A novel scheme of ROI detection and transcoding for mobile devices in high-definition videoconferencing
Yihua Lou, Ting Yao, Yongquan Chen, Wenjun Wu · 2013
The experience of watching real-time high definition videos on mobile devices is greatly limited due to the screen size, especially when people attend real-time videoconferencing meetings via their smart phones. This issue could be solved by a ROI (Region of Interest) based scalable video transcoding scheme that displays the ROIs with higher quality and other regions in the same video frame. However, currently most researches on ROI based video adaptation focus on VOD streaming applications rather than real-time videoconferencing. This paper presents a novel scheme of ROI detection and transcoding for mobile devices in video-conferencing system that uses a Kinect based approach to detect ROIs and a ROI-enabled transcoding scheme will be used to transcode the video streams by using a re-quantization approach. Experiments shows that with the ROI extraction algorithm and the ROI-enabled transcoding scheme, the bitrate of a video stream can be significantly reduced, while the perceived quality of the video is still good enough.