摘要
针对传统视频监控数据量大且复杂、不能及时有效地检测到人体异常行为的问题,文中提出了一种基于YOLOv3改进网络模型的人体异常行为检测方法(YOLOv3-MSSE)。该方法基于经典YOLOv3网络模型,利用残差模块构建多尺度特征提取网络,提升了对大目标的检测精度;同时,在网络结构不同位置融入注意力机制,对特征图各个通道的特征重要性实现加权处理,有效提高了模型人体异常行为的检测性能。实验结果表明,相比传统YOLOv3算法,YOLOv3-MSSE方法的mAP值提升了20.8%,F1-scores提升了11.3%,该方法不仅能够有效地检测出监控场景中的人体特定异常行为,还能较好地平衡检测精确率与召回率之间的关系,比同类方法更适用于实际监控场景下的人体异常行为检测。
The data of traditional video surveillance is very large and complex,and cannot detect the abnormal behaviors of human in a timely and effective manner.In response to these problems,this paper presents an improved YOLOv3 algorithm(YOLOv3-MSSE)for the detection of human abnormal behavior.This algorithm can improve the detection accuracy of large targets for it is based on the traditional YOLOv3 network model,and a multi-scale feature extraction network is constructed by the residual modules.At the same time,by incorporating the attention mechanism into different positions of the network structure,and the importance of the features in each channel of the feature map can be weighted,which effectively improves the detection performance of the model for abnormal human behavior.Experimental results show that compared with the traditional YOLOv3 algorithm,the mAP of YOLOv3-MSSE is increased by 20.8%,and F1-scores is increased by 11.3%.The proposed algorithm can not only detect the specific abnormal behavior of the human in the monitoring scene effectively,but also can balance the relationship between the detection accuracy rate and the recall rate well.In addition,It is more suitable for the detection of human abnormal behavior in actual monitoring scenarios than similar methods.
作者
张红民
李萍萍
房晓冰
刘宏
ZHANG Hong-min;LI Ping-ping;FANG Xiao-bing;LIU Hong(College of Electrical and Electronic Engineering,Chongqing University of Technology,Chongqing 400054,China;Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100080,China)
出处
《计算机科学》
CSCD
北大核心
2022年第4期233-238,共6页
Computer Science
基金
重庆市自然科学基金面上项目(cstc2021jcyj-msxmX0525)。
关键词
神经网络
异常行为
多尺度
注意力机制
残差网络
Neural networks
Abnormal behavior
Multiscale
Attention mechanism
Resnet
作者简介
通信作者:张红民(hmzhang@cqut.edu.cn),born in 1970,Ph.D,professor,is a member of China Computer Federation and ACM.His main research interests include image Processing and pattern recognition.
