Research on Safe Wearable Target Detection Technology for Power Production Scenarios based on YOLOv5-C3CA

Abstract

Aiming at the establishment of a new generation of substation auxiliary equipment detection platform intelligence, this study proposes a power production industry personnel safety wear detection technology based on improved Yolov5-C3CA to meet the demand. First, the network performance is improved by adding the CA attention mechanism module to Yolov5s network; moreover, the CA module is modified to C3CA module and added to the model for more effective addition of the attention mechanism; finally, the AFPN network structure is used to replace the original feature pyramid network structure, which further effectively improves the utilization efficiency of shallow and deep features. The experimental results show that the mean average accuracy of the designed network is improved by 3.9% to 93.1% compared with the original network, and other evaluation indexes are also improved. It can be seen that the model modification in this paper has improved the performance of the detection network, and the improved network meets the requirements of the new generation of substation auxiliary equipment detection platform, which has a positive effect on the safety and reliability of the power production industry.