Video Retargeting for Intelligent Sensing of Surveillance Devices

摘要

This paper proposes a video retargeting method for intelligent sensing of surveillence devices. The spatiotemporal saliency model is firstly built by evaluating the contrasts between the global histograms and each regional histogram. Based on the spatiotemporal saliency map, a salient object detection method is used to locate salient object regions in the video. Then the size of cropping window is evaluated based on the moving objects. Finally cropping and scaling operations are performed on the basis of salient object regions to generate the retargeted video.