智能视频监控中滞留物与人的关联分析算法  

Association Analysis Algorithm Between Abandoned Object and Human in Intelligent Video Surveillance

作　　者：王鹏[1] 朱秀昌[1] 

机构地区：[1]南京邮电大学江苏省图像处理与图像通信重点实验室,江苏南京210003

出　　处：《电视技术》2011年第3期101-105,共5页Video Engineering

基　　金：江苏省软件和集成电路业专项经费项目(苏信软2007-161号)

摘　　要：对智能视频监控中滞留物与人的关联分析算法进行了研究。当监控场景中出现物体滞留,检测滞留物并发出报警或提示,同时提取滞留关键帧;滞留物被移走时,检测移走并提取移走关键帧,根据滞留关键帧和移走关键帧中人的颜色特征进行相似性计算,来匹配移走者与滞留者是否为同一人,进而作出报警或提示等不同响应。实验证明,提出的算法具有很高的正确率。An association analysis algorithm between abandoned object and human in intelligent video surveillance is researched in this paper. When abandoned objects appear in the scene, the proposed algorithm will detect them and extract the key abandoned frame; when they are moved, the algorithm will detect the moved and extract the key moved frame, then compare the color feature of the persons in the key frames and determine whether the person who moved the object and the person who left the object are the same person. In the view of the analysis, an alarm or other responses are made. The experimental results demonstrate that the proposed algorithm has a high accuracy.

关 键 词：智能视频 滞留与移走检测 关联分析 Mean SHIFT算法 

分 类 号：TP277[自动化与计算机技术—检测技术与自动化装置]