高级检索

    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), 2021, 47(6): 734-741. 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), 2021, 47(6): 734-741. 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, 2021, 47(6): 734-741. 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, 2021, 47(6): 734-741. 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

    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。

       

      Abstract: With the development of target detection algorithms, the intrusion detection based on surveillance video has attracted more attention. Due to the complexity of the traditional target detection algorithm and the difficulty in detecting in real time in the scene of limited computing power and storage space, this paper proposes a lightweight intrusion detection algorithm. Firstly, the preliminary screening target is extracted through the adaptive update rate of the mixed Gaussian foreground extraction algorithm. And then, the preliminary screening target is identified based on the improved residual squeeze network (R-SqueezeNet) classification. It is shown via experimental results that, without reducing the detection accuracy, the proposed algorithm can increase the detection speed by an average of 30 times compared with the traditional algorithm, and the model size is reduced to 1/40 of YOLOv3-tiny.

       

    /

    返回文章
    返回