基于分层匹配五元组Codebook的运动目标检测算法  

Moving objects extraction algorithm based on hierarchical matching 5-tuple codebook

作　　者：赵晓梅[1] 孙建德[1] 张元元[2] 

机构地区：[1]山东大学信息科学与工程学院,济南250100 [2]山东省科学院情报研究所,济南250014

出　　处：《计算机工程与应用》2016年第7期196-201,共6页Computer Engineering and Applications

基　　金：国家自然科学基金(No.61001180)

摘　　要：运动目标检测是智能视频分析的第一步,Codebook算法是该领域中广泛应用的算法之一。分层匹配五元组Codebook算法是在经典Codebook算法基础上的一种改进算法。该改进算法在码字模型中引入平均亮度代替最大亮度和最小亮度,并且依据平均亮度对高亮度和低亮度区域采用不同的匹配计算方法。实验表明,改进后的Codebook算法成功利用五元组代替六元组实现处理速度的提高,利用高低亮度区域分层匹配实现检测精度的提高。Moving objects extraction is the first step of the intelligent video analysis. Codebook algorithm is one of the widely used algorithms in this field. Hierarchical matching 5-tuple-based codebook algorithm is a modification of the typical 6-tuple codebook algorithm. In the proposed algorithm, the average intensity is introduced as a variable into the Codebook model instead of the minimal and maximal intensities. And different matching methods between the current pixel and codeword are adopted according to the average intensity in the high and low intensity areas respectively. Experimental results show that the proposed codebook algorithm successfully improves the processing speed by using 5-tuple instead of6-tuple, reduces false positive rate and improves the accuracy of detection by using hierarchical matching.

关 键 词：智能视频分析 运动目标检测 背景建模 平均亮度 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]