留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于改进SSD的人群异常行为检测算法研究

亢洁 田野 杨刚

亢洁, 田野, 杨刚. 基于改进SSD的人群异常行为检测算法研究[J]. 红外技术, 2022, 44(12): 1316-1323.
引用本文: 亢洁, 田野, 杨刚. 基于改进SSD的人群异常行为检测算法研究[J]. 红外技术, 2022, 44(12): 1316-1323.
KANG Jie, TIAN Ye, YANG Gang. Research on Crowd Abnormal Behavior Detection Based on Improved SSD[J]. Infrared Technology , 2022, 44(12): 1316-1323.
Citation: KANG Jie, TIAN Ye, YANG Gang. Research on Crowd Abnormal Behavior Detection Based on Improved SSD[J]. Infrared Technology , 2022, 44(12): 1316-1323.

基于改进SSD的人群异常行为检测算法研究

基金项目: 

陕西省重点研发计划项目 2021GY-022

详细信息
    作者简介:

    亢洁(1973-),女,博士,副教授,主要研究方向:模式识别、机器视觉、智能控制。E-mail: kangjie@sust.edu.cn

  • 中图分类号: TP391

Research on Crowd Abnormal Behavior Detection Based on Improved SSD

  • 摘要: 针对人群异常行为检测任务中存在的算法复杂度较高,重叠遮挡等带来的检测精度低等问题,本文提出一种基于改进SSD(Single Shot Multi-box Detector)的人群异常行为检测算法。首先采用轻量级网络MobileNet v2代替原始特征提取网络VGG-16,并通过可变形卷积模块构建卷积层来增强感受野,然后通过将位置信息整合到通道注意力中来进行特征增强,能够捕获空间位置之间的远程依赖关系,从而可以较好处理重叠遮挡问题。实验结果表明,本文提出的算法对人群异常行为具有较好的检测效果。
  • 图  1  基于改进SSD的人群异常行为检测模型

    Figure  1.  Crowd abnormal behavior detection model based on improved SSD

    图  2  MobileNet v2网络模块

    Figure  2.  MobileNet v2 network module

    图  3  可变形卷积模块

    Figure  3.  Deformable convolution module

    图  4  坐标注意力模块

    Figure  4.  Coordinate attention module

    图  5  特征增强结构

    Figure  5.  Feature enhancement structure diagram

    图  6  LabelImg工作界面

    Figure  6.  LabelImg working interface

    图  7  本文模型在Ped1上的训练损失曲线

    Figure  7.  The training loss curve of the model in this paper on Ped1

    图  8  本文模型在Ped2上的训练损失曲线

    Figure  8.  The training loss curve of the model in this paper on Ped2

    图  9  可视化结果

    Figure  9.  Visualization results

    表  1  基于改进SSD的消融实验

    Table  1.   Ablation experiment based on improved SSD

    Methods Ped1 Ped2
    Test speed /fps AUC/% Test speed /fps AUC/%
    VGG-16 21.96 61.98 20.36 63.81
    MobileNet v2 27.92 65.26 27.02 70.25
    MobileNet v2+Deformable Conv 26.68 69.81 25.73 77.98
    MobileNet v2+Deformable Conv+CA 26.59 74.50 25.41 88.93
    下载: 导出CSV

    表  2  不同检测模型性能对比分析

    Table  2.   Comparative analysis of the performance of different detection models

    Methods Ped1 Ped2
    Test speed/fps AUC/% Test speed/fps AUC/%
    SSD 21.96 61.98 20.36 63.81
    Social Force[12] 23.36 67.50 23.18 70.00
    Pang et al.[13] 25.21 71.7 24.85 83.2
    Ours 26.59 74.50 25.41 88.93
    下载: 导出CSV
  • [1] HU Y. Design and implementation of abnormal behavior detection based on deep intelligent analysis algorithms in massive video surveillance[J]. Journal of Grid Computing, 2020, 18(2): 227-237. doi:  10.1007/s10723-020-09506-2
    [2] 张欣, 齐华. 基于YOLOv4的人体异常行为检测算法研究[J]. 计算机与数字工程, 2021, 49(4): 791-796. doi:  10.3969/j.issn.1672-9722.2021.04.034

    ZHANG X, QI H. Research on human abnormal behavior detection algorithm based on YOLOv4[J]. Computer and Digital Engineering, 2021, 49(4): 791-796. doi:  10.3969/j.issn.1672-9722.2021.04.034
    [3] 胡学敏, 陈钦, 杨丽. 基于深度时空卷积神经网络的人群异常行为检测和定位[J]. 计算机应用研究, 2020, 37(3): 891-895. https://www.cnki.com.cn/Article/CJFDTOTAL-JSYJ202003057.htm

    HU X M, CHEN Q, YANG L. Detection and localization of abnormal crowd behavior based on deep spatiotemporal convolutional neural network[J]. Application Research of Computers, 2020, 37(3): 891-895. https://www.cnki.com.cn/Article/CJFDTOTAL-JSYJ202003057.htm
    [4] Almazroey A A, Jarraya S K. Abnormal events and behavior detection in crowd scenes based on deep learning and neighborhood component analysis feature selection[C]//Proceedings of the International Conference on Artificial Intelligence and Computer Vision (AICV2020), 2020: 258-267.
    [5] MU Y L, ZHANG B. Abnormal event detection and localization in visual surveillance[C] //Communications, Signal Processing, and Systems, 2020: 1217-1225.
    [6] LIU W, Anguelov D, Erhan D, et al. SSD: Single shot multibox detector[C]//Proceedings of European Conference on Computer Vision, 2016: 21-37.
    [7] HOU Q B, ZHOU D Q, FENG J S. Coordinate attention for efficient mobile network design[C] //2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021: 13708-13717.
    [8] Ali K, MOHAMMAD S M. Improved anomaly detection in surveillance videos based on a deep learning method[C]// 8th Conference of AI & Robotics and 10th RoboCup Iranopen International Symposium, 2018: 73-81.
    [9] Sandler M, Howard A, Zhu M, et al. MobileNetV2: Inverted Residuals and Linear Bottlenecks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018: 4510-4520.
    [10] DAI J F, QI H Z, XIONG Y W, et al. Deformable Convolutional Networks[C]//2017 IEEE International Conference on Computer Vision (ICCV), 2017: 764-773.
    [11] Mahadevan V, LI W, Bhalodia V, et al. Anomaly detection in crowded scenes[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2010: 1975-1981.
    [12] WU W H, CHEN M Y, LI J H, et al. Visual information based social force model for crowd evacuation[J]. Tsinghua Science and Technology, 2022, 27(3): 619-629. doi:  10.26599/TST.2021.9010023
    [13] PANG G S, YAN C, SHEN C H, et al. Self-trained deep ordinal regression for end-to-end video anomaly detection[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020: 12170-12179.
  • 加载中
图(9) / 表(2)
计量
  • 文章访问数:  143
  • HTML全文浏览量:  14
  • PDF下载量:  33
  • 被引次数: 0
出版历程
  • 收稿日期:  2022-04-03
  • 修回日期:  2022-07-12
  • 刊出日期:  2022-12-20

目录

    /

    返回文章
    返回