Identification and characterization of rock fractures based on computer vision and software development
-
摘要: 岩石裂隙特征是评判岩体结构及其完整性的核心指标，也是评估岩石工程安全稳定性的重要因素。针对岩石裂隙识别，采用深度学习方法，通过引入混合注意力机制对Unet模型进行了改进，有效提高了岩石裂隙识别的精度。针对交叉岩石裂隙的分离与特征提取，提出了一种基于迹线方向判定的裂隙分离与表征算法，依据裂隙分离的结果形式，采用重合追踪法或断裂追踪法分离交叉裂隙骨架，继而使用微分累加法、方框法、线性回归法求得裂隙的长度、宽度及倾角等几何特征指标。基于提出的算法，研制了一套具有图形用户界面的岩石裂隙图像智能识别与表征软件系统，实现了从深度学习模型参数选择、模型训练、裂隙识别、量化分析到结果可视化的完整功能。最后对岩石裂隙识别与分离表征算法的性能进行了评判，结果表明，改进Unet模型对复杂分布的裂隙识别效果最好，其总体识别性能要优于其他网络；骨架分离算法对常见类型交叉裂隙能够取得预期结果，表征算法对分离裂隙与交叉裂隙的表征精度高，对实际岩石裂隙图像的应用效果较好。研究成果可为基于计算机视觉的岩石工程试验与岩体结构检测技术研发提供参考依据。Abstract: The characteristics of rock fractures are the core indices for evaluating the structure and integrity of rock masses, and are also the important factors for evaluating the safety and stability of rock engineering. For the rock fracture recognition based on deep learning, the Unet model is improved by introducing the convolutional block attention module, effectively improving the accuracy of rock fracture recognition. For separation and feature extraction of intersection fractures, a fracture separation and characterization algorithm based on the trace direction judgment is proposed. According to the characteristics of fracture separation, the overlapping tracing method or fracture tracing method is used to separate the intersection fracture skeleton. Then, the differential accumulation method, box method and linear regression method are employed to calculate the geometric characteristic indices such as the length, width and dip angle of the fractures. Based on the proposed algorithm, a set of software system for the intelligent identification and characterization of rock fracture images with a graphical user interface is developed, achieving complete functions from deep learning model parameter selection, model training, fracture recognition, quantitative analysis to result visualization. Finally, the performance of rock fracture recognition and separation characterization algorithms is evaluated. The results show that the improved Unet model has the best recognition performance for complex distribution fractures, and its overall recognition performance is superior to that of other networks. The skeleton separation algorithm achieves the expected results for the separation of common types of intersection fractures, and the characterization algorithm has high accuracy in characterizing the separation and intersection fractures. It has good application effects on actual rock fracture images. The research can provide reference for rock engineering tests and detection of rock mass structure by using the computer vision.
-
Keywords:
- rock fracture /
- deep learning /
- image analysis /
- fracture separation /
- fracture characterization
-
-
![]()
图 5 裂隙骨架特征点的判别原理
Figure 5. Discriminant principle of characteristic points of fracture skeleton
![]()
图 6 不同类型裂隙交叉点的判别
Figure 6. Distinguishing of different types of intersection points of fractures
![]()
图 7 交叉裂隙两种分离结果示意图
Figure 7. Schematic diagram of separation results of intersection fractures
![]()
图 8 交叉点处裂隙追踪方向判定
Figure 8. Distinguishing of fracture tracking direction at intersection point
![]()
图 13 PhotoDetector程序的模型选择与训练界面
Figure 13. Model selection and training interface of PhotoDetector program
![]()
图 14 PhotoDetector程序的裂隙识别界面
Figure 14. Fracture identification interface of PhotoDetector program
![]()
图 15 PhotoObjects的裂隙表征界面
Figure 15. Fracture characterization interface of PhotoObjects program
![]()
图 16 模拟裂隙长度与宽度的计算结果
Figure 16. Calculated results of simulated fracture length and width
![]()
图 17 实际裂隙表征结果示意图
Figure 17. Schematic diagram of characterization results of actual fractures
表 1 岩石裂隙基本类型划分
Table 1 Classification of basic types of rock fractures
裂隙类别 裂隙图像 单条 多条 分离型 
Y型 X型 单点交叉型 
多点交叉型 
下载: 导出CSV
表 2 各类算法裂隙识别效果比较
Table 2 Comparison of fracture recognition effects of various algorithms
类别 原图 基准图 VGG16 Unet 改进Unet 类别1 
类别2 
类别3 
下载: 导出CSV
表 3 不同算法的裂隙识别效果定量评价
Table 3 Quantitative evaluation of fracture recognition effects under different algorithms
评价指标 算法模型 VGG16 Unet 改进Unet F1分数 0.924 0.933 0.943 Iou 0.859 0.874 0.893
下载: 导出CSV
表 4 常见交叉裂隙骨架分离结果
Table 4 Skeleton separation results of common intersection fractures
图像类别 裂隙骨架原图 重合追踪分析结果 断裂追踪分析结果 图像A（Y型） 
图像B（X型） 
图像C（双Y型） 
图像D（三角交叉型） 
下载: 导出CSV
-
[1] 张紫杉, 王述红, 王鹏宇, 等. 岩坡坡面裂隙网络智能识别与参数提取[J]. 岩土工程学报, 2021, 43(12): 2240-2248. doi: 10.11779/CJGE202112010 ZHANG Zishan, WANG Shuhong, WANG Pengyu, et al. Intelligent identification and extraction of geometric parameters for surface fracture networks of rocky slopes[J]. Chinese Journal of Geotechnical Engineering, 2021, 43(12): 2240-2248. (in Chinese) doi: 10.11779/CJGE202112010
[2] 李术才, 刘洪亮, 李利平, 等. 基于数码图像的掌子面岩体结构量化表征方法及工程应用[J]. 岩石力学与工程学报, 2017, 36(1): 1-9. https://www.cnki.com.cn/Article/CJFDTOTAL-YSLX201701001.htm LIU Shucai, LIU Hongliang, LI Liping, et al. A quantitative method for rock structure at working faces of tunnels based on digital images and its application[J]. Chinese Journal of Rock Mechanics and Engineering, 2017, 36(1): 1-9. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSLX201701001.htm
[3] LI Y H, TANG X J, ZHU H H. Optimization of the digital image correlation method for deformation measurement of geomaterials[J]. Acta Geotechnica, 2022, 17(12): 5721-5737. doi: 10.1007/s11440-022-01646-x
[4] 许文涛, 李晓昭, 章杨松, 等. 基于摄影测量系统的岩体结构面精细识别表征及应用[J]. 测绘学报, 2022, 51(10): 2093-2106. https://www.cnki.com.cn/Article/CJFDTOTAL-CHXB202210009.htm XU Wentao, LI Xiaozhao, ZHANG Yangsong, et al. Fine identification and characterization of rock mass discontinuities and its application using a digital photogrammetry system[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(10): 2093-2106. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-CHXB202210009.htm
[5] LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521(7553): 436-444. doi: 10.1038/nature14539
[6] LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, 2015: 3431-3440.
[7] 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 Hongwei, LI Qintong. 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
[8] ZHU H, AZARAFZA M, AKGUN H. Deep learning-based key-block classification framework for discontinuous rock slopes[J]. Journal of Rock Mechanics and Geotechnical Engineering, 2022, 14: 1131-1139. doi: 10.1016/j.jrmge.2022.06.007
[9] 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 Dongjie, TANG Qichun, 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
[10] 刘金杉, 李元海, 卢昱杰, 等. 基于深度学习的隧道衬砌表观病害模拟检测系统[J]. 哈尔滨工业大学学报, 2022, 54(5): 24-33. LIU Jinshan, LI Yuanhai, LU Yujie, et al. Tunnel lining surface defect simulation and detection system based on deep learning[J]. Journal of Harbin Institute of Technology, 2022, 54(5): 24-33. (in Chinese)
[11] SONG Q, WU Y, XIN X, et al. Real-time tunnel crack analysis system via deep learning[J]. IEEE Access, 2019, 7: 64186-64197. doi: 10.1109/ACCESS.2019.2916330
[12] XIANG X, ZHANG Y, EL SADDIK A. Pavement crack detection network based on pyramid structure and attention mechanism[J]. IET Image Processing, 2020, 14(8): 1580-1586. doi: 10.1049/iet-ipr.2019.0973
[13] 刘春, 王宝军, 施斌, 等. 基于数字图像识别的岩土体裂隙形态参数分析方法[J]. 岩土工程学报, 2008, 30(9): 1383-1388. doi: 10.3321/j.issn:1000-4548.2008.09.021 LIU Chun, WANG Bao-jun, SHI Bin, et al. Analytic method of morphological parameters of cracks for rock and soil based on image processing and recognition[J]. Chinese Journal of Geotechnical Engineering, 2008, 30(9): 1383-1388. (in Chinese) doi: 10.3321/j.issn:1000-4548.2008.09.021
[14] 王军祥, 曾相森, 徐晨晖, 等. 基于图像处理技术的岩体裂隙定量识别方法研究[J]. 地下空间与工程学报, 2022, 18(2): 446-457. https://www.cnki.com.cn/Article/CJFDTOTAL-BASE202202012.htm WANG Junxiang, ZENG Xiangsen, XU Chenhui, et al. Study on quantitative identification method of rock fracture based on image processing technology[J]. Chinese Journal of Underground Space and Engineering, 2022, 18(2): 446-457. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-BASE202202012.htm
-
其他相关附件
计量
- 文章访问数: 0
- HTML全文浏览量: 0
- PDF下载量: 0
