Mobile devices are increasingly powerful in multimedia transmitting and browsing. However, the small screen and different aspect ratios of mobile devices lower visual quality while watching images or videos. Video ret...Mobile devices are increasingly powerful in multimedia transmitting and browsing. However, the small screen and different aspect ratios of mobile devices lower visual quality while watching images or videos. Video retargeting is aim at fitting an existing video into arbitrary size and aspect ratio. Previous content-aware retargeting methods are mostly high computational cost, which limits their applications on the portable devices with low computation ability. In this paper, a new crop-and-scale approach is presented to adapt video to better suit the target display. We automatically find the optimal parameters of cropping window using the dynamic programming method,, and then scale it to fit the target display. The cropping window can smoothly shift during a shot to follow the movement＇of important objects. The retargeting results using our approach introduce no deformation and jitter effects over the whole video. Experimental results show the success of our approach on adapting a variety of source videos to small display sizes.展开更多
基金supported by the the Science and Technology Commission of Shanghai Municipality(Grant No.11ZR1413000)the Innovation Program for Graduate Students of Shanghai University(Grant No.SHUCX112125)the Key Laboratory for Advanced Displays and System Appliction(Shanghai University),Ministry of Education,China(Grant No.P201004)
文摘Mobile devices are increasingly powerful in multimedia transmitting and browsing. However, the small screen and different aspect ratios of mobile devices lower visual quality while watching images or videos. Video retargeting is aim at fitting an existing video into arbitrary size and aspect ratio. Previous content-aware retargeting methods are mostly high computational cost, which limits their applications on the portable devices with low computation ability. In this paper, a new crop-and-scale approach is presented to adapt video to better suit the target display. We automatically find the optimal parameters of cropping window using the dynamic programming method,, and then scale it to fit the target display. The cropping window can smoothly shift during a shot to follow the movement＇of important objects. The retargeting results using our approach introduce no deformation and jitter effects over the whole video. Experimental results show the success of our approach on adapting a variety of source videos to small display sizes.
