架空输电线路杆塔LiDAR点云塔型识别方法
LiDAR Point Cloud Tower Type Identification Method for Overhead Transmission Line Tower
DOI: 10.12677/GST.2022.103016, PDF,    科研立项经费支持
作者: 吴少龙*：武汉大学测绘遥感信息工程国家重点实验室，湖北 武汉；裴嘉伟*, 吴宇宸：武汉大学电子信息学院，湖北 武汉；邵文轩, 郑欣婷：武汉大学遥感信息工程学院，湖北 武汉；张润凡：武汉大学电气与自动化学院，湖北 武汉
关键词: 智能电网；电塔塔型实时识别；LiDAR点云；PCA；深度学习；Smart Grid； Real-Time Identification of Tower Type； LiDAR Point Cloud； PCA； Deep Learning
摘要: “智能电网”的构建是现代化社会电力系统建设规划与发展的重中之重，输电走廊的数字化作为其中的重要一环，然而，现阶段输电走廊数字化仍需耗费大量人工，其自动化水平亟待提升。而输电杆塔的建模效率能否提升成为了决定整个输电线路三维建模效率的主要因素。为解决杆塔建模效率的问题，本文作为模型驱动的输电杆塔建模方法的前期工作，提出了一种基于PCA算法与YOLOv5目标检测算法结合的塔型识别方法。该方法首先使用PCA算法提取电塔的主方向，通过主方向投影实现了杆塔点云的二维转换，并将主方向投影图作为网络模型的输入，进而通过YOLOv5算法实现了电塔的塔型识别。实验表明，本文所提出的方法能够实现对输电杆塔点云数据实时精确的塔型识别：塔型识别的平均精确度map@0.5为0.867，识别速度为0.02 s。
Abstract: The construction of “smart grid” is the top priority of the construction planning and development of the modern social power system, and the digitization of the transmission corridor is an important part of it. However, at this stage, the digitization of the transmission corridor still requires a lot of labor, and its automation level needs to be improved urgently. Whether the modeling efficiency of transmission towers can be improved has become the main factor that determines the efficiency of 3D modeling of the entire transmission line. In order to solve the problem of tower modeling efficiency, as the preliminary work of model-driven transmission tower modeling method, this paper proposes a tower type identification method based on the combination of PCA algorithm and YOLOv5 target detection algorithm. The method first uses the PCA algorithm to extract the main direction of the tower, realizes the two-dimensional transformation of the tower point cloud through the main direction projection, and uses the main direction projection map as the input of the network model, and then realizes the tower shape of the tower through the YOLOv5 algorithm. identify. Experiments show that the method proposed in this paper can realize real-time and accurate tower type recognition for point cloud data of transmission towers: the average accuracy of tower type recognition map@0.5 is 0.867, and the recognition speed is 0.02 s.
文章引用：吴少龙, 裴嘉伟, 吴宇宸, 邵文轩, 郑欣婷, 张润凡. 架空输电线路杆塔LiDAR点云塔型识别方法[J]. 测绘科学技术, 2022, 10(3): 161-172. https://doi.org/10.12677/GST.2022.103016

参考文献

[1] Matikainen, L., Lehtomäki, M., Ahokas, E., Hyyppä, J., Karjalainen, M., Jaakkola, A., et al. (2016) Remote Sensing Methods for Power Line Corridor Surveys. ISPRS Journal of Photogrammetry and Remote Sensing, 119, 10-31. [Google Scholar] [CrossRef] 
[2] Fang, X., Misra, S., Xue, G. and Yang, D. (2011) Smart Grid—The New and Improved Power Grid: A Survey. IEEE Communications Surveys & Tutorials, 14, 944-980. [Google Scholar] [CrossRef] 
[3] Wang, H. and Hu, D. (2005) Comparison of SVM and LS-SVM for Regression. 2005 International Conference on Neural Networks and Brain, IEEE, 1, 279-283.
[4] Zhou, R., Jiang, W., Huang, W., Xu, B. and Jiang, S. (2017) A Heuristic Method for Power Pylon Reconstruction from Airborne LiDAR Data. Remote Sensing, 9, Article No. 1172. [Google Scholar] [CrossRef] 
[5] Girshick, R., Donahue, J., Darrell, T. and Malik, J. (2014) Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, 23-28 June 2014, 580-587. [Google Scholar] [CrossRef] 
[6] Girshick, R. (2015) Fast R-CNN. Proceedings of the IEEE International Conference on Computer Vision, Santiago, 7-13 December 2015, 1440-1448. [Google Scholar] [CrossRef] 
[7] Ren, S., He, K., Girshick, R. and Sun, J. (2017) Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 1137-1149. [Google Scholar] [CrossRef] 
[8] He, K., Zhang, X., Ren, S. and Sun, J. (2014) Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition. IEEE Transactions on Pattern Analysis & Machine Intelligence, 37, 1904-1916. [Google Scholar] [CrossRef] 
[9] Dai, J., Li, Y., He, K. and Sun, J. (2016) R-FCN: Object Detection via Region-Based Fully Convolutional Networks. Proceedings of the 30th International Conference on Neural Information Processing Systems, Barcelona, 5-10 December 2016, 379-387.
[10] Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R. and LeCun, Y. (2013) OverFeat: Integrated Recognition, Localization and Detection Using Convolutional Networks. arXiv:1312.6229.
[11] Redmon, J., Divvala, S., Girshick, R. and Farhadi, A. (2016) You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, 27-30 June 2016, 779-788. [Google Scholar] [CrossRef] 
[12] Redmon, J. and Farhadi, A. (2017) YOLO9000: Better, Faster, Stronger. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, 21-26 July 2017, 6517-6525. [Google Scholar] [CrossRef] 
[13] Redmon, J. and Farhadi, A. (2018) YOLOv3: An Incremental Improvement. arXiv: 1804.02767.
[14] Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., et al. (2016) SSD: Single Shot Multibox Detector. European Conference on Computer Vision, Amsterdam, 11-14 October 2016, 21-37. [Google Scholar] [CrossRef] 
[15] 王万国, 田兵, 刘越, 刘俍, 李建祥. 基于RCNN的无人机巡检图像电力小部件识别研究[J]. 地球信息科学学报, 2017, 19(2): 256 263.
[16] 杨晓旭, 温招洋. 深度学习在输电线路绝缘子故障检测中的研究与应用[J]. 中国新通信, 2018, 20(10): 208-210.
[17] Nordeng, I.E., Hasan, A., Olsen, D. and Neubert, J. (2017) DEBC detection with deep learning. Scandinavian Conference on Image Analysis, Tromsø, 12-14 June 2017, 248-259. [Google Scholar] [CrossRef] 
[18] Shlens, J. (2014) A Tutorial on Principal Component Analysis. arXiv preprint arXiv:1404.1100.
[19] Bell, A.J. and Sejnowski, T.J. (1997) The “Independent Components” of Natural Scenes Are Edge Filters. Vision Research, 37, 3327-3338. [Google Scholar] [CrossRef] 
[20] Bishop, C.M. (1995) Neural Networks for Pattern Recognition. Oxford University Press, Oxford, 253-290
[21] Lay, D.C. (2003) Linear Algebra and Its Applications. Pearson Education, India.
[22] Mitra, P.P. and Pesaran, B. (1999) Analysis of Dynamic Brain Imaging Data. Biophysical Journal, 76, 691-708. [Google Scholar] [CrossRef] 
[23] 王旭科, 闫世伟, 李艳芳, 李龙. 基于机载LiDAR和倾斜影像的城市三维建模方法[J]. 北京测绘, 2021, 35(1): 51-55.
[24] Wold, S., Esbensen, K. and Geladi, P. (1987) Principal Component Analysis. Chemometrics and Intelligent Laboratory Systems, 2, 37-52. [Google Scholar] [CrossRef] 
[25] Mouat, D.A., Mahin, G.G. and Lancaster, J. (1993) Remote Sensing Techniques in the Analysis of Change Detection. Geocarto International, 8, 39-50. [Google Scholar] [CrossRef] 
[26] 郭敬东, 陈彬, 王仁书, 王佳宇, 仲林林. 基于YOLO的无人机电力线路杆塔巡检图像实时检测[J]. 中国电力, 2019, 52(7): 17-23.
[27] 张斗斗, 晏子奕, 周良杰, 蔡先乔, 汪海波, 惠康华. 基于YOLOv5的机场飞行区目标检测方法研究[J]. 建模与仿真, 2022, 11(2): 432-441. [Google Scholar] [CrossRef] 
[28] 许德刚, 王露, 李凡. 深度学习的典型目标检测算法研究综述[J]. 计算机工程与应用, 2021, 57(8): 10-25.
[29] 邱天衡, 王玲, 王鹏, 白燕娥. 基于改进YOLOv5的目标检测算法研究[J/OL]. 计算机工程与应用: 1-13. http://kns.cnki.net/kcms/detail/11.2127.TP.20220402.1028.002.html, 2022-04-19.
[30] Qiao, S., Sun, Y. and Zhang, H. (2020) Deep Learning Based Electric Pylon Detection in Remote Sensing Images. Remote Sensing, 12, Article No. 1857. [Google Scholar] [CrossRef] 
[31] Pathak, A.R., Pandey, M. and Rautaray, S. (2018) Application of Deep Learning for Object Detection. Procedia Computer Science, 132, 1706-1717. [Google Scholar] [CrossRef] 
[32] Bhattarai, S. (2018) Multi-Scale Object Detection in Aerial Images with Feature Pyramid Networks. Ph.D. Thesis, The University of Texas, San Antonio.
[33] Li, Y., Xiao, Z., Zhen, X. and Cao, X. (2019) Attentional Information Fusion Networks for Cross-Scene Power Line Detection. IEEE Geoscience and Remote Sensing Letters, 16, 1635-1639. [Google Scholar] [CrossRef] 
[34] Guo, J., Ma, X., Sansom, A., McGuire, M., Kalaani, A., Chen, Q., et al. (2020) Spanet: Spatial Pyramid Attention Network for Enhanced Image Recognition. 2020 IEEE International Conference on Multimedia and Expo (ICME), London, 6-10 July 2020, 1-6. [Google Scholar] [CrossRef] 
[35] Li, W., Lai, C. and Zhu, J. (2020) Multi-Layer Features Fusion Strategy with GIoU Loss for Siamese Network Tracking. The International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, Xi’an, 1-3 August 2020, 1611-1619. [Google Scholar] [CrossRef] 
[36] Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R. and Ren, D. (2020) Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression. Proceedings of the AAAI Conference on Artificial Intelligence, 34, 12993-13000. [Google Scholar] [CrossRef] 
[37] 肖博健, 万烂军, 陈俊权. 采用YOLOV5模型的口罩佩戴识别研究[J]. 福建电脑, 2021, 37(3): 35-37.

为你推荐