A novel depth spatial-temporal consistency enhancement algorithm for high compression performance

摘要：

In free viewpoint video system based on multiview video plus depth, inconsistency with depth video need to be eliminated to ensure high-quality virtual view generation and compression performance. The preprocessing method proposed can compensate both spatial and temporal depth information inaccuracy by using Bayesian probability model and Rival penalized competitive learning in Self-Organizing Maps. Firstly, each gray value in depth video is assigned to specific class after clustering. Then gradient filter is utilized in smoothing. Experiments show that the proposed algorithm reduced the bit rate ranging 7.97％-46.83％ while ensuring quality of generated virtual viewpoint.

关键词： Depth video preprocessing depth spatial-temporal consistency enhancement Bayesian Probability Model

作者: Ruiqing Zhang Zongju Peng Mei Yu Gangyi Jiang Wei Bi

作者单位: Faculty of Information Science and Engineering Ningbo University Ningbo, China Zhejiang Provincial K Faculty of Information Science and Engineering Ningbo University Ningbo, China

会议类型: 国际会议

会议名称: 2011 4th International Congress on Image and Signal Processing(第四届图像与信号处理国际学术会议 CISP 2011)

会议地点: 上海

会议语种:英文

页码: 34-37

在线出版日期: 2011-10-15（万方平台首次上网日期，不代表论文的发表时间）