Research on safety helmet wearing YOLO-V3 detection technology improvement in mine environment

Abstract

The existing AI object detection technology cannot meet the demand of safety helmet wearing detection accuracy in mine environment. This paper studies YOLO correlation algorithm, establishing an optimal model based on YOLO-V3, combines the deep residual network technology with the multi-scale convolution feature based on the YOLO-V3 detection algorithm, combines the multi-scale detection training and adjusts the loss function in the training process. The experimental results show that with satisfying the detection speed, safety helmet wearing detection accuracy in mine environment is significantly improved.