Output details

Object-based video coding with dynamic quality control

This paper describes a novel priority-based multiple-video objects coding system integrating a user visual attention model, and a dynamic rate control mechanism. The importance of individual objects is defined automatically and the coding parameters are adaptively adjusted to maximise the perceptual quality. Experimental results confirm consistency with the observation of the human visual system. The proposed system offers key techniques to ensure quality of service for real-time content-based video coding and streaming systems. The research has been exploited in video surveillance system applications. Contact: Dr Xiaodong Cai, Guilin University, China, Email: caixiaodong@guet.edu.cn.