计算机工程与应用 ›› 2024, Vol. 60 ›› Issue (11): 105-114.DOI: 10.3778/j.issn.1002-8331.2307-0190

• 模式识别与人工智能 • 上一篇    下一篇

改进YOLOv5的高精度跌倒检测算法

朱胜豪,钱承山,阚希   

  1. 1.南京信息工程大学 自动化学院,南京 211800
    2.无锡学院 物联网工程学院,江苏 无锡 214105
  • 出版日期:2024-06-01 发布日期:2024-05-31

High-Precision Fall Detection Algorithm with Improved YOLOv5

ZHU Shenghao, QIAN Chengshan, KAN Xi   

  1. 1.School of Automation, Nanjing University of Information Science & Technology, Nanjing 211800, China
    2.School of The Internet of Things Engineering, Wuxi University, Wuxi, Jiangsu 214105, China
  • Online:2024-06-01 Published:2024-05-31

摘要: 针对原始YOLOv5在人体跌倒检测任务中无法有效应对复杂细节捕捉、变形处理、不同尺度目标适应和遮挡检测的困境,提出了一种基于C2D改进YOLOv5模型的新型高精度跌倒检测算法C2D-YOLO。给出了一种名为C2D的新型特征提取模块,通过融合可变形卷积、标准卷积和通道空间混合注意机制,将其添加到主干网络中,旨在增强特征表征能力,更好地捕捉复杂细节和处理变形。在颈部网络中,采用了Swin Transformer block替代C3模块的瓶颈层,旨在最大限度地保留特征信息,以提升对不同尺度目标的检测精度并改善遮挡情况下的性能。在借鉴YOLOX解耦结构的基础上对YOLOv5的Head模块进行改进,旨在优化分类和回归性能。实验结果表明,相比现有的YOLOv5s,该方法的mAP0.5和mAP0.5:0.95分别提高了3.2个百分点和6.5个百分点,明显提升了检测精度,减少了误检率。

关键词: YOLOv5, 跌倒检测, C2D, Swin Transformer block, 解耦结构

Abstract: In order to counter the limitations of the original YOLOv5 human fall detection task, a highly accurate fall detection algorithm, called C2D-YOLO, is proposed in this paper. The original task struggles to effectively handle complex detail capture, deformation handling, target adaptation to different scales, and occlusion detection. To overcome these challenges, several improvements are made to the YOLOv5 model. Firstly, a new feature extraction module called C2D is introduced, which improves feature characterisation, captures complex details, and handles deformations by combining deformable convolution, standard convolution, and channel-space hybrid attention mechanisms. Secondly, in the neck network, Swin Transformer block replaces the bottleneck layer of the C3 module to retain more feature information, thereby improving target detection accuracy at different scales and enhancing performance under occlusion. Finally, the head module of YOLOv5 is enhanced based on the decoupled structure of YOLOX borrowed from YOLOv5 to optimise classification and regression performance. Experimental results show that this method achieves a 3.2 percentage points improvement in mAP0.5 and a 6.5 percentage points improvement in mAP0.5:0.95 compared to existing YOLOv5s. These improvements significantly increase detection accuracy and reduce false alarm rates.

Key words: YOLOv5, fall detection, C2D, Swin Transformer block, decoupled structure