A METHOD FOR RECIPROCATING MOTION DETECTION IN PORN VIDEO BASED ON MOTION FEATURES

摘要：

This paper presents a new algorithm for detecting the humans reciprocating motion in pornographic videos. First, the motion vector is extracted from mpeg video stream and pretreated so that the motion features are extracted by analyzing the motion rule of the objectionable videos. Then the whole videos are detected through setting a threshold. Experimental results demonstrate that the correct recognition rate of this algorithm is up to 80%, so it is fit for the most of video detection environments.

关键词： Motion Vector Motion features Porn video Reciprocating motion Direction Histogram

作者: Qu Zhiyi Liu Yanmin Liu Ying Jiu Kang Chen Yong

作者单位: School of Information Science & Engineering, Lan zhou University Lanzhou, China,730000

会议类型: 国际会议

会议名称: 2009 2nd IEEE International Conference on Broadband Network & Multimedia Technology(2009年宽带网络与多媒体国际会议 IEEE IC-BNMT2009)

会议地点: 北京

会议语种:英文

页码: 183-187

在线出版日期: 2009-10-18（万方平台首次上网日期，不代表论文的发表时间）