基于CoordEF-YOLOv9t的煤矿井下人员行为识别

打开文本图片集

中图分类号：TD67 文献标志码：A

Abstract：Deep learning-based methods for personnel behavior recognition in underground coal mines suffer fromseveral issues，including thelack ofa systematic classification framework formulti-class behavior recognition，detail losscaused bydim lightingand low-resolutionimages，and feature deformation due to differences in miner posture and viewpoint.An underground coal mine personnel behavior recognition model， CoordEF-YOLOv9t， was proposed.The model improved YOLOv9t in two aspects： edge feature extraction and spatial position feature extraction.In YOLOv9t，the convolution operation of the RepNCSPELAN4 module tends to cause detail blurring when capturing subtle or fuzzyedges.Toaddress this problem，anEdgeFeatureExtraction Module （EFEM） fused with the Sobel operator Was designed and embedded into the RepNCSPELAN4 module， enhancing the abilityof the backbone and neck networks to perceive the edge details ofhuman bodies.Traditional convolutional neural networks have dificulty perceiving positional informationand fully learning the spatial features of personnel location and action.To address this issue， coordinate convolution was introduced at the end of the neck network to improve the model's perception of the positional information of personnel behavior.The experimental results showed that the precision （P） of CoordEF-YOLOv9t was 73.4% ，the recall （R） was 73.7% 5 the mAP@0.5 was 74.8% ，and the mAP@0.5：0.95 was 61.1% ，which were improvements of 1.2% ， 3.2% ， 1.0% ， and 2.1% ，respectively， compared with YOLOv9t. Compared with mainstream models such as RT-DETR， YOLOvl1，and YOLOvl2， CoordEF-YOLOv9t demonstrates superior overall performance and can more accurately recognize underground personnel behavior in coal mines.

Key words： underground personnel behavior recognition; YOLOv9t; edge feature extraction; spatial position feature extraction; Sobel operator; coordinate convolution

0引言

随着煤矿开采深度的增加，井下作业环境日益复杂，潜在危险因素不断增多[1]。（剩余14589字）