视频监控下利用改进型YOLOv3的弱监督式异常行为检测  

Weak supervised abnormal behavior detection using improved YOLOv3under video surveillance

作　　者：赵雪章[1] 丁犇[1] 席运江[2] ZHAO Xuezhang;DING Beng;XI Yunjiang(School of Electronic Information,Foshan polytechnic,Foshan 528137,China;South China University of Technology,School of Economics and Management,Guangzhou 510641,China)

机构地区：[1]佛山职业技术学院电子信息学院,广东佛山528137 [2]华南理工大学经济管理学院,广东广州510000

出　　处：《光学技术》2021年第1期120-128,共9页Optical Technique

基　　金：国家自然科学基金面上项目(71371077);广东省教育厅创新类项目(2019GKTSCX119)。

摘　　要：为了对监控视频中的异常行为进行准确高效地检测,提出了一种利用改进型YOLOv3的弱监督式异常行为检测。采用多尺度融合的方式改进YOLOv3网络,利用改进型YOLOv3完成视频中的目标检测,提高计算效率与方法的通用性;利用光流可有效捕捉运动信息这一特性,提出大尺度光流直方图描述符(LSOFH)描述目标行为,以更好地提取异常行为特征;训练最小二乘支持向量机(LSSVM),用于识别监控视频中的异常行为。基于MATLAB仿真平台对所提方法进行实验论证,结果表明,相比于其他方法,所提方法在UCSD数据集、UMN数据集和地铁出口数据集上的表现最佳,曲线下面积(AUC)最大、等错误率(EER)最小且检测率最高,具有较好的应用前景。In order to detect abnormal behaviors in surveillance video accurately and efficiently,a weak supervised abnormal behavior detection method based on improved yolov3is proposed.Firstly,the multi-scale fusion method is used to improve the YOLOv3network,and the improved yolov3is used to complete the target detection in the video,which improves the computational efficiency and the universality of the method.Then,the large-scale optical flow histogram descriptor(LSOFH)is proposed to describe the target behavior by using the optical flow which can effectively capture the motion information,so as to better extract the abnormal behavior features.Finally,the least squares support vector machine(LSSVM)is trained to identify abnormal behaviors in surveillance video.Based on MATLAB simulation platform,the proposed method is verified by experiments.The results show that,compared with other methods,the proposed method performs best on the UCSD data set,UMN data set and subway exit data set,that is,the area under the curve(AUC)is the largest,the equal error rate(EER)is the lowest,and the detection rate is the highest.It has a good application prospect.

关 键 词：视频监控 异常行为 弱监督式 改进型YOLOv3 大尺度光流直方图描述符 最小二乘支持向量机 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]