Image-based laser point cloud building facade structure extraction method by considering semantic information
Source abstract
Abstract
Abstract Building facade structures form the foundation for 3D model reconstructions, making the extraction of facade structures from 3D point clouds a key research area. A method for extracting the building facade structure from image-based laser point clouds by considering semantic information is proposed. First, point cloud segmentation and clustering are applied to organize the data into distinct planes. Second, semantic images and corresponding semantic image laser point cloud models are generated from each plane. Finally, an enhanced method named as SemColorED extracts the facade structures, and followed by optimization based on building morphology. Evaluation of the method using actual 3D laser point cloud data and the Semantic3D dataset shows improved accuracy, recall, and integrity compared to the current methods.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: 3D Surveying and Cultural Heritage · Remote Sensing and LiDAR Applications · Satellite Image Processing and Photogrammetry
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (26)
Show source-provided references
1. Zuo, Z. & Li, Y. A framework for reconstructing building parametric models with hierarchical relationships from point clouds. Int. J. Appl. Earth Obs. 119, 103327 (2023).
2. Zhao, Q., Zhou, L. & Lv, G. A 3D modeling method for buildings based on LiDAR point cloud and DLG. Comput. Environ. Urban 102, 101974 (2023).10.1016/j.compenvurbsys.2023.101974 ↗
3. Luo, R., Zhou, Z., Chu, X., Ma, W. & Meng, J. 3D deformation monitoring method for temporary structures based on multi-thread LiDAR point cloud. Measurement 200, 111545 (2022).10.1016/j.measurement.2022.111545 ↗
4. Yuan, Y. et al. Three dimensional deformation measurement method based on image guided point cloud registration. Opt. Laser Eng. 161, 107399 (2023).10.1016/j.optlaseng.2022.107399 ↗
5. Haghighatgou, N., Daniel, S. & Badard, T. A method for automatic identification of openings in buildings facades based on mobile LiDAR point clouds for assessing impacts of floodings. Int. J. Appl. Earth Observ. Geoinf. 108, 102757 (2022).
6. Lu, Y. et al. A deep learning method for building façade parsing utilizing improved SOLOv2 instance segmentation. Energ. Build. 295, 113275 (2023).10.1016/j.enbuild.2023.113275 ↗
7. Su, Y. et al. DLA-Net: Learning dual local attention features for semantic segmentation of large-scale building facade point clouds. Pattern Recognit. 123, 108372 (2022).10.1016/j.patcog.2021.108372 ↗
8. Gao, X. et al. Ancient Chinese architecture 3D preservation by merging ground and aerial point clouds. ISPRS J. Photogramm. 143, 72–84 (2018).10.1016/j.isprsjprs.2018.04.023 ↗
9. Yin, Y. & Antonio, J. Application of 3D laser scanning technology for image data processing in the protection of ancient building sites through deep learning. Image Vis. Comput. 102, 103969 (2020).10.1016/j.imavis.2020.103969 ↗
10. Feng, H. et al. Automated extraction of building instances from dual-channel airborne LiDAR point clouds. Int. J. Appl. Earth Obs. 114, 103042 (2022).
11. Hamid-Lakzaeian, F. Structural-based point cloud segmentation of highly ornate building façades for computational modelling. Autom. Constr. 108, 102892 (2019).10.1016/j.autcon.2019.102892 ↗
12. Maru M. B., Wang Y., Kim H., Yoon H., Park S. Improved building facade segmentation through digital twin-enabled RandLA-Net with empirical intensity correction model. J. Build Eng. 107520 (2023).10.1016/j.jobe.2023.107520 ↗
13. Zolanvari, S. M. I., Laefer, D. F. & Natanzi, A. S. Three-dimensional building façade segmentation and opening area detection from point clouds. ISPRS J. Photogramm. Remote Sens. 143, 134–149 (2018).10.1016/j.isprsjprs.2018.04.004 ↗
14. Dong, X., Xiao, Y., Chen, Z., Yao, J. & Guo, X. GPU-based supervoxel segmentation for 3D point clouds. Comput. Aided Geometr. Des. 93, 102080 (2022).10.1016/j.cagd.2022.102080 ↗
15. Poux, F., Mattes, C., Selman, Z. & Kobbelt, L. Automatic region-growing system for the segmentation of large point clouds. Autom. Constr. 138, 104250 (2022).10.1016/j.autcon.2022.104250 ↗
16. Khaloo, A. & Lattanzi, D. Robust normal estimation and region growing segmentation of infrastructure 3D point cloud models. Adv. Eng. Inform. 34, 1–16 (2017).10.1016/j.aei.2017.07.002 ↗
17. Kim, M., Lee, D., Kim, T., Oh, S. & Cho, H. Automated extraction of geometric primitives with solid lines from unstructured point clouds for creating digital buildings models. Autom. Constr. 145, 104642 (2023).10.1016/j.autcon.2022.104642 ↗
18. Wang, Y. et al. Laser point cloud registration method based on iterative closest point improved by Gaussian mixture model considering corner features. Int. J. Remote Sens. 43, 932–960 (2022).10.1080/01431161.2021.2022242 ↗
19. Wang, Y., Hu, X., Zhou, T., Ma, Y. & Li, Z. Efficient building facade structure extraction method using image-based laser point cloud. Trans. GIS 27, 1145–1163 (2023).10.1111/tgis.13063 ↗
20. Xie, Y., Tian, J. & Zhu, X. X. A co-learning method to utilize optical images and photogrammetric point clouds for building extraction. Int. J. Appl. Earth Obs. 116, 103165 (2023).
21. Wang, Y., Ma, Y., Zhu, A., Zhao, H. & Liao, L. Accurate facade feature extraction method for buildings from three-dimensional point cloud data considering structural information. ISPRS J. Photogramm. Remote Sens. 139, 146–153 (2018).10.1016/j.isprsjprs.2017.11.015 ↗
22. Zhang, H. X. & Zou, Z. Quality assurance for building components through point cloud segmentation leveraging synthetic data. Autom. Constr. 155, 105045 (2023).10.1016/j.autcon.2023.105045 ↗
23. Hu, X., Wang, Y., Zhou, T. & Mwakapesa, D. S. Building facade structure extraction method based on three-dimensional laser point cloud by considering semantic information. Ann. GIS 30, 291–305 (2024).10.1080/19475683.2024.2335953 ↗
24. Akinlar, C. & Topal, C. ColorED: Color edge and segment detection by Edge Drawing (ED). J. Vis. Commun. Image Represent 44, 82–94 (2017).10.1016/j.jvcir.2017.01.024 ↗
25. Hackel, T. et al. Semantic3D.net: a new large-scale point cloud classification benchmark. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences; IV-1/W1 (2017).10.5194/isprs-annals-IV-1-W1-91-2017 ↗
26. Lu X., Liu Y., Li K. Fast 3D Line Segment Detection From Unorganized Point Cloud [Internet]. arXiv; 2019 [cited 2022 Jul 3]. Available from: http://arxiv.org/abs/1901.02532.