高级检索

  • ISSN 1006-3080
  • CN 31-1691/TQ

一种改进的适用于监控视频的轻量级入侵检测算法及其应用

陈涛 陈天宇 万永菁 王嵘 孙静

陈涛, 陈天宇, 万永菁, 王嵘, 孙静. 一种改进的适用于监控视频的轻量级入侵检测算法及其应用[J]. 华东理工大学学报(自然科学版). doi: 10.14135/j.cnki.1006-3080.20201110002
引用本文: 陈涛, 陈天宇, 万永菁, 王嵘, 孙静. 一种改进的适用于监控视频的轻量级入侵检测算法及其应用[J]. 华东理工大学学报(自然科学版). doi: 10.14135/j.cnki.1006-3080.20201110002
CHEN Tao, CHEN Tianyu, WAN Yongjing, WANG Rong, SUN Jing. An Improved Lightweight Intrusion Detection Algorithm for Surveillance Video and Its Application[J]. Journal of East China University of Science and Technology. doi: 10.14135/j.cnki.1006-3080.20201110002
Citation: CHEN Tao, CHEN Tianyu, WAN Yongjing, WANG Rong, SUN Jing. An Improved Lightweight Intrusion Detection Algorithm for Surveillance Video and Its Application[J]. Journal of East China University of Science and Technology. doi: 10.14135/j.cnki.1006-3080.20201110002

一种改进的适用于监控视频的轻量级入侵检测算法及其应用

doi: 10.14135/j.cnki.1006-3080.20201110002
基金项目: 国家自然科学基金(61872143)
详细信息
    作者简介:

    陈涛:陈 涛(1996—),男,江苏泰州人,硕士生,主要研究方向为目标检测、深度学习。E-mail:ctzj1026@163.com

    通讯作者:

    万永菁,E-mail:wanyongjing@ecust.edu.cn

  • 中图分类号: TP391.4

An Improved Lightweight Intrusion Detection Algorithm for Surveillance Video and Its Application

  • 摘要: 由于传统的目标检测算法较为复杂,在算力、存储空间有限的场景下无法实时检测,因此本文提出了一种轻量级入侵检测算法。首先采用自适应更新率的混合高斯前景提取算法提取初筛目标,然后基于改进的残差压缩网络(R-SqueezeNet)对初筛目标进行识别分类。实验结果表明,该算法在不降低检测精度的前提下,比传统算法的检测速度平均提升了30倍,模型体积缩减至YOLOv3-tiny算法的1/40。

     

  • 图  1  整体算法流程

    Figure  1.  Overall algorithm flow

    图  2  镜头突变前后的提取效果对比

    Figure  2.  Comparison of extraction effect before and after lens mutation

    图  3  不同$ {t}_{H} $下算法的表现

    Figure  3.  Algorithm performance under different $ {t}_{H} $

    图  4  提取效果对比

    Figure  4.  Comparison of extraction effect

    图  5  R-SqueezeNet结构

    Figure  5.  Structure of R-SqueezeNet

    图  6  Fire module计算流程

    Figure  6.  Calculation process of fire module

    图  7  残差结构

    Figure  7.  Residual structure

    图  8  不同前景调整方式的分类精度对比

    Figure  8.  Comparison of different foreground resizing methods

    图  9  不同$ {t}_{H} $下的算法性能对比

    Figure  9.  Performance comparison of algorithms at different $ {t}_{H} $

    表  1  分类网络模型对比

    Table  1.   Comparison of classification network models

    ModelNumber of Fire moduleAccuracy/%Inference time/msSize/MB
    This paper Cats vs dogs Cifar-10
    SqueezeNet190.5689.991.61.340.16
    294.3590.6193.851.70.33
    396.3292.9695.742.30.89
    496.5893.1796.133.781.5
    596.6793.3996.374.042.8
    R-SqueezeNet396.5593.296.12.880.89
    496.7393.3296.353.921.5
    596.893.4996.554.562.8
    697.0193.5696.617.024.1
    797.293.7196.697.686.4
    897.3893.8796.739.38.9
    下载: 导出CSV

    表  2  基于自适应和非自适应前景提取的算法对比

    Table  2.   Comparison of algorithms based on adaptive and non-adaptive foreground extraction

    BasedBackboneFD/%MD/%
    Non-adaptive extractionLeNet13.88.2
    AlexNet9.13.3
    ZFNet8.72.9
    R-SqueezeNet8.62.7
    Adaptive extractionLeNet10.38.2
    AlexNet5.43.3
    ZFNet5.12.9
    R-SqueezeNet4.92.7
    下载: 导出CSV

    表  3  本文算法和传统目标检测算法对比

    Table  3.   Comparison with traditional object detection algorithm

    AlgorithmBackboneSize/MBFD/%MD/%FPS
    SSDVGG16[25]95.75.32.91
    RetinaNetResNet50[19]146.14.22.4<1
    YOLOv2Darknet19[8]1944.52.5<1
    YOLOv3Darknet53[9]246.94.22.31
    YOLOv3-tinyDarknet13[9]35.67.63.75
    This paperR-SqueezeNet0.894.92.744
    下载: 导出CSV
  • [1] 赵潇. 基于人类视觉系统的监控视频目标提取技术研究[D]. 重庆: 重庆邮电大学, 2018.
    [2] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. USA: IEEE, 2005: 886-893.
    [3] VIOLA P, JONES M. Rapid object detection using a boosted cascade of simple features[C]//Proceedings the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. USA: IEEE, 2001: 511-518.
    [4] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. USA: IEEE, 2014: 580-587.
    [5] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: Unified, real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. USA: IEEE, 2016: 779-788.
    [6] LIU W, ANGUELOV D, ERHAN D, et al. SSD: Single shot multibox detector[C]//European Conference on Computer Vision. Cham: Springer, 2016: 21-37.
    [7] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//Proceedings of the IEEE International Conference on Computer Vision. Italy: IEEE, 2017: 2980-2988.
    [8] REDMON J, FARHADI A. YOLO9000: Better, faster, stronger[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. USA: IEEE, 2017: 7263-7271.
    [9] REDMON J, FARHADI A. Yolov3: An incremental improvement[EB/OL]. arxiv. org, (2018-04-10)[2020-11-01]. https://arxiv.org/pdf/1804.02767.pdf.
    [10] IANDOLA F N, HAN S, MOSKEWICZ M W, et al. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size[EB/OL]. arxiv. org, (2016-03-20)[2020-11-01]. https://arxiv.org/pdf/1602.07360v3.pdf.
    [11] STAUFFER C, GRIMSON W E L. Learning patterns of activity using real-time tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(8): 747-757. doi: 10.1109/34.868677
    [12] ZIVKOVIC Z. Improved adaptive Gaussian mixture model for background subtraction[C]//Proceedings of the 17th International Conference on Pattern Recognition. UK: IEEE, 2004: 28-31.
    [13] ZIVKOVIC Z, VAN DER HEIJDEN F. Efficient adaptive density estimation per image pixel for the task of background subtraction[J]. Pattern Recognition Letters, 2006, 27(7): 773-780. doi: 10.1016/j.patrec.2005.11.005
    [14] LEE D S. Effective Gaussian mixture learning for video background subtraction[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(5): 827-832. doi: 10.1109/TPAMI.2005.102
    [15] 龚安, 牛博, 史海涛. 基于分块的帧差法和混合高斯算法的油田作业区入侵检测[J]. 计算机与数字工程, 2019, 47(12): 3041-3044.
    [16] 刘馨. 监控视频中的图像颜色评价与优化[D]. 杭州: 浙江大学, 2015.
    [17] 李均, 王志诚, 吴雨轩, 等. 熵概念的延拓——从热熵到信息熵[J]. 大学物理, 2020, 39(10): 29-33.
    [18] 王林, 王超凡. 差分信息熵在拼接图像质量评估中的应用[J]. 计算机仿真, 2020, 37(4): 265-268, 273. doi: 10.3969/j.issn.1006-9348.2020.04.055
    [19] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. USA: IEEE, 2016: 770-778.
    [20] 汪斌, 陈宁. 基于残差注意力U-Net结构的端到端歌声分离模型[J]. 华东理工大学学报(自然科学版), 2021, 47(5).
    [21] 高磊, 范冰冰, 黄穗. 基于残差的改进卷积神经网络图像分类算法[J]. 计算机系统应用, 2019, 28(7): 139-144.
    [22] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324. doi: 10.1109/5.726791
    [23] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Imagenet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90. doi: 10.1145/3065386
    [24] ZEILER M D, FERGUS R. Visualizing and understanding convolutional networks[C]//European Conference on Computer Vision. Cham: Springer, 2014: 818-833.
    [25] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[EB/OL]. arxiv. org, (2014-10-22)[2020-11-01]. https://arxiv.org/abs/1409.1556.
  • 加载中
图(9) / 表(3)
计量
  • 文章访问数:  351
  • HTML全文浏览量:  192
  • PDF下载量:  12
  • 被引次数: 0
出版历程
  • 收稿日期:  2020-11-10
  • 网络出版日期:  2021-01-25

目录

    /

    返回文章
    返回