Multi-Scale Safety Helmet Detection Based on RSSE-YOLOv3

Due to the shielding of dense and small targets, real-time detection of whether construction workers are wearing safety helmets suffers from low detection accuracy and missed detection. In this paper, a new detection algorithm based on YOLOv3 is proposed. Firstly, the parallel network RepVGG Skip Squeeze Excitation (RSSE) module is used to replace the Res8 module in the original YOLOv3 network. The RSSE module consists of 3 x 3 convolutional fusion channels and SSE branches fused. The introduction of the R-SSE module increases the network width, reduces the network depth, and improves the network detection speed and accuracy. Secondly, to avoid gradient disappearance and improve feature reuse, the residual module Res2 is used to replace the CBLx5 modules. Finally, the resolution of the input image is improved, and the four-scale feature prediction is used instead of the three-scale feature prediction to further improve the efficiency of detecting small targets. This paper also introduces the complete joint crossover (CIOU) to improve the loss function and positioning accuracy. The experimental results show that, compared with the original YOLOv3 algorithm, the improved algorithm improves the precision (P) by 3.9%, the recall (R) by 5.2%, and the average precision (mAP) by 4.7%, which significantly improves the performance of the detection.