煤矿安全2025，Vol.56Issue(9)：16-24,9.DOI:10.13347/j.cnki.mkaq.20250752
露天矿无人矿车道路障碍端到端多目标检测研究
Research on end-to-end multi-target detection of unmanned mine car road obstacles in open-pit mines
摘要
Abstract
Mining engineering is rapidly developing towards automation and intelligence,and the construction of intelligent mines has become a future trend.The multi-objective environmental perception of unmanned mine cars in open-pit mine areas is a key step in unmanned transportation.For the safety risks caused by multiple obstacles such as rolling pits,puddles,vehicles and personnel in complex unstructured roads,the existing end-to-end algorithms face the challenges of small target information loss,insufficient multi-scale feature fusion,unbalanced samples,and difficulty in balancing model complexity and accuracy in the dynamic and complex en-vironment of open-pit mines.To this end,an end-to-end multi-target detection model You Only Look Once-Mine Multi-target Detec-tion(YOLO-MMD)for unmanned mine trucks in open-pit mines is proposed.For the problem of missing observation pixel informa-tion caused by unstructured terrain in open-pit mines,Space-to-Depth Convolution(SPD-Conv)is introduced to transform image spatial information into depth information,which effectively preserves the fine-grained perception ability of small targets in unstruc-tured scenes and improves computational efficiency.In order to improve the effective use of context information,Efficient Multi-Scale Attention(EMA)is embedded in the detection layer to realize pixel-level cross-channel interaction and spatial information ag-gregation,which enhances the ability of multi-scale feature fusion without significantly increasing the computational burden.In addi-tion,considering the sample imbalance problem of different obstacle target objects in open-pit mines,the In-Focaler-IoU loss func-tion is designed to improve the efficiency and convergence speed of bounding box regression with auxiliary bounding box while pay-ing attention to rare target samples.The study show that YOLO-MMD can detect multi-target objects under the conditions of occlu-sion and blurring,and achieve the best balance between multi-target detection accuracy and complexity.It can achieve 0.939 mAP,4.56 MB model size and 5.8 G floating-point operations per second,which can provide effective and feasible environmental percep-tion for the safe driving of unmanned mine cars.关键词
矿山无人驾驶/多目标检测/YOLO/矿山计算机视觉/环境感知Key words
mine unmanned driving/multi-target detection/YOLO/mine computer vision/environmental perception分类
矿业与冶金引用本文复制引用
崔智翔,江松,毛晶,孔若男,王靖..露天矿无人矿车道路障碍端到端多目标检测研究[J].煤矿安全,2025,56(9):16-24,9.基金项目
国家自然科学基金面上资助项目(52374136) （52374136）
中国矿业大学煤炭精细勘探与智能开发全国重点实验室开放研究课题资助项目(SKLCRSM23KFO1C) （SKLCRSM23KFO1C）
