Paper
29 August 2016 Spatiotemporal saliency detection using border connectivity
Tongbao Wu, Zhi Liu, Junhao Li
Author Affiliations +
Proceedings Volume 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016); 1003344 (2016) https://doi.org/10.1117/12.2244867
Event: Eighth International Conference on Digital Image Processing (ICDIP 2016), 2016, Chengu, China
Abstract
This paper proposes a border connectivity-based spatiotemporal saliency model for videos with complicated motion and complex scenes. Based on the superpixel segmentation results of video frames, feature extraction is performed to obtain the three features, including motion orientation histogram, motion amplitude histogram and color histogram. Then the border connectivity is exploited to evaluate the importance of three features for distance fusion. Finally the background weighted contrast and saliency optimization are utilized to generate superpixel-level spatiotemporal saliency maps. Experimental results on a public benchmark dataset demonstrate that the proposed model outperforms the state-of-the- art saliency models on saliency detection performance.
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Tongbao Wu, Zhi Liu, and Junhao Li " Spatiotemporal saliency detection using border connectivity", Proc. SPIE 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016), 1003344 (29 August 2016); https://doi.org/10.1117/12.2244867
Lens.org Logo
CITATIONS
Cited by 2 scholarly publications and 1 patent.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Motion models

Video

Motion measurement

Performance modeling

Visual process modeling

Data modeling

Feature extraction

RELATED CONTENT

Small object segmentation in medical image
Proceedings of SPIE (August 01 2022)
Video co-saliency detection
Proceedings of SPIE (August 29 2016)

Back to Top