基于无人机影像的矿区地表水平位移特征识别算法效果对比研究#br#

金属矿山 ›› 2025, Vol. 54 ›› Issue (10): 226-233.

基于无人机影像的矿区地表水平位移特征识别算法效果对比研究#br#

房　平¹　刘爱军¹　张俊阳²　陈建崇¹　王　昆²　姚新宇¹　卜文超¹　赵　鑫¹　李一哲³　朱瑞劼²

1. 鄂尔多斯市昊华红庆梁矿业有限公司,内蒙古鄂尔多斯 017000;2. 山东科技大学能源与矿业工程学院,山东青岛 266590;
3. 煤炭科学技术研究院有限公司,北京 100013

出版日期:2025-10-15 发布日期:2025-11-10
通讯作者: 王　昆(1991—),男,副教授,博士,硕士研究生导师。
作者简介:房　平(1983—),男,高级工程师。
基金资助:
山东省自然科学基金项目(编号:ZR2024ME144)。

Comparative Study on the Effect of Surface Horizontal Displacement Feature Recognition Algorithm in Mining Area Based on UAV Image#br#

FANG Ping1　LIU Aijun1　ZHANG Junyang2　CHEN Jianchong1　WANG Kun2　　YAO Xinyu1　BU Wenchao1　ZHAO Xin1　LI Yizhe3　ZHU Ruijie2#br#

1. Ordos Haohua Hongqingliang Mining Co. ,Ltd. ,Ordos 017000,China;2. College of Energy and Mining Engineering,Shandong
University of Science and Technology,Qingdao 266590,China;3. CCTEG China Coal Research Institute,Beijing 100013,China

Online:2025-10-15 Published:2025-11-10

摘要/Abstract

摘要： 煤炭高强度井工开采引发地表沉陷问题日益突出,其中水平位移是导致地表不均匀形变和地质灾害的
关键因素。针对传统观测方法效率低、覆盖范围有限等问题,提出基于无人机摄影测量与特征识别算法的地表水平
位移全域观测方法。以内蒙古鄂尔多斯市红庆梁煤矿12308 工作面地表为例,系统对比FAST、Harris 和SIFT 共3 种
特征识别算法测量精度与稳定性。结果表明:SIFT 算法在采动影响范围外的水平位移观测误差为1. 20~2. 08 cm,显
著优于FAST 算法(2. 06~3. 09 cm)和Harris 算法(1. 53~3. 82 cm);在采动影响范围内,SIFT 算法误差控制在0. 67~
2. 18 cm 范围内,同样优于FAST 和Harris 算法,其多尺度特征提取能力、尺度不变性及对光照变化与植被干扰的强鲁
棒性,可保证在复杂地表地貌下稳定识别特征点,未出现特征点丢失现象。相较于传统单点观测方法,所提出方法可
实现厘米级精度的全域覆盖观测,且具备高频动态更新与低成本优势;通过提高无人机影像分辨率、优化多尺度特征
融合策略及构建动态特征点数据库,可进一步提升算法在噪声环境下的适应性。研究成果为矿区地表沉陷与地质灾
害观测提供了新手段,对保障矿山安全开采与生态保护具有重要应用价值。

关键词: 开采沉陷　摄影测量　特征识别　匹配算法　数字正射影像

Abstract: The problem of surface subsidence caused by high-intensity underground mining of coal has become increasingly
prominent,and horizontal displacement is a key factor leading to uneven surface deformation and geological disasters. Aiming
at the problems of low efficiency and limited coverage of traditional observation methods,a global observation method of
surface horizontal displacement based on UAV photogrammetry and feature recognition algorithm is proposed. Taking the surface
of 12308 working face of Hongqingliang Coal Mine in Ordos City,Inner Mongolia as an example,the measurement accuracy
and stability of three feature recognition algorithms,FAST,Harris and SIFT,are systematically compared. The results show
that the horizontal displacement observation error of SIFT algorithm outside the mining influence range is 1. 20-2. 08 cm,which
is significantly better than FAST algorithm (2. 06-3. 09 cm) and Harris algorithm (1. 53-3. 82 cm). In the range of mining
influence,the error of SIFT algorithm is controlled in the range of 0. 67-2. 18 cm,which is also better than FAST and Harris
algorithms. Its multi-scale feature extraction ability,scale invariance and strong robustness to illumination change and vegetation
interference can ensure stable recognition of feature points under complex surface topography without loss of feature points.
Compared with the traditional single-point observation method,the proposed method can achieve global coverage observation with centimeter-level accuracy,and has the advantages of high-frequency dynamic update and low cost. By improving the resolution
of UAV images,optimizing the multi-scale feature fusion strategy and constructing a dynamic feature point database,the
adaptability of the algorithm in noisy environment can be further improved. The research results provide a new method for the
observation of surface subsidence and geological disasters in the mining area,and have important application value for ensuring
the safe mining and ecological protection of the mine.

Key words: mining subsidence,photogrammetric survey,feature identification,matching algorithm,digital orthoimage

中图分类号:

TD327

房　平　刘爱军　张俊阳　陈建崇　王　昆　姚新宇　卜文超　赵　鑫　李一哲　朱瑞劼. 基于无人机影像的矿区地表水平位移特征识别算法效果对比研究#br#[J]. 金属矿山, 2025, 54(10): 226-233.

FANG Ping　LIU Aijun　ZHANG Junyang　CHEN Jianchong　WANG Kun　　YAO Xinyu　 BU Wenchao　ZHAO Xin　LI Yizhe　ZHU Ruijie. Comparative Study on the Effect of Surface Horizontal Displacement Feature Recognition Algorithm in Mining Area Based on UAV Image#br#[J]. Metal Mine, 2025, 54(10): 226-233.

扫码分享