Spatiotemporal saliency detection based on superpixel-level trajectory

作者：

Highlights：

• A superpixel-level trajectory based spatiotemporal saliency model is proposed to effectively improve the saliency detection performance on challenging videos.

• Two trajectory descriptors, i.e. accumulated motion histogram and trajectory velocity entropy, are exploited to handle motion variability of different videos.

• A novel pipeline, which systematically measures trajectory distinctiveness, trajectory-level, superpixel-level and pixel-level temporal saliency in turn, is proposed to effectively enhance the coherence of temporal saliency through the whole video.

• A quality-guided fusion method is proposed to reasonably integrate temporal saliency map with spatial saliency map to generate spatiotemporal saliency map.

摘要

•A superpixel-level trajectory based spatiotemporal saliency model is proposed to effectively improve the saliency detection performance on challenging videos.•Two trajectory descriptors, i.e. accumulated motion histogram and trajectory velocity entropy, are exploited to handle motion variability of different videos.•A novel pipeline, which systematically measures trajectory distinctiveness, trajectory-level, superpixel-level and pixel-level temporal saliency in turn, is proposed to effectively enhance the coherence of temporal saliency through the whole video.•A quality-guided fusion method is proposed to reasonably integrate temporal saliency map with spatial saliency map to generate spatiotemporal saliency map.

论文关键词：Spatiotemporal saliency detection,Trajectory,Superpixel,Temporal saliency,Spatial saliency

论文评审过程：Available online 22 May 2015, Version of Record 18 November 2015.

论文官网地址：https://doi.org/10.1016/j.image.2015.04.014