Spatiotemporal saliency detection using border connectivity

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.