SYNTHETIC RESEARCH ON CONSTRUCTION INSPECTION BASED ON BIM AND POINT CLOUD SEGMENTATION USING DEEP LEARNING
-
摘要:
建筑信息模型(BIM)为工程建设提供了丰富的空间和属性信息，三维激光扫描等三维信息获取技术的发展使获取工程建设三维场景信息变得更加便捷、高效。通过融合实际工程点云与BIM，将有助于实现工程建设质量和进度管理的自动化。既有研究一般比对点云与BIM的全局信息，需要工程人员根据不同规则检查判断，结果难以定量呈现。同时，比对结果无法与BIM构件属性自动关联并服务于智能化分析。针对上述问题，该文引入深度学习点云语义分割技术，对框架梁柱节点实现构件的对象化比对，提高了点云与BIM比对的自动化和数字化程度。模拟试验研究表明，采用的PointNet++模型在框架节点点云语义分割任务中取得了较高的精度，并对数据误差具有较好的健壮性，可为对象化的施工偏差比对提供良好的数据基础。该文方法实现的框架节点施工点云与BIM模型的对象化偏差比对，将在施工偏差展示、测量数据数字化和施工进度管理方面具有良好的应用价值和发展潜力。
Abstract:Building information modeling (BIM) provides a wealth of space and attribute information for construction, and the development of 3D information acquisition technologies such as 3D laser scanning makes it more convenient and efficient to obtain 3D information of construction scenes. By integrating the point clouds of actual construction scenes and BIM, the automation of construction quality and progress management is expected to be improved. Existing studies generally compare the global information of point clouds with BIM, which needs further inspection and judgement by engineers based on different rules, and also makes it difficult to quantify the results. Meanwhile, the comparison results cannot be automatically matched with component properties in BIM and then serve intelligent analysis. The point cloud semantic segmentation using deep learning is introduced to realize the object-oriented comparison of components for the frame nodes, which increases the automation and digitization level of point-cloud-vs-BIM comparison. Synthetic experiments show that the adopted PointNet++ achieves high accuracy of semantic segmentation in the task, and has good robustness to data acquisition errors, which can provide a solid foundation for object-oriented construction deviation comparison. The object-oriented deviation comparison of point clouds with BIM realized by this method will have a promising prospect in the application to construction deviation visualization, measurement data digitization, and construction progress management.
-
-
![]()
图 5 虚拟深度相机获得的深度图和语义标签
Figure 5. Depth map and semantic labels obtained by the virtual depth camera
![]()
图 7 不同相机水平距离下的预测结果混淆矩阵
Figure 7. Prediction confusion matrix for different camera horizontal distances
![]()
图 11 预测误差位置的标签对比与法向量可视化
Figure 11. Comparison of labels at where the errors occur and visualization of normal vectors
表 1 不同相机水平距离下的mIoU预测结果
Table 1 Prediction mIoU for different camera horizontal distances
相机水平距离/m 3 6 9 平均交并比mIoU 0.992 0.989 0.988 
下载: 导出CSV
表 2 不同节点类型的mIoU预测结果
Table 2 Prediction mIoU for different node styles
节点类型 中柱节点 边柱节点 角柱节点 平均交并比mIoU 0.989 0.991 0.992
下载: 导出CSV
-
[1] 林佳瑞, 张建平, 钟耀锋. 基于4D-BIM的施工进度-资源均衡模型自动构建与应用[J]. 土木建筑工程信息技术, 2014, 6(6): 44 − 49. doi: 10.16670/j.cnki.cn11-5823/tu.2014.06.009 LIN Jiarui, ZHANG Jianping, ZHONG Yaofeng. Schedule-resource trade-off modeling and application based on 4D-BIM [J]. Journal of Information Technology in Civil Engineering and Architecture, 2014, 6(6): 44 − 49. (in Chinese) doi: 10.16670/j.cnki.cn11-5823/tu.2014.06.009
[2] 吴贤国, 秦文威, 张立茂, 等. 基于BIM的项目进度管理与控制研究[J]. 建筑经济, 2018, 39(10): 59 − 63. doi: 10.14181/j.cnki.1002-851x.201810059 WU Xianguo, QIN Wenwei, ZHANG Limao, et al. Research on project schedule management and control based on BIM [J]. Construction Economy, 2018, 39(10): 59 − 63. (in Chinese) doi: 10.14181/j.cnki.1002-851x.201810059
[3] CHEN C, TANG L. BIM-based integrated management workflow design for schedule and cost planning of building fabric maintenance [J]. Automation in Construction, 2019, 107: 102944. doi: 10.1016/j.autcon.2019.102944
[4] LI C Z, ZHONG R Y, XUE F, et al. Integrating RFID and BIM technologies for mitigating risks and improving schedule performance of prefabricated house construction [J]. Journal of Cleaner Production, 2017, 165: 1048 − 1062. doi: 10.1016/j.jclepro.2017.07.156
[5] ZHANG J P, HU Z Z. BIM- and 4D-based integrated solution of analysis and management for conflicts and structural safety problems during construction: 1. Principles and methodologies [J]. Automation in Construction, 2011, 20(2): 155 − 166. doi: 10.1016/j.autcon.2010.09.013
[6] 赵馨怡, 郭晓. 基于BIM和三维激光扫描技术的建设工程质量检测方法研究[J]. 土木建筑工程信息技术, 2020, 12(5): 131 − 134. doi: 10.16670/j.cnki.cn11-5823/tu.2020.05.22 ZHAO Xinyi, GUO Xiao. Research on construction quality inspection methodology based on the BIM and 3D laser scanning technology [J]. Journal of Information Technology in Civil Engineering and Architecture, 2020, 12(5): 131 − 134. (in Chinese) doi: 10.16670/j.cnki.cn11-5823/tu.2020.05.22
[7] RAUSCH C, HAAS C. Automated shape and pose updating of building information model elements from 3D point clouds [J]. Automation in Construction, 2021, 124: 103561. doi: 10.1016/j.autcon.2021.103561
[8] 丁一凡, 刘宇飞, 樊健生, 等. 基于空间位形的在役索膜结构有限元模型修正与安全评估[J]. 工程力学, 2022, 39(5): 44 − 54. doi: 10.6052/j.issn.1000-4750.2021.08.ST08 DING Yifan, LIU Yufei, FAN Jiansheng, et al. Finite element model updating and safety assessment of in-service cable-membrane structure based on spatial configuration [J]. Engineering Mechanics, 2022, 39(5): 44 − 54. (in Chinese) doi: 10.6052/j.issn.1000-4750.2021.08.ST08
[9] 刘宇飞, 樊健生, 孔思宇, 等. 多视角几何三维重建法识别工程结构缺损与变形[J]. 工程力学, 2020, 37(9): 103 − 111. doi: 10.6052/j.issn.1000-4750.2019.10.0598 LIU Yufei, FAN Jiansheng, KONG Siyu, et al. Detection of structural defect and deformation based on multi-view geometric three-dimensional reconstruction method [J]. Engineering Mechanics, 2020, 37(9): 103 − 111. (in Chinese) doi: 10.6052/j.issn.1000-4750.2019.10.0598
[10] 雷素素, 刘宇飞, 段先军, 等. 复杂大跨空间钢结构施工过程综合监测技术研究[J]. 工程力学, 2018, 35(12): 203 − 211. doi: 10.6052/j.issn.1000-4750.2018.09.0836 LEI Susu, LIU Yufei, DUAN Xianjun, et al. Study of comprehensive monitoring technology of the construction process of complex large-span spatial steel structures [J]. Engineering Mechanics, 2018, 35(12): 203 − 211. (in Chinese) doi: 10.6052/j.issn.1000-4750.2018.09.0836
[11] 杨娜, 张翀, 李天昊. 基于无人机与计算机视觉的中国古建筑木结构裂缝监测系统设计[J]. 工程力学, 2021, 38(3): 27 − 39. doi: 10.6052/j.issn.1000-4750.2020.04.0263 YANG Na, ZHANG Chong, LI Tianhao. Design of crack monitoring system for Chinese ancient wooden buildings based on UAV and CV [J]. Engineering Mechanics, 2021, 38(3): 27 − 39. (in Chinese) doi: 10.6052/j.issn.1000-4750.2020.04.0263
[12] KIM S, KIM S, LEE D E. Sustainable application of hybrid point cloud and BIM method for tracking construction progress [J]. Sustainability, 2020, 12(10): 4106. doi: 10.3390/su12104106
[13] XIE Y, TIAN J, ZHU X X. Linking points with labels in 3D: A review of point cloud semantic segmentation [J]. IEEE Geoscience and Remote Sensing Magazine, 2020, 8(4): 38 − 59. doi: 10.1109/MGRS.2019.2937630
[14] ZHOU Q. 3D urban modeling from city-scale aerial LiDAR data [D]. Los Angeles, CA, USA: University of Southern California, 2012.
[15] QI C R, SU H, MO K, et al. PointNet: Deep learning on point sets for 3D classification and segmentation [C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, HI, USA: IEEE, 2017: 77 − 85.
[16] QI C R, YI L, SU H, et al. PointNet++: Deep hierarchical feature learning on point sets in a metric space [C]// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook, NY, USA: Curran Associates Inc., 2017: 5105 − 5114.
[17] LI Y, BU R, SUN M, et al. PointCNN: Convolution on X-transformed points [C]// Advances in Neural Information Processing Systems: 31. Montréal, Canada: Curran Associates, Inc., 2018.
[18] WANG Y, SUN Y, LIU Z, et al. Dynamic graph CNN for learning on point clouds [J/OL]. arXiv: 1801.07829 [cs], 2019[2022-03-14]. http://arxiv.org/abs/1801.07829.
[19] SUN C J, ZHANG F, ZHAO P J, et al. Automated simulation framework for urban wind environments based on aerial point clouds and deep learning [J]. Remote Sensing, 2021, 13(12): 2383. doi: 10.3390/rs13122383
[20] LOWPHANSIRIKUL C, KIM K, VINAYARAJ P, et al. 3D semantic segmentation of large-scale point-clouds in urban areas using deep learning [C]// 2019 11th International Conference on Knowledge and Smart Technology (KST). Phuket, Thailand: KST, 2019: 238 − 243.
[21] KIM H, YOON J, SIM S H. Automated bridge component recognition from point clouds using deep learning [J]. Structural Control and Health Monitoring, 2020, 27(9): e2591. doi: 10.1002/stc.2591
[22] SUN J, ZHANG Q, KAILKHURA B, et al. Benchmarking robustness of 3D point cloud recognition against common corruptions [J/OL]. arXiv: 2201.12296 [cs], 2022[2022-02-18]. http://arxiv.org/abs/2201.12296.
[23] LiDAR Camera L515 – Intel® RealSense™ Depth and Tracking Cameras [EB/OL]. https://www.intelrealsense.com/lidar-camera-l515/. [2022-03-14].
[24] ZHOU Q Y, PARK J, KOLTUN V. Open3D: A modern library for 3D data processing [J/OL]. arXiv: 1801.09847 [cs], 2018[2022-03-15]. http://arxiv.org/abs/1801.09847.
计量
- 文章访问数: 476
- HTML全文浏览量: 185
- PDF下载量: 88
