侯相军, 陈亚军, 孙超越, 肖慈. 基于骨骼特征点的跌倒检测方法[J]. 内江师范学院学报, 2024, 39(2): 52-57. DOI:10.13603/j.cnki.51-1621/z.2024.02.009
引用本文: 侯相军, 陈亚军, 孙超越, 肖慈. 基于骨骼特征点的跌倒检测方法[J]. 内江师范学院学报, 2024, 39(2): 52-57.DOI:10.13603/j.cnki.51-1621/z.2024.02.009
HOU Xiangjun, CHEN Yajun, SUN Chaoyue, XIAO Ci. A fall detection method based on skeletal feature points[J]. Journal of Neijiang Normal University, 2024, 39(2): 52-57. DOI:10.13603/j.cnki.51-1621/z.2024.02.009
Citation: HOU Xiangjun, CHEN Yajun, SUN Chaoyue, XIAO Ci. A fall detection method based on skeletal feature points[J].Journal of Neijiang Normal University, 2024, 39(2): 52-57.DOI:10.13603/j.cnki.51-1621/z.2024.02.009

基于骨骼特征点的跌倒检测方法

A fall detection method based on skeletal feature points

  • 摘要:针对现有跌倒检测方法中利用时空图卷积网络(ST-GCN)进行行为检测的准确率有待提高、时间信息利用不够充分等问题,提出了一种基于轻量级YOLO v3人体目标检测模型结合人体骨骼特征点的跌倒检测方法.本方法利用AlphaPose算法实时得到人体的骨骼特征点信息,在此基础上结合改进的ST-GCN模型提取了强化后的行为时空信息,从而对跌倒进行更加准确的检测.在通用数据集及自建数据集上的测试结果表明,该方法在跌倒检测中具有良好的效果.

    Abstract:Aiming at the problem that the accuracy of behavior detection using Spatio-Temporal Graph Convolutional Network (ST-GCN) in the existing fall detection methods needs to be improved, and the time information is not enough utilized, a fall detection method based on lightweight YOLOv3 human target detection model combined with human skeletal feature points is proposed. In this method, the AlphaPose algorithm is used to obtain the information of human skeletal feature points in real time. On the basis, combined with the improved ST-GCN model, the enhanced behavioral spatio-temporal information is extracted, so as to detect falls more accurately. The test results on the general data set and the self-built data set show that the method is effective in fall detection.

/

    返回文章
    返回
      Baidu
      map