视频监控环境下行人异常识别方法研究  

Study on Pedestrian Abnormal Recognition Based on Video Surveillance

作　　者：王家鹏 张著洪 WANG Jiapeng;ZHANG Zhuhong(College of Big Data and Information Engineering, Guizhou University, Guiyang 550025, Chin)

机构地区：[1]贵州大学大数据与信息工程学院,贵州贵阳550025

出　　处：《贵州大学学报（自然科学版）》2018年第2期72-75,105,共5页Journal of Guizhou University:Natural Sciences

基　　金：国家自然科学基金资助项目(61563009);贵州大学研究生创新基金项目(研理工2017013)

摘　　要：针对智能监控中行人异常行为检测难的问题,研究反映行人的局部、全局特征的特征信息和探讨异常行为检测的方法。首先,通过设计和利用轮廓特征、局部检测频率、运动速度特征量与轮廓变化曲线模型,获得行为检测的特征模型,进而借助特征信息融合和利用模板库获得异常行为检测算法。比较性的实验结果显示,该算法能有效识别行人的异常行为。For the difficulty of pedestrian abnormal behavior detection in intelligent monitoring,this study investigates pedestrians’ local and global feature information and abnormal behavior detection. A behavior feature vector model is first developed to present pedestrians’ motion features by means of contour feature,local detection frequency,motion velocity and contour curve. Second,an abnormal behavior detection approach is designed to identify whether a pedestrian behaves abnormally,based on feature fusion and template library. The numerically comparative experiments show that one such approach can effectively detect whether the pedestrian is abnormal.

关 键 词：行人 行为检测 特征提取 异常识别 智能监控 

分 类 号：TP391.413[自动化与计算机技术—计算机应用技术]