A Model of Saliency-Based Visual Attention for Rapid Scene Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Seam carving for content-aware image resizing
ACM SIGGRAPH 2007 papers
Improved seam carving for video retargeting
ACM SIGGRAPH 2008 papers
Multi-operator media retargeting
ACM SIGGRAPH 2009 papers
A system for retargeting of streaming video
ACM SIGGRAPH Asia 2009 papers
FSCAV: fast seam carving for size adaptation of videos
MM '09 Proceedings of the 17th ACM international conference on Multimedia
A high-speed multi-GPU implementation of bottom-up attention using CUDA
ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
Fast JND-based video carving with GPU acceleration for real-time video retargeting
IEEE Transactions on Circuits and Systems for Video Technology
Video retargeting with multi-scale trajectory optimization
Proceedings of the international conference on Multimedia information retrieval
Motion-based video retargeting with optimized crop-and-warp
ACM SIGGRAPH 2010 papers
A comparative study of image retargeting
ACM SIGGRAPH Asia 2010 papers
Algorithms for video retargeting
Multimedia Tools and Applications
Scalable and coherent video resizing with per-frame optimization
ACM SIGGRAPH 2011 papers
SeamCrop: changing the size and aspect ratio of videos
Proceedings of the 4th Workshop on Mobile Video
Context-Aware Saliency Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
| Hi-index | 0.00 |
In this paper, we present a fast parallel algorithm for the retargeting of videos. It combines seam carving and cropping and is aimed for real-time adaptation of video streams. The basic idea is to first find an optimal cropping path over the whole sequence with the target size. Then, the borders are slightly extended to be reduced again by seam carving on a frame-by-frame basis. This allows the algorithm to get more important content into the cropping window as it is also able to remove pixels from within the window. In contrast to the previous SeamCrop algorithm, the presented technique is optimized for parallel processes and a CUDA GPU implementation. In comparison, the computation time of our GPU algorithm is 10.5 times faster (on a 960 x 540 video with a retarget factor of 25%) than the already efficient CPU implementation.