BIM modeling of oil pipeline based on RGB-D depth image and LiDAR point cloud

doi:10.13474/j.cnki.11-2246.2022.0270

Abstract

Abstract: Building information modeling (BIM) has been widely used to improve the management efficiency of complex pipeline systems. However, BIM modeling of existing oil pipelines often relies on design drawings or field mapping, which is time-consuming and laborious. Therefore, a BIM reconstruction method for oil pipeline based on RGB-D depth image and LiDAR point cloud data is proposed. Based on the rich semantic information provided by RGB-D image and the precise geometric information of LiDAR point cloud, the RGB image collected by depth camera is segmced to generate 3D semantic map. Then data fusion is realized by point cloud rough matching and precise matching. Finally, the BIM model making method of different structure pipeline components is given. The experimental results show that compared with the previous BIM reconstruction methods of pipelines, this method is more accurate and efficient, which is helpful for petroleum enterprises to implement information management for the metering and transfer stations containing complex pipelines.

Key words: RGB-D, LiDAR point cloud, oil pipeline, BIM

CLC Number:

P237

NIU Pengtao, CAO Yi, QIAO Wenbin. BIM modeling of oil pipeline based on RGB-D depth image and LiDAR point cloud[J]. Bulletin of Surveying and Mapping, 2022, 0(9): 93-97,157.

References

[1] 张刘军, 韩永波, 田娜. 长输管道完整性管理信息系统建设现状及发展方向[J]. 石油化工自动化, 2020, 56(4):58-61.
[2] 贾迪, 王子滔, 李宇扬, 等. 结合LiDAR与RGB数据构建稠密深度图的多阶段指导网络[J]. 中国图象图形学报, 2022, 27(2):435-446.
[3] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural network[C]//Proceedings of the 28th International Conference on NeuralInformation Processing Systems. Cambridge:MIT Press,2015:91-99.
[4] 范军林, 肖斌, 涂梨平, 等. RGB-D SLAM在室内高精度三维测图中的应用[J]. 测绘通报, 2021(8):119-122.
[5] CHARLES R Q, HAO Su, MO Kaichun, et al. PointNet:deep learning on point sets for 3D classification and segmentation[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu:IEEE, 2017:77-85.
[6] 付燕平, 严庆安, 廖杰, 等. 基于彩色图像引导的RGB-D相机追踪与三维重建[J]. 武汉大学学报(工学版), 2022, 55(1):92-100.
[7] BADRINARAYANAN V,KENDALL A,CIPOLLA R.SegNet:a deep convolutional encoder-decoder architecture for image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(12):2481-2495.
[8] MEI Shaohui, GENG Yunhao, HOU Junhui, et al. Learning hyperspectral images from RGB images via a coarse-to-fine CNN[J]. Science China Information Sciences, 2022, 65(5):152102.
[9] WANG Boyu, WANG Qian, CHENG J C P, et al. Vision-assisted BIM reconstruction from 3D LiDAR point clouds for MEP scenes[J]. Automation in Construction, 2022, 133:103997.
[10] 洪运志, 吴怀宇, 陈志环. 室内环境下深度相机V-SLAM的稠密建图[J]. 计算机工程与设计, 2020, 41(9):2552-2558.
[11] 张爱武, 宫辉力, Jiaguo QI, 等. 移动激光雷达的瞬时三维构像方法[J]. 测绘学报, 2018, 47(6):741-747.
[12] 屈航,嵇启春,段中兴.改进Deeplab V3+网络在视觉SLAM三维地图构建应用[J/OL].小型微型计算机系统.[2022-01-04].http://kns.cnki.net/kcms/detail/21.1106.TP.20210818.1048.026.html.
[13] 王玮琦, 游雄, 杨剑, 等. 一种改进匹配点对选取策略的ElasticFusion室内三维重建算法[J]. 武汉大学学报(信息科学版),2020, 45(9):1469-1477.
[14] 王佳文, 李彩林, 王志勇, 等. 影像数量对SFM三维重建模型测量精度的影响分析[J]. 激光杂志, 2021, 42(3):63-69.
[15] 闫利, 任大伟, 谢洪, 等. 一种激光点云与密集匹配点云融合方法[J/OL]. 中国激光, 2021:1-18[2021-11-12]. https://kns.cnki.net/kcms/detail/31.1339.tn.20211110.0939.018.html.
[16] 苏云龙, 平雪良, 李楠. 基于RANSAC三维点云的平面提取算法[J]. 激光与红外, 2019, 49(6):780-784.
[17] WANG Yanjun, LI Shaochun, WANG Mengjie, et al. A simple deep learning network for classification of 3D mobile LiDAR point clouds[J]. Journal of Geodesy and Geoinformation Science, 2021(3):49-59.
[18] 陈岳飞, 肖珍芳, 方向. 数字孪生技术及其在石油化工行业的应用[J]. 天然气化工(C1化学与化工), 2021, 46(2):25-30.
[19] YOON H, JANG M, HUH J, et al. Multiple sensor synchronization with the real sense RGB-D camera[J]. Sensors (Basel, Switzerland), 2021, 21(18):6276.
[20] JIA Jingyuan, WANG Bo. The development of intelligent operation method of urban public infrastructure driven by accurate spatio-temporal information[J]. Journal of Geodesy and Geoinformation Science, 2021(2):27-35.