测绘通报 ›› 2025, Vol. 0 ›› Issue (10): 63-70.doi: 10.13474/j.cnki.11-2246.2025.1011

• 学术研究 • 上一篇    

无人机露天煤矿早期煤火红外图像目标检测识别方法

庞文宇1, 张小栋1,2, 诸伟3, 陶庆1   

  1. 1. 新疆大学机械工程学院, 新疆 乌鲁木齐 830047;
    2. 西安交通大学机械工程学院, 陕西 西安 711049;
    3. 北清通航科技(乌鲁木齐)有限公司, 新疆 乌鲁木齐 830000
  • 收稿日期:2025-03-21 发布日期:2025-10-31
  • 通讯作者: 张小栋。E-mail:xdzhang@mail.xjtu.edu.cn
  • 作者简介:庞文宇(1997-),男,硕士,主要研究方向为无人机智能巡检方向。E-mail:3143417140@qq.com
  • 基金资助:
    新疆维吾尔自治区天山英才项目(2023TSYCLJ0051);特种无人设备在露天煤矿的应用项目(202407140005)

An early UAV coal fire infrared image target detection and recognition method in open-pit coal mines

PANG Wenyu1, ZHANG Xiaodong1,2, ZHU Wei3, TAO Qing1   

  1. 1. School of Mechanical Engineering, Xinjiang University, Urumqi 830047, China;
    2. School of Mechanical Engineering, Xi'an Jiaotong University, Xi'an 711049, China;
    3. Beiqing General Aviation Technology Co., Ltd., (Urumqi), Urumqi 830000, China
  • Received:2025-03-21 Published:2025-10-31

摘要: 针对当前露天煤矿早期煤火自燃火情存在检测困难、发现时间晚等问题,本文提出一种基于YOLOv12n改进的无人机露天煤矿早期煤层自燃红外图像目标检测识别方法,即在模型上更换主干网络PP-LCNet,引入二次改进的MCADSA注意力机制模块,并添加改进后的NWD损失函数。该方法提升了红外图像煤火数据集的检测精度,为实现早期煤层自燃火情的智能化巡检提供了帮助。

关键词: 煤火自燃, 无人机, 红外图像, 目标检测, YOLOv12

Abstract: In view of the current difficulties in early detection of coal fires in open-pit coal mines and the late discovery time, this paper proposes an improved UAV infrared image target detection and recognition method for early coal seam spontaneous combustion in open-pit coal mines based on YOLOv12n.By replacing the backbone network with PP-LCNet, introducing a secondary improved MCADSA attention mechanism module, and adding an improved NWD loss function, the detection accuracy of the infrared image coal fire dataset has been improved, providing assistance for the intelligent inspection of early coal seam spontaneous combustion.

Key words: coal fire spontaneous combustion, UAV, infrared image, target detectio, YOLOv12

中图分类号: