摘要
提出一种与视频编码器共用运动搜索模块的实时场景切换检测算法.通过分析原始图像与其运动补偿图像的一阶与二阶差值信号统计特性,分别构造对应于不同场景切换类型的两种测度函数,并联合使用该测度函数检测突变场景切换,同时自适应调节每个测度函数输出值的判决门限.分析和实验结果表明,该算法在视频编码位移估值基础上只增加少量的计算,而对视频序列中的突变场景切换检测的查全率和查准率均优于已有的几种实时检测算法.
A real time scene cut detection algorithm is proposed which shares the results of motion estimation with the video encoder. To deal with different kinds of scene cuts, two metric functions are introduced based on the statistics of the first and second order difference between the original pictures and their motion compensated pictures. The detection thresholds for each metric are adaptively adjusted according to the scenes. The experimental results and analysis show that the recall and precision of the proposed algorithm are generally higher than other tested ones at the cost of little computation time increment.
出处
《光子学报》
EI
CAS
CSCD
北大核心
2010年第6期1058-1063,共6页
Acta Photonica Sinica
基金
国家自然科学基金(60772134)
高等学校学科创新引智计划(B08038)
西电-华为多媒体通信联合实验室合作专项基金
西电研究生创新基金(创05018)资助