改进YOLOv3网络模型的人体异常行为检测方法

doi:10.11896/jsjkx.210300251

计算机科学 ›› 2022, Vol. 49 ›› Issue (4): 233-238.doi: 10.11896/jsjkx.210300251

• 计算机图形学&多媒体 • 上一篇下一篇

改进YOLOv3网络模型的人体异常行为检测方法

张红民¹, 李萍萍¹, 房晓冰¹, 刘宏²

1 重庆理工大学电气与电子工程学院重庆 400054;
2 中国科学院计算技术研究所北京 100080

收稿日期:2021-03-22 修回日期:2021-06-10 发布日期:2022-04-01
通讯作者: 张红民(hmzhang@cqut.edu.cn)
基金资助:
重庆市自然科学基金面上项目(cstc2021jcyj-msxmX0525)

Human Abnormal Behavior Detection Method Based on Improved YOLOv3 Network Model

ZHANG Hong-min¹, LI Ping-ping¹, FANG Xiao-bing¹, LIU Hong²

1 College of Electrical and Electronic Engineering, Chongqing University of Technology, Chongqing 400054, China;
2 Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100080, China

Received:2021-03-22 Revised:2021-06-10 Published:2022-04-01
About author:ZHANG Hong-min,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.
Supported by:
This work was supported by the Natural Science Foundation of Chongqing,China(cstc2021jcyj-msxmX0525).

摘要/Abstract

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。

关键词: 残差网络, 多尺度, 神经网络, 异常行为, 注意力机制

Abstract: 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 mo-dules.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.

Key words: Abnormal behavior, Attention mechanism, Multiscale, Neural networks, Resnet

中图分类号:

TP391

张红民, 李萍萍, 房晓冰, 刘宏. 改进YOLOv3网络模型的人体异常行为检测方法[J]. 计算机科学, 2022, 49(4): 233-238. https://doi.org/10.11896/jsjkx.210300251

ZHANG Hong-min, LI Ping-ping, FANG Xiao-bing, LIU Hong. Human Abnormal Behavior Detection Method Based on Improved YOLOv3 Network Model[J]. Computer Science, 2022, 49(4): 233-238. https://doi.org/10.11896/jsjkx.210300251

参考文献

[1] LENTZAS A,VRAKAS D.Non-intrusive human activity recognition and abnormal behavior detection on elderly people:a review[J].Artificial Intelligence Review,2020,53(3):1975-2021.
[2] XU T,TIAN C Y,LIU C H.Deep Learning for AbnormalCrowd Behavior Detection:A Review[J].Computer Science,2021,48(9):125-134.
[3] FAN Z,YIN J,SONG Y,et al.Real-time and accurate abnormal behavior detection in videos[J].Machine Vision and Applications,2020,31(7):1-13.
[4] WANG Y N,LUO J J,WANG D W.An abnormal behavior detection algorithm based on key frame and amplitude histogram entropy[J].Computer and Digital Engineering,2019,47(9):2281-2285.
[5] SATYBALDINA D Z,GLAZYRINA N S,KALYMOVA K A,et al.Development of an algorithm for abnormal human behavior detection in intelligent video surveillance system[J].IOP Conference Series:Materials Science and Engineering,2021,1069(1):12046-12054.
[6] WU C F,CHENG Z X,JIANG Y Z.A Novel Detection Framework for Detecting Abnormal Human Behavior[J].Mathema-tical Problems in Engineering,2020,2020(1):1-9.
[7] ZHENG H,LIU J F,LIAO M Y.Detection and recognition of abnormal human behavior based on hybrid algorithm under indoor video surveillance[J].Computer Applications and Software,2019,36(7):224-230,241.
[8] LI X Q,SUN S L.Research on abnormal behavior detection based YOLO network[J].Electronic Design Engineering,2018,26(20):160-164,170.
[9] LUO F B,WANG P,LIANG S Y,et al.Recognition of abnormal crowd behavior based on deep learning and sparse optical flow[J].Computer Engineering,2020,46(4):287-293,300.
[10] MA Y D,LUO Z J,NI Z F,et al.Improved SSD algorithm for multi-target detection[J].Computer Engineering and Applications,2020,966(23):29-36.
[11] HE K M,ZHANG X Y,REN S Q,et al.Deep Residual Learning for Image Recognition[C]//2016 IEEE Conference on Compu-ter Vision and Pattern Recognition (CVPR).Las Vegas,USA:IEEE Xplore,2016:770-778.
[12] HU J,SHEN L,ALBANIE S,et al.Squeeze and Excitation Networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2020,42(8):2011-2023.
[13] KANG Y,CUI G R,LI H,et al.Software requirement clustering algorithm integrating self-attention mechanism and multi-pyramid convolution[J].Computer Science,2020,47(3):48-53.
[14] WANG S Y,WANG J J.Research on real time detection method of high density crowd target based on improved yolov3 algorithm[J].Safety and Environmental Engineering,2019,26(5):194-200.
[15] REDMON J,FARHADI A.YOLOv3:An Incremental Improvement[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Salt Lake City,USA:IEEE Xplore,2018:1086-1091.
[16] ZOU Z W,QIN C.Method of dynamically constructing spatial topic R-tree based on k-means++[J].Journal of Computer Applications,2021,41(3):733-737.
[17] ZHANG F K,YANG F,LI C.Fastvehicle detection methodbased on improved YOLOv3[J].Computer Engineering and Application,2019,55(2):12-20.

相关文章 15

[1]	饶志双, 贾真, 张凡, 李天瑞. 基于Key-Value关联记忆网络的知识图谱问答方法 Key-Value Relational Memory Networks for Question Answering over Knowledge Graph 计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277
[2]	宁晗阳, 马苗, 杨波, 刘士昌. 密码学智能化研究进展与分析 Research Progress and Analysis on Intelligent Cryptology 计算机科学, 2022, 49(9): 288-296. https://doi.org/10.11896/jsjkx.220300053
[3]	周芳泉, 成卫青. 基于全局增强图神经网络的序列推荐 Sequence Recommendation Based on Global Enhanced Graph Neural Network 计算机科学, 2022, 49(9): 55-63. https://doi.org/10.11896/jsjkx.210700085
[4]	戴禹, 许林峰. 基于文本行匹配的跨图文本阅读方法 Cross-image Text Reading Method Based on Text Line Matching 计算机科学, 2022, 49(9): 139-145. https://doi.org/10.11896/jsjkx.220600032
[5]	周乐员, 张剑华, 袁甜甜, 陈胜勇. 多层注意力机制融合的序列到序列中国连续手语识别和翻译 Sequence-to-Sequence Chinese Continuous Sign Language Recognition and Translation with Multi- layer Attention Mechanism Fusion 计算机科学, 2022, 49(9): 155-161. https://doi.org/10.11896/jsjkx.210800026
[6]	熊丽琴, 曹雷, 赖俊, 陈希亮. 基于值分解的多智能体深度强化学习综述 Overview of Multi-agent Deep Reinforcement Learning Based on Value Factorization 计算机科学, 2022, 49(9): 172-182. https://doi.org/10.11896/jsjkx.210800112
[7]	汪鸣, 彭舰, 黄飞虎. 基于多时间尺度时空图网络的交通流量预测模型 Multi-time Scale Spatial-Temporal Graph Neural Network for Traffic Flow Prediction 计算机科学, 2022, 49(8): 40-48. https://doi.org/10.11896/jsjkx.220100188
[8]	李瑶, 李涛, 李埼钒, 梁家瑞, Ibegbu Nnamdi JULIAN, 陈俊杰, 郭浩. 基于多尺度的稀疏脑功能超网络构建及多特征融合分类研究 Construction and Multi-feature Fusion Classification Research Based on Multi-scale Sparse Brain Functional Hyper-network 计算机科学, 2022, 49(8): 257-266. https://doi.org/10.11896/jsjkx.210600094
[9]	李宗民, 张玉鹏, 刘玉杰, 李华. 基于可变形图卷积的点云表征学习 Deformable Graph Convolutional Networks Based Point Cloud Representation Learning 计算机科学, 2022, 49(8): 273-278. https://doi.org/10.11896/jsjkx.210900023
[10]	王馨彤, 王璇, 孙知信. 基于多尺度记忆残差网络的网络流量异常检测模型 Network Traffic Anomaly Detection Method Based on Multi-scale Memory Residual Network 计算机科学, 2022, 49(8): 314-322. https://doi.org/10.11896/jsjkx.220200011
[11]	郝志荣, 陈龙, 黄嘉成. 面向文本分类的类别区分式通用对抗攻击方法 Class Discriminative Universal Adversarial Attack for Text Classification 计算机科学, 2022, 49(8): 323-329. https://doi.org/10.11896/jsjkx.220200077
[12]	姜梦函, 李邵梅, 郑洪浩, 张建朋. 基于改进位置编码的谣言检测模型 Rumor Detection Model Based on Improved Position Embedding 计算机科学, 2022, 49(8): 330-335. https://doi.org/10.11896/jsjkx.210600046
[13]	王润安, 邹兆年. 基于物理操作级模型的查询执行时间预测方法 Query Performance Prediction Based on Physical Operation-level Models 计算机科学, 2022, 49(8): 49-55. https://doi.org/10.11896/jsjkx.210700074
[14]	陈泳全, 姜瑛. 基于卷积神经网络的APP用户行为分析方法 Analysis Method of APP User Behavior Based on Convolutional Neural Network 计算机科学, 2022, 49(8): 78-85. https://doi.org/10.11896/jsjkx.210700121
[15]	朱承璋, 黄嘉儿, 肖亚龙, 王晗, 邹北骥. 基于注意力机制的医学影像深度哈希检索算法 Deep Hash Retrieval Algorithm for Medical Images Based on Attention Mechanism 计算机科学, 2022, 49(8): 113-119. https://doi.org/10.11896/jsjkx.210700153

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

改进YOLOv3网络模型的人体异常行为检测方法

Human Abnormal Behavior Detection Method Based on Improved YOLOv3 Network Model

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0