An instance segmentation method for mining-induced ground fissures in shallow coal seams using UAV imagery

doi:10.13474/j.cnki.11-2246.2025.1112

Abstract

Abstract: Ground fissures induced by shallow coal mining significantly damage the ecological environment of mining areas.Timely detection and landfill treatment can prevent secondary hazards such as spontaneous combustion of residual coal and water inrush during rainy seasons.This paper proposes an improved YOLOv8 model for instance segmentation of ground fissures from UAV imagery.Firstly,the backbone of YOLOv8 is replaced with a pyramid vision transformer (PVT) to enhance multi-scale and high-resolution feature learning for dense fissures,improving geometric recognition capabilities.Then,UAV images from the Huangyuchuan Coal Mine in Inner Mongolia were processed to create the HYCdata dataset for model training.Experiments demonstrate that the modified YOLOv8 outperforms the original model,achieving a mAP_0.5 of 74.3%,providing an effective solution for automatic segmentation of widespread mining-induced fissures.

Key words: UAV imagery, Huang Yuchuan mines, mining-induced ground fissures, instance segmentation, YOLOv8 network

CLC Number:

P237

SUN Bin, ZHANG Ruiling, REN Chenfeng, LIN Yunhao, SUN Chao, LIU Yihan, LIU Mengjie, YUAN Debao, XU Zhihua. An instance segmentation method for mining-induced ground fissures in shallow coal seams using UAV imagery[J]. Bulletin of Surveying and Mapping, 2025, 0(11): 78-83.

References

[1] 周宏春,李长征,周春.我国能源领域科学低碳转型研究与思考[J].中国煤炭,2022,48(1):2-9.
[2] 刘辉.西部黄土沟壑区采动地裂缝发育规律及治理技术研究[D].徐州:中国矿业大学,2014.
[3] 彭苏萍,毕银丽.黄河流域煤矿区生态环境修复关键技术与战略思考[J].煤炭学报,2020,45(4):1211-1221.
[4] 范立民,孙魁,李成,等.西北大型煤炭基地地下水监测背景、思路及方法[J].煤炭学报,2020,45(1):317-329.
[5] 陈超,胡振琪.我国采动地裂缝形成机理研究进展[J].煤炭学报,2018,43(3):810-823.
[6] BRUNORI C A,BIGNAMI C,ALBANO M,et al.Land subsidence,ground fissures and buried faults:InSAR monitoring of Ciudad guzmán (Jalisco,Mexico)[J].Remote Sensing,2015,7(7):8610-8630.
[7] KASAI M,IKEDA M,ASAHINA T,et al.LiDAR-derived DEM evaluation of deep-seated landslides in a steep and rocky region of Japan[J].Geomorphology,2009,113(1/2):57-69.
[8] 张兴航,朱琳,王威,等.基于对象的地裂缝分步提取方法研究与应用[J].国土资源遥感,2019,31(1):87-94.
[9] 张健,毕银丽,彭苏萍.采动地表裂缝三维形态探测方法及精度评价研究[J].煤炭科学技术,2020,48(9):236-242.
[10] 侯恩科,张杰,谢晓深,等.无人机遥感与卫星遥感在采煤地表裂缝识别中的对比[J].地质通报,2019,38(S1):443-448.
[11] LIU Zhenqing,CAO Yiwen,WANG Yize,et al.Computer vision-based concrete crack detection using U-Net fully convolutional networks[J].Automation in Construction,2019,104:129-139.
[12] SHAHIN M,CHEN F F,MAGHANAKI M,et al.Improving the concrete crack detection process via a hybrid visual transformer algorithm[J].Sensors,2024,24(10):3247.
[13] CHUN Chanjun,RYU S K.Road surface damage detection using fully convolutional neural networks and semi-supervised learning[J].Sensors,2019,19(24):5501.
[14] 范立民,张晓团,向茂西,等.浅埋煤层高强度开采区地裂缝发育特征:以陕西榆神府矿区为例[J].煤炭学报,2015,40(6):1442-1447.
[15] JIANG Xiao,MAO Shanjun,LI Mei,et al.MFPA-Net:an efficient deep learning network for automatic ground fissures extraction in UAV images of the coal mining area[J].International Journal of Applied Earth Observation and Geoinformation,2022,114:103039.
[16] CHEN Peng,LI Peixian,WANG Bing,et al.GFSegNet:a multi-scale segmentation model for mining area ground fissures[J].International Journal of Applied Earth Observation and Geoinformation,2024,128:103788.
[17] DENG Jianghua,LU Ye,LEE V C.Imaging-based crack detection on concrete surfaces using You Only Look Once network[J].Structural Health Monitoring,2021,20(2):484-499.
[18] YE Guanting,QU Jinsheng,TAO Jintai,et al.Autonomous surface crack identification of concrete structures based on the YOLOv7 algorithm[J].Journal of Building Engineering,2023,73:106688.
[19] YANG Zhen,NI Changshuang,LI Lin,et al.Three-stage pavement crack localization and segmentation algorithm based on digital image processing and deep learning techniques[J].Sensors,2022,22(21):8459.
[20] 肖力炀,李伟,袁博,等.一种基于改进实例分割模型的路面裂缝检测方法[J].武汉大学学报(信息科学版),2023,48(5):765-776.
[21] TERVEN J,CÓRDOVA-ESPARZA D M,ROMERO-GONZÁLEZ J A.A comprehensive review of YOLO architectures in computer vision:from YOLOv1 to YOLOv8 and YOLO-NAS[J].Machine Learning and Knowledge Extraction,2023,5(4):1680-1716.
[22] WANG Wenhai,XIE Enze,LI Xiang,et al.Pyramid vision transformer:a versatile backbone for dense prediction without convolutions[C]//Proceedings of 2021 IEEE/CVF International Conference on Computer Vision (ICCV).Montreal:IEEE,2021:548-558.
[23] WANG C Y,YEH I H,MARK LIAO H Y.YOLOv9:learning what you want to learn using programmable gradient information[M]//Computer Vision-ECCV 2024.Cham:Springer Nature Switzerland,2024:1-21.
[24] WANG A,CHEN H,LIU L,et al.Yolov10:real-time end-to-end object detection[J].Advances in Neural Information Processing Systems,2024,37:107984-108011.
[25] KHANAM R,HUSSAIN M.Yolov11:an overview of the key architectural enhancements[EB/OL].[2024-02-15].https://www.arxiv.org/abs/2410.17725.