Pipeline Damage Depth Estimation and 3D Reconstruction Based on Boosting-Monodepth Algorithm
CSTR:
Author:
Affiliation:

1.Yellow River Laboratory, Zhengzhou University, Zhengzhou 450001, China;2.Shanghai Institute of Disaster Prevention and Relief, Shanghai 200092, China;3.Key Laboratory of Urban Safety Risk Monitoring and Early Warning of the Ministry of Emergency Management, Shanghai 200092, China;4.Beijing Beipai Construction Co., Ltd., Beijing 100071, China;5.Shenzhen Bomingwei Technology Co., Ltd., Shenzhen 518000, China

Clc Number:

U178

  • Article
  • | |
  • Metrics
  • |
  • Reference [28]
  • |
  • Related [20]
  • | | |
  • Comments
    Abstract:

    Urban underground pipelines are the blood channels of the city. However, with the large number of drainage pipelines put into operation and their service life increasing, a series of hidden dangers of pipeline diseases have arisen, such as the overall structural deformation of the pipeline, internal surface cracking, and the insertion of foreign matters in the pipeline. Traditional disease image video capture, detection, and later disease classification and selection are conducted from a two-dimensional(2D) perspective, lacking consideration of three-dimensional spatial information (depth). Aimed at the above three diseases, an experiment is conducted from generating depth maps and reconstructing three-dimensional(3D) pipeline diseases from 2D depth maps. A dual depth estimation method based on boosting-monodepth is proposed to improve the effect of depth maps, and finally a depth map with continuous and consistent images and clear outlines is generated. In terms of performance evaluation, Abs-Rel, RMSE, SqRel, ORD, D3R and other general indexes are compared with those of the traditional algorithm, and the results show that the boosting-monodepth is reduced by 30% at RMSE and increased by 18% at a threshold of δ< 1.25. Afterwards, the 3D point cloud of pipeline disease is reconstructed based on the depth map obtained, and 3D visualization is performed on CloudCompare. Finally, the disease depth is calculated using the random sampling consistent algorithm and compared with the real measured data to prove its effectiveness and accuracy.

    Reference
    [1] BAAH K, DUBEY B, HARVEY R, et al. A risk-based approach to sanitary sewer pipe asset management[J]. Science of the Total Environment, 2015, 505: 1011.
    [2] LI Linyi, YANG Junsheng, GAO Chao, et al. Simulation tests on structural deformation and seepage field of high-speed railway tunnels under drainage clogging[J]. Chinese Journal of Geotechnical Engineering, 2021, 43(4): 715.
    [3] CAO Jingguo. Engineering demonstration of cured in place pipe repair material for urban drainage canals[J]. Water & Wastewater Engineering, 2020, 46(1): 115.
    [4] 车毅峰. 城市排洪管道对城市应急系统的影响[J]. 四川水泥, 2017 (12): 288.CHE Yifeng. Influence of urban flood discharge pipeline on urban emergency system [J]. Sichuan Cement, 2017 (12): 288.
    [5] ANBARI M J, TABESH M, ROOZBAHANI A. Risk assessment model to prioritize sewer pipes inspection in wastewater collection networks[J]. Journal of Environmental Management, 2017, 190: 91.
    [6] 金惠玲,孙振平,杨海静,等.排水管道非开挖修复技术的应用现状及展望[J].混凝土世界, 2022(9):82.JIN Huiling, SUN Zhenping, YANG Haijing, et al. Application status and prospect of trenchless repair technology for drainage pipes [J]. Concrete World, 2022(9):82.
    [7] QIN Chaokui, LI Jun, YanMingjun, et al. Analysis of failure probability of urban underground gas pipelines under corrosion effect[J]. Natural Gas Industry 2015,35(5):85.
    [8] YANG Lijian, SHEN Bo, GAO Songwei. Method of pipeline geographic measurement applied to pipeline inspection Gauge[J]. Instrument Technique and Sensor, 2013(11):84.
    [9] HUANG J, LEUNG K E, VERCELES R, et al. Automated detection of sewer pipe structural defects using machine learning[C]//WEFTEC 2017. [s.l.]: Water Environment Federation, 2017: 4605-4615.
    [10] 俞树荣, 何娜, 顾生斌. 基于成本的长输管道腐蚀缺陷检测及维修规划[J]. 煤气与热力, 2010, 30(5): 21.YU Shurong, HE Na, GU Shengbin. Cost based inspection and maintenance planning for corrosion defects of long-distance pipeline [J]. Gas & Heat, 2010, 30(5): 21.
    [11] 徐小云, 颜国正, 鄢波. 一种新型管道检测机器人系统[J]. 上海交通大学学报, 2004, 38(8): 1324.XU Xiaoyun, YAN Guozheng, YAN Bo. A new style pipeline inspection robot system[J]. Journal of Shanghai Jiaotong University, 2004, 38(8): 1324.
    [12] YE Wenwei, ZHOU Tianfu, HUANG Jinxuan, et al. Design of dual-vision double telecentric optical system based on machine vision[J]. Laser & Optoelectronics Progress, 2020, 57(1): 012202.
    [13] LIU Yan, WANG Gang, WANG Guodong, et al. For machine vision image acquisition and image processing of weld[J]. Computer Engineering and Applications, 2014, 2014(5):135.
    [14] WANG Weidong, ZHANG Kanghui, LI Ziqi, et al. Machine vision detection of foreign objects in coal using deep learning[J]. Journal of Mining Science and Technology, 2021, 6(1): 115.
    [15] 李康. 基于机器视觉的管道内表面缺陷检测方法研究[D]. 包头:内蒙古科技大学, 2019.LI Kang. Research on detection method of inner surface defects of pipeline based on machine vision [D]. Baotou: Inner Mongolia University of Science & Technology, 2019.
    [16] 李耀宇, 王宏民, 张一帆, 等. 基于结构化深度学习的单目图像深度估计[J]. 机器人, 2017, 39(6): 812.LI Yaoyu, WANG Hongmin, ZHANG Yifan, et al. Structured deep learning based depth estimation from a monocular image[J]. Robot, 2017,39(6): 812.
    [17] 曾一鸣, 胡瑜, 韩银和, 等. 利用稀疏点云偏序关系的半监督单目图像深度估计[J]. 计算机辅助设计与图形学学报, 2019, 31(11): 2038.ZENG Yiming, HU Yu, HAN Yinhe, et al. Exploiting partial order relationship of sparse point cloud for semi-supervised monocular image depth estimation[J]. Journal of Computer-Aided Design & Computer Graphics, 2019, 31(11): 2038.
    [18] SNAVELY N. Scene reconstruction and visualization from internet photo collections: A survey[J]. IPSJ Transactions on Computer Vision and Applications, 2011, 3: 44.
    [19] YUAN Hongxing, WU Shaoqun, YU Huiqing, et al. A 2D-to-3D method via semantic depth transfer[J]. Journal of Computer-Aided Design & Computer Graphics, 2014, 26(1): 72.
    [20] 刘芳, 刘东升, 桂志国. 基于马尔科夫随机场的图像锐化方法[J]. 计算机工程, 2011, 37(1): 224.LIU Fang, LIU Dongsheng, GUI Zhiguo. Image sharpening method based on markov random field[J]. Computer Engineering, 2011, 37(1): 224.
    [21] 程婷婷, 郭立君, 黄元捷. 基于鲁棒高阶条件随机场的视频自动分割[J]. 计算机工程, 2015, 41(7): 261.CHENG Tingting, GUO Lijun, HUANG Yuanjie. Automatic video segmentation based on robust higher order conditional random field[J]. Computer Engineering, 2015, 41(7): 261.
    [22] 吴恩启. 微细管道内表面检测及三维重建关键技术研究[D]. 杭州: 浙江大学, 2005.WU Enqi. Research on key technologies of inner surface detection and 3D reconstruction of micro-pipe [D]. Hangzhou: Zhejiang University, 2005.
    [23] 叶晶, 周常河, 贾伟. 小型管道内壁三维成像测量系统[J]. 中国激光, 2010, 37(8): 2025.YE Jing, ZHOU Changhe, JIA Wei. Small pipe inner wall three-dimensional imaging measurement system[J]. Chinese Journal of Lasers, 2010, 37(8): 2025.
    [24] 盛沙, 戴波, 谢祖荣. 管道超声内检测三维成像技术研究[J]. 北京石油化工学院学报, 2012, 20(1): 1.SHENG Sha, DAI Bo, XIE Zurong. Research on 3D imaging technology for ultrasonic internal inspection of pipeline [J]. Journal of Beijing Institute of Petrochemical Technology, 2012, 20(1): 1.
    [25] CHAE M J, KIM W, HWANG H K. Digital pipeline image scanning and intelligent data management for sewer pipelines[C]// International Pipelines Conference. Atlanta: [S.n.]: 2008: 1046-1056.
    [26] 甘小明, 徐滨士, 张旭明, 等. 基于微型CCD的管道缺陷检测系统[J]. 机械工程师, 2004 (1): 77.GAN Xiaoming, XU Binshi, ZHANG Xuming, et al. Pipeline defect detection system based on micro CCD [J]. Mechanical Engineer, 2004 (1): 77.
    [27] MORALEDA J, OLLERO A, ORTE M. A robotic system for internal inspection of water pipelines[J]. IEEE Robotics & Automation Magazine, 1999, 6(3): 30.
    [28] ZHOU T, BROWN M, SNAVELY N, et al. Unsupervised learning of depth and ego-motion from video[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Hawaii: IEEE, 2017: 1851-1858.
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation

FANG Hongyuan, JIANG Xue, WANG Niannian, HU Qunfang, LEI Jianwei, WANG Fei, ZHAO Jicheng, DAI Yi. Pipeline Damage Depth Estimation and 3D Reconstruction Based on Boosting-Monodepth Algorithm[J].同济大学学报(自然科学版),2023,51(2):161~169

Copy
Share
Article Metrics
  • Abstract:268
  • PDF: 686
  • HTML: 938
  • Cited by: 0
History
  • Received:November 24,2022
  • Online: March 03,2023
Article QR Code