Video Retargeting Based on Adaptive Spatiotemporal Saliency Mapping

This paper proposes a video retargeting method based on spatiotemporal saliency model for intelligent sensing of surveillance devices. Global histograms and regional histograms of the video are first calculated in both spatial domain and temporal domain, respectively, and then the spatiotemporal saliency model is built by evaluating the contrasts between the global histograms and each regional histogram. Experimental results on a variety of videos demonstrate that the proposed approach is simple and effective, and can preserve important objects well and achieve a better retargeting performance.