工矿自动化2025，Vol.51Issue(9)：33-42,65,11.DOI:10.13272/j.issn.1671-251x.2025050058
基于图像增强和改进YOLOv8的煤矿低光照目标检测
Low-light target detection in coal mines based on image enhancement and improved YOLOv8
摘要
Abstract
At present,the existing image enhancement techniques for underground coal mines suffer from insufficient stability and large fluctuations in the quality of generated images,which affect the accuracy of subsequent target detection.Meanwhile,target detection methods based on YOLOv8 also face certain limitations in low-light environments due to weakened image features and information loss.To address these problems,a low-light target detection algorithm for coal mines based on image enhancement and improved YOLOv8 was proposed.The Denoising Diffusion Probabilistic Model(DDPM)was used to denoise and enhance the original images,restoring illumination and detail information.Based on YOLOv8n,improvements were made by introducing a Low-Frequency Filter Enhancement Module(LEF)and a Feature Enhancement Module(FEM)to enhance feature extraction performance for low-light images.The original CIoU regression loss function in YOLOv8n was replaced with MPDIoU,yielding the YOLOv8-DLFM model.The YOLOv8-DLFM was then used for target detection to improve accuracy and robustness.Experimental results showed that:① compared with mainstream image enhancement methods,DDPM achieved a peak signal-to-noise ratio of 28.379 dB,a structural similarity index of 0.886,and a perceptual similarity of 0.104,demonstrating superior image reconstruction quality and structural similarity.② YOLOv8-DLFM exhibited excellent overall performance,with precision,recall,and mAP@0.5 reaching 0.878,0.791,and 0.896,respectively,and a frame rate of 88.6 frames/s.Compared with the original YOLOv8n model,the precision,recall,and mAP@0.5 of YOLOv8-DLFM increased by 8.13％,6.6％,and 8.74％,respectively.③ Compared with mainstream target detection models,YOLOv8-DLFM demonstrated stronger robustness and higher detection accuracy under complex low-light environments.It also exhibited high robustness and adaptability under typical conditions such as target occlusion,lighting interference,sparse targets,and dense targets.关键词
井下目标检测/低光照/图像增强/YOLOv8n/去噪概率扩散模型/低频滤波/特征增强Key words
underground target detection/low light/image enhancement/YOLOv8n/Denoising Diffusion Probabilistic Model/low-frequency filtering/feature enhancement分类
矿业与冶金引用本文复制引用
王宏伟,刘学刚,王浩然,曹文艳,付翔,刘泽平,李建忠..基于图像增强和改进YOLOv8的煤矿低光照目标检测[J].工矿自动化,2025,51(9):33-42,65,11.基金项目
国家自然科学基金青年基金项目(52404176) （52404176）
山西省基础研究计划项目(202203021222105,202303021212074,202403011242001) （202203021222105,202303021212074,202403011242001）
智能采矿装备技术国家重点实验室自主研究项目(ZNCK20240108) （ZNCK20240108）
山西省创新平台与基地建设专项项目(202404010911004Z). （202404010911004Z）
