摘要
针对传统的非压缩域镜头检测算法数据量大、运算量大和效率低的缺点,提出一种基于压缩域的镜头检测算法.该算法首先根据MPEG压缩标准,从视频流中提取DCT系数,然后经预处理得到每一帧的DC系数,最后依DC系数建立镜头检测信息系统模型,依分割模型产生视频镜头.实验结果表明,此算法相对传统非压缩域算法运算量和数据量大大减少,提高了算法效率.
Aimed at the'shortcoming in conventional shot inspection algorithm oriented to non-compressed domain such as enormous quantity of data and computation and low inspection efficiency, a new compressed-domain-oriented shot inspection algorithm was presented..In this method, the DCT coefficients were extracted first from the video stream according to MPEG standard and then the DC coefficients were obtained for each frame after preprocessing of the former. Finally, a model of the shot inspection informa- tion system was established by using the DC coefficients and a video shot was obtained by using a segmen- tation model. Experimental result showed that, by using this method, the amount of computation and data was reduced greatly and the algorithm efficiency increased dramaticly.
出处
《兰州理工大学学报》
CAS
北大核心
2008年第6期97-101,共5页
Journal of Lanzhou University of Technology
基金
甘肃省自然科学基金(3ZS051-A25-047)
关键词
镜头
镜头检测
I帧
shot
shot detection
I frame