| 130 | 3 | 64 |
| Downloads | Citas | Reads |
Aiming at the problem of large positioning error of existing methods for underground pipelines on airport pavement, a three-dimensional positioning algorithm for underground pipelines on airport pavements was proposed. Firstly, the B-scan image of the pipeline formed by the ground penetrating radar was preprocessed, the processed image was input into the Faster-RCNN network, and the pipeline in the B-scan image was identified. Secondly, since the pipeline target conformed to the hyperbolic morphological characteristics, the hyperbolic vertex acquisition algorithm was used to determine the vertex position. Finally, the three-dimensional space line fitting(TDSLF) algorithm was designed to determine the specific location of the underground pipeline and carried out the three-dimensional reconstruction of the underground pipeline. The proposed algorithm realized the automatic identification and the positioning of underground pipelines, and the maximum error with the actual position of the pipeline under the real airport pavement was only 4 cm.
[1] 陈思静，胡祥云，彭荣华.城市地下管线探测研究进展与发展趋势[J].地球物理学进展，2021,36(3):1236-1247.CHEN S J,HU X Y,PENG R H.Review of urban underground pipeline detection[J].Progress in geophysics,2021,36(3):1236-1247.
[2] 廉飞宇，李青.探地雷达图中地下管径尺寸的SVM识别方法[J].信息与电子工程，2011,9(4):403-408.LIAN F Y,LI Q.Recognition method based on SVM for underground pipe diameter size in GPR map[J].Information and electronic engineering,2011,9(4):403-408.
[3] 胡浩帮，方宏远，王复明，等.基于Faster R-CNN算法的探地雷达管线目标智能识别[J].城市勘测，2020(3):203-208.HU H B,FANG H Y,WANG F M,et al.Intelligent recognition of pipeline target based on Faster R-CNN algorithm for ground penetrating radar[J].Urban geotechnical investigation & surveying,2020(3):203-208.
[4] REN S Q,HE K M,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.
[5] GIRSHICK R.Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision.Piscataway:IEEE Press,2015:1440-1448.
[6] LEI W T,HOU F F,XI J C,et al.Automatic hyperbola detection and fitting in GPR B-scan image[J].Automation in construction,2019,106:102839.
[7] LIU Z W,ZHANG Z Y,GAO Y Y,et al.Using adaptive cross approximation to accelerate simulation of B-scan GPR for detecting underground pipes[EB/OL].[2021-09-12].https://www.researchgate.net/publication/310456507.
[8] DINH K,GUCUNSKI N,DUONG T H.An algorithm for automatic localization and detection of rebars from GPR data of concrete bridge decks[J].Automation in construction,2018,89:292-298.
[9] 侯斐斐，施荣华，雷文太，等.面向探地雷达B-scan图像的目标检测算法综述[J].电子与信息学报，2020,42(1):191-200.HOU F F,SHI R H,LEI W T,et al.A review of target detection algorithm for GPR B-scan processing[J].Journal of electronics & information technology,2020,42(1):191-200.
[10] 钟羽中，吴仁彪，刘家学.基于GPR的机场跑道钢筋回波检测与抑制[J].信号处理，2011,27(10):1509-1514.ZHONG Y Z,WU R B,LIU J X.Rebar echo detection and suppression in runway using GPR[J].Signal processing,2011,27(10):1509-1514.
[11] 马雷，田中旭，邸义.地下管线检测中的曲线重构算法[J].机床与液压，2006,34(11):13-15.MA L,TIAN Z X,DI Y.An algorithm for curve reconstruction on underground pipeline detection[J].Machine tool & hydraulics,2006,34(11):13-15.
[12] 夏锋，黄廷磊，刘邵华.地下管线探测回波中目标双曲线的快速拟合方法[J].计算机系统应用，2013,22(5):85-89.XIA F,HUANG T L,LIU S H.A rapid method of fitting out targets hyperbola of underground pipeline prospecting image[J].Computer systems & applications,2013,22(5):85-89.
[13] 吴勤伟.三维探地雷达在地下金属管线定位探测中的应用研究[J].世界有色金属，2020(15):215-216.WU Q W.Application of 3D ground penetrating radar in location detection of underground metal pipelines[J].World nonferrous metals,2020(15):215-216.
[14] 杨军，张华，冯德山，等.GPR探测中管线异常自动提取与识别[J].地球物理学进展，2021,36(3):1333-1340.YANG J,ZHANG H,FENG D S,et al.Automatic extraction and recognition of anomalies in GPR pipeline detection[J].Progress in geophysics,2021,36(3):1333-1340.
[15] 李策，徐频捷，徐昕军，等.基于深度卷积神经网络的雷达信号铁路路基病害检测方法：CN107621626A[P].2018-01-23.LI C,XU P J,XU X J,et al.Radar signal railway roadbed disease detection method based on radar signal of deep convolution neural network:CN107621626A[P].2018-01-23.
[16] PARK J,YUN J,KIM N,et al.Fully automated lung lobe segmentation in volumetric chest CT with 3D U-net:validation with intra- and extra-datasets[J].Journal of digital imaging,2020,33(1):221-230.
[17] POLAT H,DANAEI M H.Classification of pulmonary CT images by using hybrid 3D-deep convolutional neural network architecture[J].Applied sciences,2019,9(5):940.
[18] 张丽，李潇，吴皓天，等.基于最大类间方差的图像分割算法研究[J].科技创新与应用，2021(8):39-41,46.ZHANG L,LI X,WU H T,et al.Research on image segmentation algorithm based on maximum between-class variance[J].Technology innovation and application,2021(8):39-41,46.
Basic Information:
DOI：10.13705/j.issn.1671-6841.2021473
China Classification Code:V351;TP391.41
Citation Information:
[1]LI Haifeng,LUO Yufei,WANG Huaichao ,et al.Three-dimensional Positioning Algorithm for Underground Pipelines on Airport Pavement[J].Journal of Zhengzhou University(Natural Science Edition),2023,55(02):57-62.DOI:10.13705/j.issn.1671-6841.2021473.
Fund Information:
国家重点研发课题计划项目(2019YFB1310601)
2022-06-07
2022-06-07
2022-06-07