摘要
随着视频监控系统的广泛应用,视频信息中的隐私保护日趋重要.提出一种能够有选择性地保护监控场所工作人员隐私信息的视频监控系统框架.它将固定的工作人员所在的区域作为隐私信息,并基于可逆水印的方式嵌入到背景修复后的视频流.在水印嵌入上,利用H.264/AVC编码的DCT系数量化后服从柯西分布这一特点,结合率失真优化分配水印数据,采用直方图平移算法实现了大容量的水印嵌入.对于授权用户,可以通过水印提取实现无损地恢复原始视频.实验结果表明,本文提出的方案能够在没有明显失真及低比特率增加的情况下,隐藏受保护的隐私信息,且对于授权用户可以通过水印提取实现无损恢复原始视频.
With the wide application of video surveillance system, the privacy protection of video information is gaining considerable concerns. In this paper, an improved privacy information protection framework is proposed. It discriminates fixed persons from those ordinary persons. The fixed persons are removed from surveillance video, and its information is embedded into in-painted video as watermark. The privacy information is embedded into surveillance video as reversible watermark, and only legal user with key can extract it. For watermark embedding, it exploits the fact that the quantized DCT coefficients of H. 264/AVC coded video follows Cauchy distribution. Based on a rate-distortion optimization scheme, histogram shifting algorithm is utilized to realize high-capacity watermark embedding. Experimental results show that the proposed reversible watermarking-based privacy information protection framework can hide the privacy information without significant distortion and bitrate increase. Moreover, the authorized users can lossless recover the original video by watermark extraction.
出处
《小型微型计算机系统》
CSCD
北大核心
2014年第6期1226-1231,共6页
Journal of Chinese Computer Systems
基金
国家自然科学基金项目(61072122)资助
教育部新世纪优秀人才计划项目(NCET-11-0134)资助
教育部高等学校博士学科点专项科研基金项目(20120161110014)资助
湖南省自然科学基金重点项目(11JJ2053)资助