Line Structure Extraction from LiDAR Point Cloud Based on the Persistence of Tensor Feature
Source abstract
Abstract
The LiDAR point cloud has been widely used in scenarios of automatic driving, object recognition, structure reconstruction, etc., while it remains a challenging problem in line structure extraction, due to the noise and accuracy, especially in data acquired by consumer electronic devices. To address the issue, a line structure extraction method based on the persistence of tensor feature is proposed, and subsequently applied to the data acquired by an iPhone-based LiDAR sensor. The tensor of each point is encoded, voted, and aggregated by its neighborhood, and further decomposed into different geometric features in each dimension. Then, the line feature in the point cloud is represented and computed using the persistence of the tensor feature. Finally, the line structure is extracted based on the persistent homology according to the discrete Morse theory. With the LiDAR point cloud collected by the iPhone 12 Pro MAX, experiments are conducted, line structures are extracted from two different datasets, and results perform well in comparison with other related results.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Topological and Geometric Data Analysis · Advanced Vision and Imaging · Digital Image Processing Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Jiangsu Key Laboratory of Spectral Imaging & Intelligence Sense (SIIS), Nanjing University of Science and Technology, Nanjing 210094, China
Smart Health Big Data Analysis and Location Services Engineering Research Center of Jiangsu Province, Nanjing University of Posts and Telecommunications, Nanjing 210023, China
Funding
National Natural Science Foundation of China (NSFC)
References (34)
Show source-provided references
1. Semantic line framework-based indoor building modeling using backpacked laser scanning point cloud10.1016/j.isprsjprs.2018.03.025 ↗
2. Mallya, A., and Lazebnik, S. (2015, January 7–13). Learning informative edge maps for indoor scene layout prediction. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.10.1109/ICCV.2015.113 ↗
3. Edge-semantic learning strategy for layout estimation in indoor environment10.1109/TCYB.2019.2895837 ↗
4. Facet segmentation-based line segment extraction for large-scale point clouds10.1109/TGRS.2016.2639025 ↗
5. A Review of Deep Learning-Based Semantic Segmentation for Point Cloud10.1109/ACCESS.2019.2958671 ↗
6. Wang, X., Lyu, H., Mao, T., He, W., and Chen, Q. (2022). Point Cloud Segmentation from iPhone-Based LiDAR Sensors Using the Tensor Feature. Appl. Sci., 12.10.3390/app12041817 ↗
7. Deep Learning for 3d Point Clouds: A Survey10.1109/TPAMI.2020.3005434 ↗
8. Zheng, B., Zhao, Y., Yu, J.C., Ikeuchi, K., and Zhu, S.C. (2013, January 23–28). Beyond Point Clouds: Scene Understanding by Reasoning Geometry and Physics. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA.10.1109/CVPR.2013.402 ↗
9. A shape-based segmentation method for mobile laser scanning point clouds10.1016/j.isprsjprs.2013.04.002 ↗
10. Analytical and numerical investigations on the accuracy and robustness of geometric features extracted from 3D point cloud data10.1016/j.isprsjprs.2017.02.012 ↗
11. Su, H., Maji, S., Kalogerakis, E., and Learned-Miller, E. (2015, January 11–18). Multi-View Convolutional Neural Networks for 3d Shape Recognition. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.10.1109/ICCV.2015.114 ↗
12. Efficient RANSAC for Point-Cloud Shape Detection10.1111/j.1467-8659.2007.01016.x ↗
13. Continuous plane detection in point-cloud data based on 3D Hough Transform10.1016/j.jvcir.2013.04.001 ↗
14. Bazazian, D., Casas Pla, J.R., and Ruiz Hidalgo, J. (March, January 27). Segmentation-based multi-scale edge extraction to measure the persistence of features in unorganized point clouds. Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, Porto, Portugal.
15. Multi-scale tensor voting for feature extraction from unstructured point clouds10.1016/j.gmod.2012.04.008 ↗
16. King, B.J. (2008). Range Data Analysis by Free-Space Modeling and Tensor Voting, Rensselaer Polytechnic Institute.
17. Curvature-augmented tensor voting for shape inference from noisy 3D data10.1109/TPAMI.2002.1008395 ↗
18. Computing persistent homology10.1007/s00454-004-1146-y ↗
19. Topological pattern recognition for point cloud data10.1017/S0962492914000051 ↗
20. Learning persistent homology of 3D point clouds10.1016/j.cag.2021.10.022 ↗
21. Chen, T., and Wang, Q. (2010, January 8–12). 3d line segment detection for unorganized point clouds from multi-view stereo. Proceedings of the Asian Conference on Computer Vision, Queenstown, New Zealand.10.1007/978-3-642-19309-5_31 ↗
22. Lu, X., Liu, Y., and Li, K. (2019). Fast 3D line segment detection from unorganized point cloud. arXiv.
23. Dewez, T.J.B., Girardeau-Montaut, D., Allanic, C., and Rohmer, J. (2016, January 12–19). Facets: A Cloudcompare Plugin to Extract Geological Planes from Unstructed 3D Point Clouds. Proceedings of the International Archives of the Photogrammetry, Remote Sensing & Spatial Information Sciences, Prague, Czech Republic.10.5194/isprsarchives-XLI-B5-799-2016 ↗
24. Gankhuyag, U., and Han, J.H. (2020). Automatic 2d floorplan cad generation from 3d point clouds. Appl. Sci., 10.10.3390/app10082817 ↗
25. Towards automatic discontinuity trace extraction from rock mass point cloud without triangulation10.1016/j.ijrmms.2018.10.023 ↗
26. Guo, B., Li, Q., Huang, X., and Wang, C. (2016). An improved method for power-line reconstruction from point cloud data. Remote Sens., 8.10.3390/rs8010036 ↗
27. Demantké, J., Mallet, C., David, N., and Vallet, B. (2011, January 29–31). Dimensionality Based Scale Selection in 3D Lidar Point Clouds. Proceedings of the ISPRS Workshop on Laser Scanning, Calgary, AB, Canada.
28. Tensor voting guided mesh denoising10.1109/TASE.2016.2553449 ↗
29. Segmentation of LiDAR data using the tensor voting framework
30. The persistent cosmic web and its filamentary structure–I. Theory and implementation10.1111/j.1365-2966.2011.18394.x ↗
31. The persistent cosmic web and its filamentary structure–II. Illustrations10.1111/j.1365-2966.2011.18395.x ↗
32. The topology toolkit10.1109/TVCG.2017.2743938 ↗
33. Wong, C.C., and Vong, C.M. (2021, January 10–17). Persistent Homology Based Graph Convolution Network for Fine-Grained 3D Shape Segmentation. Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, QC, Canada.10.1109/ICCV48922.2021.00701 ↗
34. A topology-based descriptor for 3D point cloud modeling: Theory and experiments10.1016/j.imavis.2019.05.004 ↗