[1]伊小娟,罗威,李 伟,等.基于MaskR-CNN的地质雷达岩溶预报图像识别研究[J].高速铁路技术,2024,15(02):50-55.[doi:10.12098/j.issn.1674-8247.2024.02.009]
 YI Xiaojuan,LUO Wei,LI Wei,et al.Study on Karst Forecast Image Recognition with Geological Radar Based on Mask R-CNN[J].HIGH SPEED RAILWAY TECHNOLOGY,2024,15(02):50-55.[doi:10.12098/j.issn.1674-8247.2024.02.009]
点击复制

基于MaskR-CNN的地质雷达岩溶预报图像识别研究()
分享到:

《高速铁路技术》[ISSN:1674-8247/CN:51-1730/U]

卷:
15卷
期数:
2024年02期
页码:
50-55
栏目:
研究创新
出版日期:
2024-04-30

文章信息/Info

Title:
Study on Karst Forecast Image Recognition with Geological Radar Based on Mask R-CNN
文章编号:
1674-8247(2024)02-0050-06
作者:
伊小娟12罗威12李 伟1王志军1尹小康1
1.中铁二院工程集团有限责任公司, 成都610031;2.成都理工大学,成都 610000
Author(s):
YI Xiaojuan12LUO Wei12LI Wei1WANG Zhijun1YIN Xiaokang1
1.China Railway Eryuan Engineering Group Co. ,Ltd. ,Chengdu 610031 ,China;2.Chengdu University of Technology ,Chengdu 610000 ,China
关键词:
地质雷达Mask R-CNN岩溶空洞智能识别
Keywords:
geological radarMask R-CNNkarst cavitiesintelligent recognition
分类号:
U452.1+1
DOI:
10.12098/j.issn.1674-8247.2024.02.009
文献标志码:
A
摘要:
岩溶隧道开挖可能遭遇岩溶涌水、突泥等岩溶地质灾害,地质雷达能够有效预报岩溶等地质灾害。然而,传统地质雷达图像解译存在专家经验依赖性强、解译效率慢且易误判漏判等情况。本文采用可实现端到端识别的深度学习技术开展地质雷达图像目标检测与识别的研究,将基于MaskR-CNN的卷积神经网络算法应用于地质雷达岩溶预报图像异常的智能识别。在TensorFlow和Keras框架下,利用地质雷达设备采集获得的数据构建训练数据集和测试数据集,对MaskR-CNN深度学习模型进行训练,最终得到权重参数较好的地质雷达岩溶预报图像的双曲异常检测模型。试验结果及应用案例表明,MaskR-CNN目标检测方法在地质雷达岩溶预报图像的目标检测与识别上取得了良好的效果,有效提高了地质雷达图像的智能化识别效率。
Abstract:
Tunnel excavation in karst regions may encounter karst-related geological hazards such as sudden karst water bursts and mud flows. Geological radar is effective in forecasting such karstic and other geological events. However,traditional interpretation of geological radar images heavily relies on expert knowledge,is time-consuming,and is prone to misinterpretation or oversight. This paper explored the use of deep learning technology,specifically designed for end-to-end recognition,in the context of geological radar image object detection and identification. It applied the convolutional neural network algorithm based on Mask R-CNN for intelligent identification of anomalies in karst forecast images generated by geological radar. Under the TensorFlow and Keras frameworks,a training dataset and a test dataset were constructed using data acquired from geological radar. The Mask R-CNN deep learning model was trained on these datasets,ultimately yielding a robust model with better weight parameters for detecting hyperbolic anomalies in karst forecast geological radar images. Experimental results and case studies demonstrate that the Mask R-CNN object detection method achieves excellent performance in detecting and identifying targets within geological radar karst forecast images,significantly enhancing the efficiency of intelligent recognition for geological radar imagery.

参考文献/References:

[1] 李术才,刘斌,孙怀凤,等. 隧道施工超前地质预报研究现状及发展趋势[J]. 岩石力学与工程学报,2014,33(6):1090-1113. LI Shucai,LIU Bin,SUN Huaifeng,et al. State of Art and Trends of Advanced Geological Prediction in Tunnel Construction[J]. Chinese Journal of Rock Mechanics and Engineering,2014,33(6):1090-1113.
[2] 肖宽怀. 隧道超前预报地球物理方法及应用研究[D]. 成都:成都理工大学,2012. XIAO Kuanhuai. Tunnel Advanced Prediction Geophysical Method and Application Research[D]. Chengdu:Chengdu University of Technology,2012.
[3] 王凯,牟元存,李星. 综合超前预报技术在复杂地质隧道中的应用[J]. 高速铁路技术,2022,13(4):82-86. WANG Kai,MU Yuancun,LI Xing. Application of Comprehensive Prediction Technology in Tunnels with Complex Geological Conditions [J]. High Speed Railway Technology,2022,13(4):82-86.
[4] 钟明文,李文菊,房昱纬,等. 综合地质预报在公路隧道施工中的应用[J]. 勘察科学技术,2021(2):52-55. ZHONG Mingwen,LI Wenju,FANG Yuwei,et al. Application of Comprehensive Geological Forecast in Highway Tunnel Construction [J]. Site Investigation Science and Technology,2021(2):52-55.
[5] 温树林,吴世林. TSP203在云南元磨高速公路隧道超前地质预报中的应用[J]. 地球物理学进展,2003,18(3):465-471. WEN Shulin,WU Shilin. Application of the TSP203 System in Geological Advanced Prediction of Yuanmo Expressway Tunnel[J]. Progress In Geophysics,2003,18(3):465-471.
[6] 范佳俊. 地质雷达在地铁隧道超前地质预报中的应用研究[J].山西建筑,2017,43(2):191-193. FAN Jiajun. Study on GPR in Subway Tunnel Geological Forecast[J]. Shanxi Architecture,2017,43(2):191-193.
[7] 李俊均. 加林山隧道地质雷达超前预报准确性评判研究[J]. 广东交通职业技术学院学报,2017,16(3):42-47. LI Junjun. Evaluation of the Prediction Accuracy of the Jialinshan Tunnel Geological Radar[J]. Journal of Guangdong Communication Polytechnic,2017,16(3):42-47.
[8] 舒畅. 提高探地雷达超前地质预报精度的方法研究[J]. 铁道工程学报,2006,23(3):13-16,28. SHU Chang. Research on the Method of Improving the Precision of the GPR in Beforehand Geological Forecast[J]. Journal of Railway Engineering Society,2006,23(3):13-16,28.
[9] 马王鹏,王晓东,刘冬. 探地雷达图像异常识别中YOLO目标检测算法的研究[J]. 测绘通报,2019(S1):72-76. MA Wangpeng,WANG Xiaodong,LIU Dong. Research on YOLO Target Detection Algorithm in Ground Penetrating Radar Image Anomaly Recognition[J]. Bulletin of Surveying and Mapping, 2019(S1):72-76.
[10]冯德山,杨子龙. 基于深度学习的隧道衬砌结构物探地雷达图像自动识别[J]. 地球物理学进展,2020,35(4):1552-1556. FENG Deshan,YANG Zilong. Automatic Recognition of Ground Penetrating Radar Image of Tunnel Liningstructure Based on Deep Learning[J]. Progress in Geophysics,2020,35(4):1552-1556.
[11]HE Kaiming,GKIOXARI G,DOLLAR P,et al. Mask R-CNN[C]//2017 IEEE International Conference on Computer Vision (ICCV). Venice,Italy. IEEE,2017 :2980-2988.
[12]REN Shaoqing,HE Kaiming,GIRSHICK R,et al. Faster R-CNN:Towards Real-time Object Detection with Region Proposal Networks [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149.
[13]李大军,何维龙,郭丙轩,等. 基于Mask-RCNN的建筑物目标检测算法[J]. 测绘科学,2019,44(10):172-180. LI Dajun,HE Weilong,GUO Bingxuan,et al. Building Target Detection Algorithm Based on Mask-RCNN[J]. Science of Surveying and Mapping,2019,44(10):172-180.
[14]伍锡如,邱涛涛,王耀南. 改进Mask R-CNN的交通场景多目标快速检测与分割[J]. 仪器仪表学报,2021,42(7):242-249. WU Xiru,QIU Taotao,WANG Yaonan. Multi-object Detection and Segmentation for Traffic Scene Based on Improved Mask R-CNN[J]. Chinese Journal of Scientific Instrument,2021,42(7):242-249.
[15]向伟. 基于探地雷达城市地下空间图像的探测识别研究[D].长沙:湖南大学,2014. XIANG Wei. Detection and Recognition Research on Urban Underground Space Images Based on Ground Penetrating Radar[D]. Changsha:Hunan University,2014.
[16]林春旭. 基于探地雷达和深度学习的地下目标智能探测与定位方法[D]. 广州:广州大学,2020. LIN Chunxu. Automatic Detection and Localization of Underground Target by Deep Learning Using Ground Penetrating Radar[D]. Guangzhou:Guangzhou University,2020.
[17]温世儒,杨晓华,吴霞. 基于BP神经网络的探地雷达图像特征判识与提取研究[J]. 公路,2018,63(7):312-317. WEN Shiru,YANG Xiaohua,WU Xia. Research on Intelligent Identification and Extraction of GPR Image Property Based on BP Neural Network[J]. Highway,2018,63(7):312-317.
[18]李仁最. 基于Mask R-CNN的菜品图像识别和分割算法[D]. 武汉:武汉轻工大学,2019. LI Renzui. Image Recognition and Segmentation Algorithm Based on Mask R-CNN[D]. Wuhan:Wuhan Polytechnic University,2019.
[19]张云帅. 基于Mask R-CNN改进的图像实例分割算法研究[D].西安:西安电子科技大学,2021. ZHANG Yunshuai. Improved Image Instance Segmentation Algorithm Based on Mask R-CNN[D]. Xi’an:Xidian University,2021.[20]谢文博. 基于改进Mask R-CNN的木材缺陷检测分割算法研究[D]. 哈尔滨:哈尔滨理工大学,2022. XIE Wenbo. Research of Improved Mask R-CNN-Based Detection Segmentation Algorithm for Wood Defects[D]. Harbin: Harbin University of Science and Technology,2022.

相似文献/References:

[1]刘伟,周超,金俊俊.不同地质雷达设备在铁路工程隐伏岩溶探测中的应用与对比[J].高速铁路技术,2024,15(04):82.[doi:10.12098/j.issn.1674-8247.2024.04.015]
 LIU Wei,ZHOU Chao,JIN Junjun.Application and Comparison of Different Ground Penetrating Radar Systems in the Detection of Concealed Karst in Railway Engineering[J].HIGH SPEED RAILWAY TECHNOLOGY,2024,15(02):82.[doi:10.12098/j.issn.1674-8247.2024.04.015]

备注/Memo

备注/Memo:
收稿日期:2023-10-08
作者简介:伊小娟(1985-),女,高级工程师。
更新日期/Last Update: 2024-04-30