基于优化YOLOv5s的老人跌倒检测算法

An algorithm for elderly fall detection based on optimization YOLOv5s

针对跌倒对老年人安全性问题造成的影响,以及现有目标检测模型在人物跌倒时易漏检、鲁棒性和泛化能力差等问题,对YOLOv5s算法进行优化,提出一种老人跌倒检测算法。使用改进的RepVGG模块代替YOLOv5s算法中的3×3卷积模块,优化损失函数,选择K-means++算法对所用数据集进行聚类优化。结果表明,所提算法的鲁棒性好、泛化能力强,平均准确率比YOLOv3,YOLOv4,YOLOv5s,CBAM-YOLOv5s模型分别提高了9%,8%,3%和1.2%。所提出的算法能够满足现实中不同场景对老人跌倒行为的检测需求,可以应用于移动设备或者监控设备中,在老年人安全保障领域发挥重要作用。

In response to the safety concerns caused by falls and the limitations of existing object detection models in robustness,generalization and susceptibility to missing fall events,an optimized algorithm for detecting falls in the elderly population was proposed.The improved RepVGG modules was used for replacing the 3×3 convolutional modules of the YOLOv5s algorithm,the loss function was optimized,and the K-means++clustering algorithm was employed to enhance dataset clustering.Experimental results demonstrate that the proposed algorithm exhibits strong robustness and generalization,achieving an average accuracy improvement of 9%,8%,3%,and 1.2%compared to YOLOv3,YOLOv4,YOLOv5s and CBAM-YOLOv5s models,respectively.The proposed algorithm meets the diverse requirements for fall detection in different real-world scenarios and can be applied in mobile devices or monitoring equipment,making a significant contribution to the field of elderly safety and protection.