A Pedestrian Fall Detection System Based on an Improved YOLOv5 Network

Considering the risk of falling, this paper designed a pedestrian fall detection system based on the improved YOLOv5 network, which optimizes the YOLOv5 network structure using BiFPN, DIoU-NMS and RepVGG as backbone network. Experimental results show that the accuracy of the system is 95.8%. This paper can provide reference for the development of fall detection technology and provide ideas and directions for future research.