Intelligent identification and extraction of geometric parameters for surface fracture networks of rocky slopes
-
摘要: 作为高陡岩质边坡建模的重要先决条件,快速精准地进行岩坡表面裂隙网络的参数化建模近年来成为了研究的热点。研究引入深度学习技术与智能算法聚类思想,提出了一种结合无人机摄影技术的高陡边坡坡面裂隙网络智能识别与几何参数提取的方法。采用空洞卷积算法对传统U-net分割识别网络进行改进,并运用GMM-EM算法对识别出的二值图中的裂隙进行聚类,最后引入RANSAC算法实现裂隙面的几何参数自动提取并运用DICE相似系数对识别结果进行对比分析。结果表明,该方法裂隙提取的准确率高于97%,相较于传统算法有所提高。同时,将该方法应用于云南鲁奎山铁矿边坡工程,实现了高陡岩坡表面裂隙信息的快速采集,为后续高陡岩质节理边坡建模提供了必要的技术支撑。Abstract: As an important prerequisite for modeling the high steep rocky slope, a fast and accurate parametric modeling for fracture networks of rocky slopes has become a popular research topic in recent years. Focusing on the deep learning and intelligent algorithmic clustering method, a UAV photography-based joint detection technique is proposed to identify and extract the geometric parameters of the fracture network on high steep slope surface. A dilated convolution is adopted to improve the traditional U-net segmentation network, and a GMM-EM algorithm is employed to cluster the segmented fractures on the binary images. Finally, a RANSAC algorithm is used to perform the extraction process of geometric parameter of the fracture network. Seen from the comparative results of DICE similar index, the accuracy of segmentation recognition is more than 97%, which shows that the proposed fracture extraction technique is more efficient and accurate than other traditional algorithms. The improved technique is applied to the slope of Lukuishan open pit, implementing the in-site rapid data extraction of fracture networks on the slope surface. This technique may provide an effective technical support for the refined modeling of high and steep rocky slopes.
-
-
![]()
图 4 改进U-net法与其他裂隙检测方法的结果对比
Figure 4. Comparison of results between improved U-net method with other fracture detection methods
![]()
图 6 GMM-EM聚类算法与其他算法的结果对比
Figure 6. Comparison of clustering results of GMM-EM algorithm with other algorithms
![]()
图 9 云南鲁奎山边坡裂隙面提取
Figure 9. Extraction of slope fracture surface in Lukuishan open-pit slope
表 1 改进U-net网络计算参数
Table 1 Configuration of improved U-net network equipment
项目 参数 项目 参数 CPU Intel i7-8500 Cuda 10.0 GPU NVIDIA GeforceGTX 1080 语言 Python 3.6 RAM DDR 416G 系统 Vmware+linux 框架 Pytorch 1.7 
下载: 导出CSV
表 2 各种边缘检测方法的DICE相似值对比
Table 2 Comparison of DICE similarity index in each edge detection algorithm
(%) 岩体种类 标签图 本文算法 传统FCN Sobel检测 Log检测 混凝土 100 98.32 95.21 76.63 83.18 沥青 100 97.32 96.32 69.64 77.21 花岗岩 100 98.82 91.23 58.01 68.47
下载: 导出CSV
-
[1] ZHANG P, LI J H, YANG X, et al. Semi-automatic extraction of rock discontinuities from point clouds using the ISODATA clustering algorithm and deviation from mean elevation[J]. International Journal of Rock Mechanics and Mining Sciences, 2018, 110: 76-87. doi: 10.1016/j.ijrmms.2018.07.009
[2] LATO M J, VÖGE M. Automated mapping of rock discontinuities in 3D lidar and photogrammetry models[J]. International Journal of Rock Mechanics and Mining Sciences, 2012, 54: 150-158. doi: 10.1016/j.ijrmms.2012.06.003
[3] GUO J T, LIU Y H, WU L X, et al. A geometry- and texture-based automatic discontinuity trace extraction method for rock mass point cloud[J]. International Journal of Rock Mechanics and Mining Sciences, 2019, 124: 104132. doi: 10.1016/j.ijrmms.2019.104132
[4] ZHANG P, DU K, TANNANT D D, et al. Automated method for extracting and analysing the rock discontinuities from point clouds based on digital surface model of rock mass[J]. Engineering Geology, 2018, 239: 109-118. doi: 10.1016/j.enggeo.2018.03.020
[5] VÖGE M, LATO M J, DIEDERICHS M S. Automated rockmass discontinuity mapping from 3-dimensional surface data[J]. Engineering Geology, 2013, 164: 155-162. doi: 10.1016/j.enggeo.2013.07.008
[6] CHEN J Q, ZHU H H, LI X J. Automatic extraction of discontinuity orientation from rock mass surface 3D point cloud[J]. Computers & Geosciences, 2016, 95: 18-31.
[7] WANG S H, ZHANG Z S, WANG C G, et al. Multistep rocky slope stability analysis based on unmanned aerial vehicle photogrammetry[J]. Environmental Earth Sciences, 2019, 78: 260. doi: 10.1007/s12665-019-8145-z
[8] CHEN N, KEMENY J, JIANG Q H, et al. Automatic extraction of blocks from 3D point clouds of fractured rock[J]. Computers & Geosciences, 2017, 109: 149-161.
[9] 贾曙光, 金爱兵, 赵怡晴. 无人机摄影测量在高陡边坡地质调查中的应用[J]. 岩土力学, 2018, 39(3): 1130-1136. https://www.cnki.com.cn/Article/CJFDTOTAL-YTLX201803044.htm JIA Shu-guang, JIN Ai-bing, ZHAO Yi-qing. Application of UAV oblique photogrammetry in the field of geology survey at the high and steep slope[J]. Rock and Soil Mechanics, 2018, 39(3): 1130-1136. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YTLX201803044.htm
[10] PAN D D, LI S C, XU Z H, et al. A deterministic-stochastic identification and modelling method of discrete fracture networks using laser scanning: development and case study[J]. Engineering Geology, 2019, 262: 105310. doi: 10.1016/j.enggeo.2019.105310
[11] 张顺, 龚怡宏, 王进军. 深度卷积神经网络的发展及其在计算机视觉领域的应用[J]. 计算机学报, 2019, 42(3): 453-482. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJX201903001.htm ZHANG Shun, GONG Yi-hong, WANG Jin-jun. The development of deep convolution neural network and its applications on computer vision[J]. Chinese Journal of Computers, 2019, 42(3): 453-482. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JSJX201903001.htm
[12] 李尧, 李术才, 刘斌, 等. 基于改进后向投影算法的地质雷达探测岩体裂隙的成像方法[J]. 岩土工程学报, 2016, 38(8): 1425-1433. https://www.cnki.com.cn/Article/CJFDTOTAL-YTGC201608009.htm LI Yao, LI Shu-cai, LIU Bin, et al. Imaging method of ground penetrating radar for rock fracture detection based on improved back projection algorithm[J]. Chinese Journal of Geotechnical Engineering, 2016, 38(8): 1425-1433. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YTGC201608009.htm
[13] ZHANG Z X, LIU Q J, WANG Y H. Road extraction by deep residual U-net[J]. IEEE Geoscience and Remote Sensing Letters, 2018, 15(5): 749-753.
[14] 薛亚东, 李宜城. 基于深度学习的盾构隧道衬砌病害识别方法[J]. 湖南大学学报(自然科学版), 2018, 45(3): 100-109. https://www.cnki.com.cn/Article/CJFDTOTAL-HNDX201803012.htm XUE Ya-dong, LI Yi-cheng. A method of disease recognition for shield tunnel lining based on deep learning[J]. Journal of Hunan University (Natural Sciences), 2018, 45(3): 100-109. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-HNDX201803012.htm
[15] 黄宏伟, 李庆桐. 基于深度学习的盾构隧道渗漏水病害图像识别[J]. 岩石力学与工程学报, 2017, 36(12): 2861-2871. https://www.cnki.com.cn/Article/CJFDTOTAL-YSLX201712001.htm HUANG Hong-wei, LI Qing-tong. Image recognition for water leakage in shield tunnel based on deep learning[J]. Chinese Journal of Rock Mechanics and Engineering, 2017, 36(12): 2861-2871. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSLX201712001.htm
[16] 朱大庆, 曹国. 基于全卷积网络的砂石图像粒径检测[J]. 计算机与现代化, 2020(7): 111-116. https://www.cnki.com.cn/Article/CJFDTOTAL-JYXH202007021.htm ZHU Da-qing, CAO Guo. Particle size detection of sandstone images based on full convolutional network[J]. Computer and Modernization, 2020(7): 111-116. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JYXH202007021.htm
[17] 薛东杰, 唐麒淳, 王傲, 等. 基于FCN的岩石混凝土裂隙几何智能识别[J]. 岩石力学与工程学报, 2019, 38(增刊2): 3393-3403. https://www.cnki.com.cn/Article/CJFDTOTAL-YSLX2019S2014.htm XUE Dong-jie, TANG Qi-chun, WANG Ao, et al. FCN-based intelligent identification of crack geometry in rock or concrete[J]. Chinese Journal of Rock Mechanics and Engineering, 2019, 38(S2): 3393-3403. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSLX2019S2014.htm
[18] 王鹏宇, 王述红. 四类常见边坡岩石类别识别和边界范围确定的方法[J]. 岩土工程学报, 2019, 41(8): 1505-1512. https://www.cnki.com.cn/Article/CJFDTOTAL-YTGC201908018.htm WANG Peng-yu, WANG Shu-hong. Method for identifying four common rock types of slopes and determining boundary range[J]. Chinese Journal of Geotechnical Engineering, 2019, 41(8): 1505-1512. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YTGC201908018.htm
[19] RONNEBERGER O, FISCHER P, BROX T. U-net: convolutional networks for biomedical image segmentation[C]//Medical Image Computing and Computer- Assisted Intervention-MICCAI 2015, 2015. doi: 10.1007/978-3-319-24574-4_28.
[20] FABRESSE F R, CABALLERO F, MAZA I, et al. An efficient approach for undelayed range-only SLAM based on Gaussian mixtures expectation[J]. Robotics and Autonomous Systems, 2018, 104: 40-55.
[21] SCHNABEL R, WAHL R, KLEIN R. Efficient RANSAC for point-cloud shape detection[J]. Computer Graphics Forum, 2007, 26(2): 214-226.
[22] 王述红, 张紫杉, 王存根, 等. 岩体结构面产状随机分布空间表征[J]. 东北大学学报(自然科学版), 2017, 38(1): 121-125. https://www.cnki.com.cn/Article/CJFDTOTAL-DBDX201701025.htm WANG Shu-hong, ZHANG Zi-shan, WANG Cun-gen, et al. Stochastic spatial characterization of structural plane occurrence in rockmass[J]. Journal of Northeastern University (Natural Science), 2017, 38(1): 121-125. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-DBDX201701025.htm
-
期刊类型引用(8)
1. 杨旭辉，柏谦，贾鹏蛟. 地铁车站小直径管幕-横梁支护参数优化分析. 沈阳工业大学学报. 2025(01): 114-123 . 
百度学术
2. 邱建，赵文，路博，孙旭. 新型管幕工法修建地铁车站地层变形特性及参数优化. 东北大学学报(自然科学版). 2024(11): 1645-1655 . 百度学术
3. 崔光耀，宋博涵，何继华，田宇航. 超近接上跨既有隧道施工影响分区及加固措施效果. 长江科学院院报. 2023(06): 114-118+125 . 百度学术
4. 伍凯，毕延哲，杨鑫，储修琼. 超浅覆土小净距上跨运营线路盾构掘进超前管幕支护模拟分析. 路基工程. 2023(04): 130-136 . 百度学术
5. 陈凯. 基于变形控制的密排管幕顶管施工顺序优化分析. 铁道勘察. 2023(05): 149-157 . 百度学术
6. 王子君，赵文，程诚，柏谦. 地铁车站小直径管幕工法开挖变形规律. 东北大学学报(自然科学版). 2022(11): 1630-1637 . 百度学术
7. 袁庆利. 大直径密排管幕的力学分析及在地铁车站中的应用. 吉林水利. 2021(06): 1-10 . 百度学术
8. 张贺. 新型钢管幕力学变形特征及其在地铁车站中的应用. 工程建设. 2021(09): 1-6 . 百度学术
其他类型引用(3)
计量
- 文章访问数:
- HTML全文浏览量: 0
- PDF下载量:
- 被引次数: 11
