基于动态蛇形-膨胀卷积模型的矿区地裂缝提取

doi:10.13474/j.cnki.11-2246.2024.1024.

测绘通报 ›› 2024, Vol. 0 ›› Issue (10): 144-150.doi: 10.13474/j.cnki.11-2246.2024.1024.

• 技术交流 • 上一篇

基于动态蛇形-膨胀卷积模型的矿区地裂缝提取

王晓宇^1,2, 蔡音飞¹, 胡海峰¹

1. 太原理工大学矿业工程学院, 山西太原 030024;
2. 山西省煤炭地质勘查研究院有限公司, 山西太原 030006

收稿日期:2024-01-26 发布日期:2024-11-02
通讯作者: 蔡音飞,E-mail:caiyinfei@tyut.edu.cn
作者简介:王晓宇(1993—),男,硕士,研究方向为3S技术集成与应用。E-mail:wxiaoyu186@163.com
基金资助:
国家自然科学基金(52074133);教育部产学合作协同育人项目(220905458233959)

Extracting crack in mining areas based on dynamic snake-dilation convolution model

WANG Xiaoyu^1,2, CAI Yinfei¹, HU Haifeng¹

1. College of Mining Engineering, Taiyuan University of Technology, Taiyuan 030024, China;
2. Shanxi Coal Geological Investigation and Research Institute Co., Ltd., Taiyuan 030006, China

Received:2024-01-26 Published:2024-11-02

摘要/Abstract

摘要： 采动裂缝是煤矿地下开采造成的破坏形式之一。针对矿区地表环境复杂、无人机图像裂缝提取方法精度较低的问题,本文融合动态蛇形卷积和膨胀卷积构建了全新的动态蛇形-膨胀卷积,并将其添加到现有分割模型的编码、解码结构,以优化整体网络模型结构;构建了矿区裂缝数据集,并在该自制数据集上进行裂缝提取精度验证。结果表明,加入动态蛇形-膨胀卷积,可使模型的分割精度(平均交并比)提高14.96%,对于实现地裂缝准确提取具有实践价值。

关键词: 地下开采, 地裂缝, 无人机, 裂缝提取, 动态蛇形-膨胀卷积, 精度评价

Abstract: Mining cracks are a common type of damage that occurs in coal mines due to underground mining. Aiming at the problems of complex surface environment in mining areas and low accuracy of crack extraction methods in UAV images, this studyfused the dynamic snake convolution and dilation convolution to construct a new dynamic snake-dilation convolution. The proposed convolution is added to the encoding and decoding structure of the reference model to optimize the overall network structure; In addition, constructed a crack dataset of the mining area, and verified the accuracy of the crack extraction on this custom dataset. The results show that the addition of dynamic snake-dilation convolution can improve the segmentation accuracy (mean intersection over union) of the model by 14.96%, which is of practical value for achieving accurate extraction of ground cracks.

Key words: underground mining, ground surface crack, unmanned aerial vehicle, crack extraction, dynamic snake-dilation convolution, precision assessment

中图分类号:

王晓宇, 蔡音飞, 胡海峰. 基于动态蛇形-膨胀卷积模型的矿区地裂缝提取[J]. 测绘通报, 2024, 0(10): 144-150.

WANG Xiaoyu, CAI Yinfei, HU Haifeng. Extracting crack in mining areas based on dynamic snake-dilation convolution model[J]. Bulletin of Surveying and Mapping, 2024, 0(10): 144-150.

参考文献

[1] 贺卫中,向茂西,刘海南,等.榆神府矿区地面塌陷特征及环境问题[J].煤田地质与勘探,2016,44(5):131-135.
[2] 杨奇让,胡振琪,韩佳政,等.煤矿区无人机影像采动地裂缝提取方法研究[J].煤炭科学技术,2023,51(6):187-196.
[3] VAZQUEZ-NICOLAS J M,ZAMORA E,GONZALEZ-HERNANDEZ I,et al.Towards automatic inspection:crack recognition based on Quadrotor UAV-taken images[C]//Proceedings of 2018 International Conference on Unmanned Aircraft Systems.Dallas:IEEE,2018.
[4] ZHAO Yingxiang,ZHOU Lumei,WANG Xiaoli,et al.Highway crack detection and classification using UAV remote sensing images based on CrackNet and CrackClassification[J].Applied Sciences,2023,13(12):7269.
[5] 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.
[6] 胡波,陈志谋,吴洋,等.利用DInSAR技术检测地裂缝分布及走向[J].测绘通报,2018(2):103-106.
[7] 孙月敏,杨天亮,卢全中,等.基于SBAS-InSAR的西安市鱼化寨地区地面沉降与地裂缝时空演变特征研究[J].工程地质学报,2022,30(2):553-564.
[8] 肖春蕾,郭兆成,张宗贵,等.利用机载LiDAR数据提取与分析地裂缝[J].国土资源遥感,2014,26(4):111-118.
[9] ZHANG Fan,HU Zhenqi,LIANG Yusheng,et al.An optimal approach for crack extraction from UAV sub-images after cutting[J].International Journal of Remote Sensing,2022,43(7):2638-2659.
[10] LIANG Yusheng,ZHANG Fan,YANG Kun,et al.A surface crack damage evaluation method based on kernel density estimation for UAV images[J].Sustainability,2022,14(23):16238.
[11] 王瑞国.基于WorldView-2数据的乌东煤矿地质灾害遥感调查及成因分析[J].国土资源遥感,2016,28(2):132-138.
[12] 邓博,许强,董秀军,等.点云与数字图像数据融合的斜坡变形裂缝自动检测[J].武汉大学学报(信息科学版),2023,48(8):1296-1311.
[13] 许强,郭晨,董秀军.地质灾害航空遥感技术应用现状及展望[J].测绘学报,2022,51(10):2020-2033.
[14] 郭运冲,李孟军,刘名果,等.基于Canny算子的建筑裂缝边缘检测改进算法[J].计算机仿真,2022,39(11):360-365.
[15] 赵毅鑫,许多,孙波,等.基于无人机红外遥感和边缘检测技术的采动地裂缝辨识[J].煤炭学报,2021,46(2):624-637.
[16] 刘星,莫思特,张江,等.轻量化模型的PeleeNetyolov3地表裂缝识别[J].哈尔滨工业大学学报,2023,55(4):81-89.
[17] 李怡静,程浩东,李火坤,等.基于改进U2-Net与迁移学习的无人机影像堤防裂缝检测[J].水利水电科技进展,2022,42(6):52-59.
[18] TAO Huaqi,LIU Bingxi,CUI Jinqiang,et al.A convolutional-transformer network for crack segmentation with boundary awareness[C]//Proceedings of 2023 IEEE International Conference on Image Processing.Kuala Lumpur:IEEE,2023:86-90.
[19] QI Yaolei,HE Yuting,QI Xiaoming,et al.Dynamic snak econvolution based on topological geometric constraints for tubular structure segmentation[C]//Proceedings of 2023 IEEE/CVF International Conference on Computer Vision.Paris:IEEE,2023:6047-6056.
[20] CHEN Feng,WU Fei,XU Jing,et al.Adaptive deformable convolutional network[J].Neurocomputing,2021,453(C):853-864.
[21] LI Aijin,JIAO Licheng,ZHU Hao,et al.Multitask semantic boundary awareness network for remote sensing image segmentation[J].IEEE Transactions on Geoscience and Remote Sensing,2022,60:5400314.
[22] CHEN Tianxiang,CHU Qi,TAN Zhentao,et al.BAUENet:boundary-aware uncertainty enhanced network for infrared small target detection[C]//Proceedings of 2023 IEEE International Conference on Acoustics,Speech and Signal Processing.Rhodes Island:IEEE,2023:1-5.
[23] MEHTA S,RASTEGARI M.MobileViT:light-weight,general-purpose,and mobile-friendly vision transformer[EB/OL].arXiv[2023-12-25].http://arxiv.org/abs/2110.02178.
[24] YANG Fan,ZHANG Lei,YU Sijia,et al.Feature pyramid and hierarchical boosting network for pavement crack detection[J].IEEE Transactions on Intelligent Transportation Systems,2020,21(4):1525-1535.
[25] ZHANG Lei,YANG Fan,ZHANG Y D,et al.Road crack detection using deep convolutional neural network[C]//Proceedings of 2016 IEEE International Conference on Image Processing.Phoenix:IEEE,2016:3708-3712.
[26] LIU Yahui,YAO Jian,LU Xiaohu,et al.DeepCrack:a deep hierarchical feature learning architecture for crack segmentation[J].Neurocomputing,2019,338(C):139-153.

基于动态蛇形-膨胀卷积模型的矿区地裂缝提取

Extracting crack in mining areas based on dynamic snake-dilation convolution model

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	蓝贵文, 徐梓睿, 任新月, 钟展, 郭瑞东, 范冬林. 基于YOLOv8n改进的航拍输电线路图像多类电力部件检测算法[J]. 测绘通报, 2024, 0(9): 38-43,49.
[2]	韦忠扬, 黄景金, 郭伟立, 冯一军, 李正洪, 韦秋莲, 盘贻峰, 谢洪. 面向耕地变化的无人机组网监测技术研究与实践[J]. 测绘通报, 2024, 0(9): 140-144.
[3]	徐宇翔, 胡庆武, 段延松, 李加元, 艾明耀, 赵鹏程. 融合LiDAR点云与无人机影像的滑坡动态监测技术[J]. 测绘通报, 2024, 0(8): 42-47.
[4]	谢幸生, 张永挺, 丁宗宝, 江玉欢, 刘剑. 激光导航与决策融合的小样本无人机航拍图像分类[J]. 测绘通报, 2024, 0(7): 173-177.
[5]	石耀榕, 肖敬达. 无人机影像拼接多分辨率自适应无缝融合方法[J]. 测绘通报, 2024, 0(6): 36-40.
[6]	陆玉婷, 段金荣. 基于无人机多光谱技术的池塘水质分析与可视化设计[J]. 测绘通报, 2024, 0(6): 127-133.
[7]	梁文广, 吴勇锋, 石一凡, 王冬梅, 王轶虹. 基于无人机高光谱的太浦河水质反演[J]. 测绘通报, 2024, 0(4): 29-34.
[8]	肖杰. 无人机载LiDAR点云密度对DEM精度的影响分析[J]. 测绘通报, 2024, 0(4): 35-40.
[9]	张书航, 李旺民, 庞尹宁, 常兵涛, 马德富, 李秀龙, 张吴明. 基于无人机倾斜摄影和激光扫描的离岸海岛高精度实景三维重建[J]. 测绘通报, 2024, 0(3): 25-30.
[10]	高桂棠, 郗连霞, 钟晓龙. 基于卷积神经网络和无人机倾斜摄影图像的单个高层建筑物高度测算方法[J]. 测绘通报, 2024, 0(3): 118-122.
[11]	赵莲, 于亚杰, 梁治华. 基于冠层高度模型的遥感影像玉米倒伏范围提取[J]. 测绘通报, 2024, 0(3): 127-133.
[12]	徐花芝, 蒋文婷, 陈春雷, 张允涛, 王萧. 智航无人机载LiDAR系统在轨道交通建设中的应用分析[J]. 测绘通报, 2024, 0(2): 178-182.
[13]	廖超明, 云子恒, 罗恒, 韦媛媛, 凌子燕, 潘桂颖. 基于特征优选的喀斯特地区覆被信息提取及精度分析[J]. 测绘通报, 2024, 0(2): 45-50.
[14]	黄海峰, 张瑞, 周红, 易武, 薛蓉花, 董志鸿, 柳青, 邓永煌, 张国栋. 小尺度山区地质灾害隐患的无人机精细化识别方法与实践[J]. 测绘通报, 2024, 0(1): 6-11.
[15]	黄玉林, 刘龙飞, 祖为国, 谭金石. 无人机LiDAR在输电线路平断面测绘中的应用[J]. 测绘通报, 2024, 0(1): 131-135.