Abstract
Accurate powerline classification from LiDAR point clouds is essential for efficient monitoring and management of power distribution networks. Currently, the classification is being done through manual labeling or some semi-automatic methods which are time-consuming and resource intensive. In this study, we explore three deep learning architectures, namely KPConv, PointCNN, and RandLA-Net, for powerline segmentation in aerial and mobile LiDAR datasets. We utilize manually labeled aerial and mobile LiDAR datasets from Surry in Canada and Kerala in India, respectively. Impressive results are obtained, demonstrating high powerline classification accuracy and precision. KPConv outperformed the other architectures, achieving over 98% accuracy for ALS data and surpassing 94% for MLS data. Additionally, we investigate the impact of ground removal on powerline extraction. The results highlight a significant improvement in powerline classification accuracy, with an approximate 3–4% enhancement observed, particularly in the test sets with a higher density of powerline points. Removing ground points effectively reduces noise and clutter in LiDAR data, leading to improved segmentation outcomes. Furthermore, ground removal proves beneficial in classifying wires in challenging scenarios, such as areas with nearby objects or branch and loose wires. KPConv demonstrates superior performance in powerline classification, capturing intricate powerline details even in scenes with varying point densities. PointCNN shows limitations, especially in wire point classification near other objects. RandLA-Net exhibits higher speed but slightly lower accuracy compared to KPConv. The findings contribute to advancing powerline classification and provide valuable insights for more efficient and automated management of power distribution networks.
Similar content being viewed by others
Data availability
The labeled data used in the study can be accessed at https://www.lidaverse.com/#/.
References
Awrangjeb M (2019) Extraction of Power Line pylons and wires using Airborne LiDAR Data at different height levels. Remote Sens 11:1798. https://doi.org/10.3390/rs11151798
Bello SA, Yu S, Wang C et al (2020) Review: deep learning on 3D point clouds. Remote Sens 12:1729. https://doi.org/10.3390/rs12111729
Chen C, Yang B, Song S et al (2018) Automatic clearance anomaly detection for transmission line corridors utilizing UAV-Borne LIDAR Data. Remote Sens 10:613. https://doi.org/10.3390/rs10040613
Cheng L, Tong L, Wang Y, Li M (2014) Extraction of Urban Power Lines from Vehicle-Borne LiDAR Data. Remote Sens 6:3302–3320. https://doi.org/10.3390/rs6043302
Ekhtari N, Glennie C, Fernandez-Diaz JC (2018) Classification of Airborne Multispectral Lidar Point clouds for Land Cover Mapping. IEEE J Sel Top Appl Earth Observations Remote Sens 11:2068–2078. https://doi.org/10.1109/JSTARS.2018.2835483
Fischler MA, Bolles RC (1981) Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun ACM 24:381–395. https://doi.org/10.1145/358669.358692
Fu S, Zuo Q, Hou Z-G et al (2008) Unsupervised learning of categories from sets of partially matching image features for power line inspection robot. In: 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence). pp 2596–2603
Grigillo D, Ozvaldič S, Vrecko A, Fras M (2015) Extraction of power lines from airborne and terrestrial laser scanning data using the hough transform. Geodetski Vestnik 59:246–261. https://doi.org/10.15292/geodetski-vestnik.2015.02.246-261
Guan H, Yu Y, Li J et al (2016) Extraction of power-transmission lines from vehicle-borne lidar data. Int J Remote Sens 37:229–247. https://doi.org/10.1080/01431161.2015.1125549
Guan H, Sun X, Su Y et al (2021) UAV-lidar aids automatic intelligent powerline inspection. Int J Electr Power Energy Syst 130:106987. https://doi.org/10.1016/j.ijepes.2021.106987
Guo B, Huang X, Zhang F, Sohn G (2015) Classification of airborne laser scanning data using JointBoost. ISPRS J Photogrammetry Remote Sens 100:71–83. https://doi.org/10.1016/j.isprsjprs.2014.04.015
Guo Y, Wang H, Hu Q et al (2020) Deep learning for 3D point clouds. A Survey
Hu Q, Yang B, Xie L et al (2020) RandLA-Net. Efficient Semantic Segmentation of Large-Scale Point Clouds
Huiying D, Tingting H (2015) Transmission line extraction method based on Hough transform. In: The 27th Chinese Control and Decision Conference (2015 CCDC). pp 4892–4895
Jung J, Che E, Olsen MJ, Shafer KC (2020) Automated and efficient powerline extraction from laser scanning data using a voxel-based subsampling with hierarchical approach. ISPRS J Photogrammetry Remote Sens 163:343–361. https://doi.org/10.1016/j.isprsjprs.2020.03.018
Jwa Y, Sohn G (2012) A Piecewise Catenary curve model growing for 3D Power Line Reconstruction. Photogramm eng Remote Sens 78:1227–1240. https://doi.org/10.14358/PERS.78.11.1227
Kim HB, Sohn G (2010) 3D CLASSIFICATION OF POWER-LINE SCENE FROM AIRBORNE LASER SCANNING DATA USING RANDOM FORESTS. 7
Kim H, Sohn G (2011) Random Forests based multiple classifier system for power-line scene classification
Kim HB, Sohn G (2013) Point-based classification of Power Line Corridor Scene using Random forests. Photogramm eng Remote Sens 79:821–833. https://doi.org/10.14358/PERS.79.9.821
Lehtomäki M, Kukko A, Matikainen L et al (2019) Power line mapping technique using all-terrain mobile laser scanning. Autom Constr 105:102802. https://doi.org/10.1016/j.autcon.2019.03.023
Li Z, Liu Y, Walker R et al (2010) Towards automatic power line detection for a UAV surveillance system using pulse coupled neural filter and an improved Hough transform. Mach Vis Appl 21:677–686. https://doi.org/10.1007/s00138-009-0206-y
Li Y, Bu R, Sun M et al (2018) PointCNN: Convolution on X-Transformed points. Advances in neural information Processing systems. Curran Associates, Inc
Li W, Luo Z, Xiao Z et al (2022) A GCN-Based method for Extracting Power lines and pylons from Airborne LiDAR Data. IEEE Trans Geosci Remote Sens 60:1–14. https://doi.org/10.1109/TGRS.2021.3076107
Liu Y, Li Z, Hayward R et al (2009) Classification of Airborne LIDAR Intensity Data Using Statistical Analysis and Hough Transform with Application to Power Line Corridors. In: 2009 Digital Image Computing: Techniques and Applications. pp 462–467
Liu W, Sun J, Li W et al (2019a) Deep learning on Point clouds and its application: a Survey. Sensors 19:4188. https://doi.org/10.3390/s19194188
Liu Z, Tang H, Lin Y, Han S (2019b) Point-Voxel CNN for efficient 3D Deep Learning. Advances in neural information Processing systems. Curran Associates, Inc
Munir N, Awrangjeb M, Stantic B (2019) An Automated Method for Individual Wire Extraction from Power Line Corridor using LiDAR Data. In: 2019 Digital Image Computing: Techniques and Applications (DICTA). pp 1–8
Niemeyer J, Rottensteiner F, Soergel U (2014) Contextual classification of lidar data and building object detection in urban areas. ISPRS J Photogrammetry Remote Sens 87:152–165. https://doi.org/10.1016/j.isprsjprs.2013.11.001
Ortega S, Trujillo A, Santana JM et al (2019) Characterization and modeling of power line corridor elements from LiDAR point clouds. ISPRS J Photogrammetry Remote Sens 152:24–33. https://doi.org/10.1016/j.isprsjprs.2019.03.021
Qi CR, Yi L, Su H, Guibas LJ (2017) PointNet++: deep hierarchical feature learning on point sets in a metric space. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. Curran Associates Inc., Red Hook, NY, USA, pp 5105–5114
Ritter M, Benger W (2012) Reconstructing Power Cables from LIDAR Data using Eigenvector streamlines of the point distribution Tensor Field. J WSCG 8
Sánchez-Rodríguez A, Soilán M, Cabaleiro M, Arias P (2019) Automated inspection of railway tunnels’ Power Line using LiDAR Point clouds. Remote Sens 11:2567. https://doi.org/10.3390/rs11212567
Su H, Maji S, Kalogerakis E, Learned-Miller E (2015) Multi-View Convolutional Neural Networks for 3D Shape Recognition. pp 945–953
Thomas H, Qi CR, Deschaud J-E et al (2019) KPConv: Flexible and Deformable Convolution for Point Clouds. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV). IEEE, Seoul, Korea (South), pp 6410–6419
Valseca V, Paneque J, Martinez-de Dios JR, Ollero A (2022) Real-time LiDAR-based Semantic Classification for Powerline Inspection. In: 2022 International Conference on Unmanned Aircraft Systems (ICUAS). IEEE, Dubrovnik, Croatia, pp 478–486
Varney N, Asari VK, Graehling Q (2020) DALES: A Large-Scale Aerial LiDAR Data Set for Semantic Segmentation. pp 186–187
Wang Y, Chen Q, Liu L et al (2017) Supervised classification of power lines from Airborne LiDAR Data in Urban Areas. Remote Sens 9:771. https://doi.org/10.3390/rs9080771
Wang Y, Chen Q, Liu L, Li K (2019a) A hierarchical unsupervised method for power line classification from airborne LiDAR data. Int J Digit Earth 12:1406–1422. https://doi.org/10.1080/17538947.2018.1503740
Wang Y, Sun Y, Liu Z et al (2019b) Dynamic Graph CNN for Learning on Point Clouds
Yadav M, Chousalkar CG (2017) Extraction of power lines using mobile LiDAR data of roadway environment. Remote Sens Applications: Soc Environ 8:258–265. https://doi.org/10.1016/j.rsase.2017.10.007
Yan G, Li C, Zhou G et al (2007) Automatic extraction of power lines from aerial images. IEEE Geosci Remote Sens Lett 4:387–391. https://doi.org/10.1109/LGRS.2007.895714
Yang J, Kang Z (2018) Voxel-based extraction of transmission lines from Airborne LiDAR Point Cloud Data. IEEE J Sel Top Appl Earth Observations Remote Sens 11:3892–3904. https://doi.org/10.1109/JSTARS.2018.2869542
Zhang J, Lin X, Ning X (2013) SVM-Based classification of Segmented Airborne LiDAR Point clouds in Urban Areas. Remote Sens 5:3749–3775. https://doi.org/10.3390/rs5083749
Zhang W, Qi J, Wan P et al (2016) An Easy-to-use Airborne LiDAR Data Filtering Method based on Cloth Simulation. Remote Sens 8:501. https://doi.org/10.3390/rs8060501
Zhang J, Zhao X, Chen Z, Lu Z (2019) A review of Deep Learning-based semantic segmentation for Point Cloud. IEEE Access 7:179118–179133. https://doi.org/10.1109/ACCESS.2019.2958671
Zhu L, Hyyppa J (2014a) Fully-automated power line extraction from Airborne Laser scanning point clouds in Forest areas. Remote Sens 6:11267–11282. https://doi.org/10.3390/rs61111267
Zhu L, Hyyppa J (2014b) The Use of Airborne and Mobile Laser scanning for modeling Railway environments in 3D. Remote Sens 6:3075–3100. https://doi.org/10.3390/rs6043075
Acknowledgements
The authors acknowledge Geokno India Pvt. Ltd. for mobile data and DALES Object for aerial data.
Funding
The authors used the support provided by the cluster project under the Data Science (DS) Research of Frontier and Futuristic Technologies (FFT) Division of the Department of Science and Technology (DST), Government of India, New Delhi. The authors also used financial support provided by the National Geospatial Programme (NGP), the Department of Science and Technology (DST), Government of India, New Delhi under grant NGP/V.Kumar/IISER-Bhopal/2023 (G).
Author information
Authors and Affiliations
Contributions
Vaibhav Kumar has developed the methodology, supervised the work, and written the manuscript.Aritra Nandy and Vishal Soni have done formal analysis and written the manuscript.Bharat Lohani has developed the methodology and supervised the work.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Communicated by H. Babaie.
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Kumar, V., Nandy, A., Soni, V. et al. Powerline extraction from aerial and mobile LiDAR data using deep learning. Earth Sci Inform (2024). https://doi.org/10.1007/s12145-024-01310-w
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12145-024-01310-w