gaze map from subjective experiments, the output of the multi-feature based video saliency detection model is close to gaze map.

Paper Details

Date Published: 13 July 2010
PDF: 9 pages
Proc. SPIE 7744, Visual Communications and Image Processing 2010, 774404 (13 July 2010); doi: 10.1117/12.863281
Show Author Affiliations
Yubing Tong, Lab. Hubert Curien, CNRS, Univ. Jean Monnet (France)
Univ. Lyon (France)
Hubert Konik, Lab. Hubert Curien, CNRS, Univ. Jean Monnet (France)
Univ. Lyon (France)
Faouzi Alaya Cheikh, Gjovik Univ. College (Norway)
Fahad Fazal Elahi Guraya, Gjovik Univ. College (Norway)
Alain Tremeau, Lab. Hubert Curien, CNRS, Univ. Jean Monnet (France)
Univ. Lyon (France)

Published in SPIE Proceedings Vol. 7744:
Visual Communications and Image Processing 2010
Pascal Frossard; Houqiang Li; Feng Wu; Bernd Girod; Shipeng Li; Guo Wei, Editor(s)

© SPIE. Terms of Use
Back to Top