DOI: 10.11799/ce202602021
Lightweight high-precision foreign object detection network for underground conveyor belt
SHUI Yifei
GAO Guijun
JIAO Shaoni
Abstract：To address the challenge of balancing detection performance and real-time capability under complex factors in coal mine environments,such as noise,multi-scale targets,and occlusion,we proposed a lightweight and high-precision foreign object detection method for underground conveyor belts based on an improved YOLOv11.Firstly,building upon YOLOv11,a dynamic convolution module integrating multi-path channel attention(DCNv2-Dynamic)was introduced to replace the standard convolutions in the C3k2 blocks of the backbone network,enhancing the capture of critical features in complex scenes.Secondly,a 160×160 detection layer was added to strengthen small object perception,while the redundant 20×20 output layer was removed to reduce computational load.Furthermore,a Separate and Enhance Attention Module(SEAM)was embedded into the detection heads to mitigate the information loss caused by occlusion.Experimental results show that the improved model achieves significant performance gains,achieving a 3.7%improvement in mAP50 and a 10.8%improvement in mAP50:95,alongside a 26.2%reduction in computational cost and a 21.8%reduction in model size,thereby establishing an efficient and reliable solution for foreign object detection in underground coal mine conveyor belts.
Keywords：conveyor belt foreign object detectionYOLOdynamic convolutionlightweight network
Publication Date：2026-02-20
Online Publishing Date：2026-03-23(First online date of this platform, not the publication date of the document)
Pages：7( 169-175 )