+高级检索
首页 > 过刊浏览>2024年第47卷第10期 >191-204. DOI:10.11835/j.issn.1000.582X.2024.10.015
PDF HTML阅读 XML下载 导出引用 引用提醒
基于机器学习的石窟顶板裂隙热红外识别
作者:
作者单位:

1.1a长安大学，公路学院，西安 710064;2.1b长安大学，西安市绿色智慧交通岩土工程重点实验室，西安 710064;3.中国科学院地理科学与资源研究所 资源与环境信息系统国家重点实验室，北京 100101;4.中国文化遗产研究院，北京 100029

作者简介:

李昌波（2000—），男，研究生，主要从事岩体结构智能识别方向研究，(E-mail)lcblcb564@outlook.com。

通讯作者:

包含，男，教授，(E-mail) baohan@chd.edu.cn。

基金项目:

国家自然科学基金（42177142，42041006）；中央高校基本科研业务费（300102212213）。


Machine-learning-based thermal infrared recognition of fractures in grotto roofs
Author:
Affiliation:

1.1aSchool of Highway, Chang’an University, Xi’an710064, P. R. China;2.1bXi’an Key Laboratory of Geotechnical Engineering for Green and Intelligent Transport, Chang’an University, Xi’an710064, P. R. China;3.State Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, CAS, Beijing100101, P. R. China;4.China Academy of Cultural Heritage, Beijing100029, P. R. China

Fund Project:

Supported by National Natural Science Foundation of China(42177142, 42041006), and the Fundamental Research Funds for the Central Universities(300102212213).

  • 摘要
    • | |
  • 访问统计
    • |
  • 参考文献 [35]
    • |
  • 相似文献 [20]
    • | | |
  • 文章评论
    摘要:

    石窟顶板层状岩体中发育的裂隙相互交切，极易引发石窟岩体的失稳破坏，对其快速精准识别是石窟保护的重要基础。针对石窟顶板岩体裂隙的非接触精准测量需求，结合热红外探测技术和改进的UNet网络模型，对顶板裂隙网络二值图进行提取，并运用聚类算法，完成了裂隙网络二值图分割识别以及裂隙分组。结果表明，该网络模型各项性能相较于其他网络模型有所提高，Dice系数和推理速度分别达到了71.63%和0.84帧/s，识别过程抵抗人工结构物影响的能力较强，凸显该方法推理速度快，提取精度高、热红外图像适用性好等特点。以安岳圆觉洞顶板为例，应用该方法共分割识别出153条裂隙，并确定了NW327°和NE55°是顶板裂隙的优势走向，与其他测量方法相比识别效果更好。

    Abstract:

    The cracks developed in the layered rock mass of grotto roofs intersect with each other, which can easily cause instability and failure of the cave rock mass. Rapid and precise fracture identification is crucial for grotto protection. To meet the need for non-contact, precise fracture measurement, this study integrates thermal infrared detection technology with an improved UNet network model to extract binary maps of roof fracture networks. Clustering algorithms are employed for segmentation and recognition, achieving a Dice coefficients of 71.63% and a detection speed of 0.84 frames/s. The method exhibits high extraction efficiency, accuracy, good applicability of thermal infrared images and resilience against artificial structure influence. Applied to the roof of Anyue Yuanjue Grotto, this method successfully identified 153 fractures and reveals dominant fracture trends at NW327° and NE55°, outperforming other measurement techniques.

    参考文献
    [1] 兰恒星, 吕洪涛, 包含, 等. 石窟寺岩体劣化机制与失稳机理研究进展[J]. 地球科学, 2023, 48(4): 1603-1633.Lan H X, Lyu H T, Bao H, et al. Advances in degradation and instability mechanism of grotto temple rock mass[J]. Earth Science, 2023, 48(4): 1603-1633.(in Chinese)
    [2] 裴强强, 刘鸿, 崔惠萍, 等. 北石窟寺平顶窟顶板稳定性评价与黏结补强有效性研究[J]. 岩土力学, 2023, 44(S1): 561-571.Pei Q Q, Liu H, Cui H P, et al. Stability evaluation of the roof of the flat-roof caves and the analysis of the effectiveness of bonding and reinforcement in North Grottoes[J]. Rock and Soil Mechanics, 2023, 44(S1): 561-571.(in Chinese)
    [3] Lan H X, Zhang Y X, Macciotta R, et al. The role of discontinuities in the susceptibility, development, and runout of rock avalanches: a review[J]. Landslides, 2022, 19(6): 1391-1404.
    [4] 孟志刚. 圆觉洞石窟顶板变形机理及控制对策研究[D]. 北京: 中国矿业大学(北京), 2021.Meng Z G. Study on deformation mechanism and control countermeasures of roof in Yuanjue Cave[D]. Beijing: China University of Mining & Technology (Beijing), 2021. (in Chinese)
    [5] 白玉书, 裴强强, 刘鸿, 等. 砂岩石窟顶板微小型锚杆倒置锚固方法与性能研究[J]. 岩石力学与工程学报, 2023, 42(12): 3031-3042.Bai Y S, Pei Q Q, Liu H, et al. Study on inverted anchorage method and performance of microminiature bolts in sandstone grotto roof[J]. Chinese Journal of Rock Mechanics and Engineering, 2023, 42(12): 3031-3042.(in Chinese)
    [6] 宣程强, 章杨松, 许文涛. 基于数字表面模型的岩体结构面产状获取[J]. 水文地质工程地质, 2022, 49(1): 75-83.Xuan C Q, Zhang Y S, Xu W T. Extraction of the discontinuity orientation from a digital surface model[J]. Hydrogeology & Engineering Geology, 2022, 49(1): 75-83.(in Chinese)
    [7] Bao H, Liu C Q, Lan H X, et al. Time-dependency deterioration of polypropylene fiber reinforced soil and guar gum mixed soil in loess cut-slope protecting[J]. Engineering Geology, 2022, 311: 106895.
    [8] 朱合华, 潘柄屹, 武威, 等. 岩体结构面信息采集及识别方法研究进展[J]. 应用基础与工程科学学报, 2023, 31(6): 1339-1360.Zhu H H, Pan B Y, Wu W, et al. Review on collection and extraction methods of rock mass discontinuity information[J]. Journal of Basic Science and Engineering, 2023, 31(6): 1339-1360.(in Chinese)
    [9] Ge Y F, Chen Q, Tang H M, et al. A semi-automatic approach to quantifying the geological strength index using terrestrial laser scanning[J]. Rock Mechanics and Rock Engineering, 2023, 56(9): 6559-6579.
    [10] 吕洪涛, 包含, 兰恒星, 等. 基于热红外响应的岩体单裂隙埋藏深度探测方法[J]. 地球科学与环境学报, 2022, 44(6): 1048-1065.Lyu H T, Bao H, Lan H X, et al. Detection method of buried depth of single crack in rock mass based on thermal infrared response[J]. Journal of Earth Sciences and Environment, 2022, 44(6): 1048-1065.(in Chinese)
    [11] Jaiswal M, Sebastian R, Mulaveesala R. Thermal monitoring and deep learning approach for early warning prediction of rock burst in underground structures[J]. Journal of Physics D: Applied Physics, 2024, 57(10): 105502.
    [12] Fiorucci M, Marmoni G M, Martino S, et al. Thermal response of jointed rock masses inferred from infrared thermographic surveying (acuto test-site, Italy)[J]. Sensors, 2018, 18(7): 2221.
    [13] Pappalardo G, Mineo S, Zampelli S P, et al. InfraRed thermography proposed for the estimation of the Cooling Rate Index in the remote survey of rock masses[J]. International Journal of Rock Mechanics and Mining Sciences, 2016, 83: 182-196.
    [14] 刘丹, 朱鸿泰, 程虎, 等. 基于双引导滤波的红外和可见光图像融合算法[J]. 激光与红外, 2023, 53(11): 1778-1784.Liu D, Zhu H T, Cheng H, et al. Infrared and visible image fusion algorithm based on dual-guided filter[J]. Laser & Infrared, 2023, 53(11): 1778-1784.(in Chinese)
    [15] Mineo S, Caliò D, Pappalardo G. UAV-based photogrammetry and infrared thermography applied to rock mass survey for geomechanical purposes[J]. Remote Sensing, 2022, 14(3): 473.
    [16] Caliò D, Mineo S, Pappalardo G. Digital rock mass analysis for the evaluation of rockfall magnitude at poorly accessible cliffs[J]. Remote Sensing, 2023, 15(6): 1515.
    [17] 陈国庆, 潘元贵, 张国政, 等. 节理岩桥裂纹扩展的热红外前兆信息研究[J]. 岩土工程学报, 2019, 41(10): 1817-1826.Chen G Q, Pan Y G, Zhang G Z, et al. Thermal infrared precursor information of crack propagation for rock bridges[J]. Chinese Journal of Geotechnical Engineering, 2019, 41(10): 1817-1826.(in Chinese)
    [18] 哈纳提·吐尔森哈力, 林杭. 融合自注意力机制与深度学习的混凝土表面裂隙智能识别[J]. 铁道科学与工程学报, 2021, 18(04): 844-852.Hanat T, Liu H. Intelligent identification of cracks on concrete surface combining self-attention mechanism and deep learning[J]. Journal of Railway Science and Engineering, 2021, 18(04): 844-852. (in Chinese)
    [19] 李轶惠, 许振浩, 潘东东, 等. 基于数字图像的隧道岩体裂隙智能识别与参数提取方法[J]. 应用基础与工程科学学报, 2023, 31(6): 1427-1443.Li Y H, Xu Z H, Pan D D, et al. An intelligent identification and parameter extraction method for rockfractures based on digital images[J]. Journal of Basic Science and Engineering, 2023, 31(6): 1427-1443.(in Chinese)
    [20] Chen J Y, Zhou M L, Huang H W, et al. Automated extraction and evaluation of fracture trace maps from rock tunnel face images via deep learning[J]. International Journal of Rock Mechanics and Mining Sciences, 2021, 142: 104745.
    [21] 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.Zhang Z S, Wang S H, Wang P Y, 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)
    [22] 张农, 袁钰鑫, 韩昌良, 等. 基于Mask R-CNN的煤矿巷道掘进迎头裂隙检测与定位算法[J]. 采矿与安全工程学报, 2023, 40(5): 925-932.Zhang N, Yuan Y X, Han C L, et al. Research on crack detection and localization algorithm for advancing face in coalmine roadways based on Mask R-CNN[J]. Journal of Mining & Safety Engineering, 2023, 40(5): 925-932.(in Chinese)
    [23] 刘世杰, 兰恒星, 包含, 等. 石窟寺典型工程地质变形破坏模式及分类体系[J]. 地球科学, 2022, 47(12): 4710-4723.Liu S J, Lan H X, Bao H, et al. Classification system of typical engineering geological deformation and failure modes in grottoes[J]. Earth Science, 2022, 47(12): 4710-4723.(in Chinese)
    [24] 刘长青, 包含, 兰恒星, 等. 石窟寺多尺度岩体结构发育特征与三维精细化建模方法研究—以安岳圆觉洞为例[J]. 工程地质学报, 2023: 1-12.Liu C Q, Bao H, Lan H X, et al. Multi-scale rock structures development characteristics and 3D refinement modeling method of grottoes: a case study of Anyue Yuanjue Cave[J]. Journal of Engineering Geology, 2023: 1-12. (in Chinese)
    [25] Hu J, Wang M Y, Rong X L, et al. Influences of joint persistence on the compressive-shear and tensile-shear failure behavior of jointed rock mass: an experimental and numerical study[J]. Rock Mechanics and Rock Engineering, 2023, 56(11): 8151-8165.
    [26] Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation[M]//Lecture Notes in Computer Science. Cham: Springer International Publishing, 2015: 234-241.
    [27] He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, USA: IEEE, 2016: 770-778.
    [28] Guo M H, Xu T X, Liu J J, et al. Attention mechanisms in computer vision: a survey[J]. Computational Visual Media, 2022, 8(3): 331-368.
    [29] Niu Z Y, Zhong G Q, Yu H. A review on the attention mechanism of deep learning[J]. Neurocomputing, 2021, 452: 48-62.
    [30] Wang X L, Girshick R, Gupta A, et al. Non-local neural networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: IEEE, 2018: 7794-7803.
    [31] Zhao R J, Qian B Y, Zhang X L, et al. Rethinking dice loss for medical image segmentation[C]//2020 IEEE International Conference on Data Mining (ICDM). Sorrento, Italy: IEEE, 2020: 851-860.
    [32] 张平, 佟昆宏, 王学珍. 基于改进U-net网络的液压管路分割方法[J]. 电子测量与仪器学报, 2023, 37(1): 123-129.Zhang P, Tong K H, Wang X Z. Hydraulic pipeline segmentation method based on improved U-net network[J]. Journal of Electronic Measurement and Instrumentation, 2023, 37(1): 123-129.(in Chinese)
    [33] Zhang P Y, Ma Q M. Brain tumor segmentation algorithm based on asymmetric encoder and multimodal cross-collaboration[J]. International Journal of Advanced Computer Science and Applications, 2023, 14(11): 943-953.
    [34] Zhou L C, Zhang C, Wu M. D-LinkNet: LinkNet with pretrained encoder and dilated convolution for high resolution satellite imagery road extraction[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Salt Lake City, USA: IEEE, 2018: 192-1924.
    [35] Li M, Xu D C, Zhang D M, et al. The seeding algorithms for spherical k-means clustering[J]. Journal of Global Optimization, 2020, 76(4): 695-708.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

李昌波,包含,兰恒星,李黎,陈卫昌,刘长青,吕洪涛.基于机器学习的石窟顶板裂隙热红外识别[J].重庆大学学报,2024,47(10):191-204.

复制
分享
文章指标
  • 点击次数:809
  • 下载次数: 157
  • HTML阅读次数: 92
  • 引用次数: 0
历史
  • 收稿日期:2024-01-10
  • 在线发布日期: 2024-11-14
文章二维码
您是第11254407 位访问者
主管单位：中华人民共和国教育部
主办单位：重庆大学
地址：重庆市沙坪坝正街174号
电话：
重庆大学学报 ® 2025 版权所有