In recent years, a wide variety of three-dimensional (3D) scanning devices have been developed, allowing users to select appropriate sensing systems depending on their objectives and operational constraints. Among these devices, terrestrial laser scanners (TLS) offer superior scanning quality and accuracy and continue to play an important role in 3D sensing. Within TLS point cloud processing, object recognition and semantic segmentation are regarded as particularly important tasks. Numerous methods have been proposed for this purpose, and in recent years, approaches based on deep learning have attracted considerable attention. However, point cloud data are inherently irregular, unstructured, and unordered, which can make it challenging for existing methods to fully exploit their spatial information and consistently achieve satisfactory performance. In this study, we focus on TLS point clouds with RGB information and propose a semantic segmentation framework based on cube map projection. In the proposed framework, the 3D point cloud is first projected into a cube map representation to generate images corresponding to each face of the cube. Semantic segmentation is then applied to the generated images using mature two-dimensional (2D) convolutional neural networks (CNNs). The resulting semantic labels are subsequently reprojected onto the original point cloud, thereby achieving semantic segmentation of the 3D point cloud. The first advantage of the proposed framework is that it enables the application of well-established 2D CNN-based segmentation methods to the inherently challenging task of 3D point cloud segmentation. The second advantage is that RGB images, which are relatively easy to acquire and annotate, can be used as training data instead of 3D point clouds. The effectiveness of the proposed framework is validated through a series of experiments and evaluations conducted on TLS point clouds acquired in forest environments.

1. [1] T. Mizoguchi, “Detection of building equipment from mobile laser scanning point clouds using reflection intensity correction for detailed BIM generation,” Sensors, Vol.25, No.22, Article No.6937, 2025. https://doi.org/10.3390/s25226937
2. [2] R. Blaskow and H. G. Maas, “Structural health monitoring of bridge with personal laser scanning: Segment-based analysis of systematic point cloud deformations,” ISPRS Ann. Photogramm. Remote Sens. Spat. Inf. Sci., Vol.X-2-2024, pp. 9-16, 2024. https://doi.org/10.5194/isprs-annals-x-2-2024-9-2024
3. [3] K. Ishikawa, D. Kubo, and Y. Amano, “Curb detection and accessibility evaluation from low-density mobile mapping point cloud data,” Int. J. Automation Technol., Vol.12, No.3, pp. 376-385, 2018. https://doi.org/10.20965/ijat.2018.p0376
4. [4] J. R. Kellner et al., “New opportunities for forest remote sensing through ultra-high-density drone lidar,” Surv. Geophys., Vol.40, pp. 959-977, 2019. https://doi.org/10.1007/s10712-019-09529-9
5. [5] N. Miura, T. F. Koyanagi, S. Yamada, and S. Yokota, “Classification of grass and forb species on riverdike using UAV LiDAR-based structural indices,” Int. J. Automation Technol., Vol.15, No.3, pp. 268-273, 2021. https://doi.org/10.20965/ijat.2021.p0268
6. [6] K. Khoshelham, H. Tran, and D. Acharya, “Indoor mapping eyewear: Geometric evaluation of spatial mapping capability of hololens,” Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci., Vol.XLII-2/W13, pp. 805-810, 2019. https://doi.org/10.5194/isprs-archives-xlii-2-w13-805-2019
7. [7] M. Weinmann et al., “3D indoor mapping with the microsoft hololens: Qualitative and quantitative evaluation by means of geometric features,” ISPRS Ann. Photogramm. Remote Sens. Spat. Inf. Sci., Vol.V-1-2020, pp. 165-172, 2020. https://doi.org/10.5194/isprs-annals-v-1-2020-165-2020
8. [8] C. Gollob, T. Ritter, R. Kraßnitzer, A. Tockner, and A. Nothdurft, “Measurement of forest inventory parameters with Apple iPad Pro and integrated LiDAR technology,” Remote Sens., Vol.13, No.16, Article No.3129, 2021. https://doi.org/10.3390/rs13163129
9. [9] L. T. Losè, A. Spreafico, F. Chiabrando, and F. Giulio Tonolo, “Apple LiDAR sensor for 3D surveying: Tests and results in the cultural heritage domain,” Remote Sens., Vol.14, No.17, Article No.4157, 2022. https://doi.org/10.3390/rs14174157
10. [10] T. Mizoguchi et al., “Quantitative scaling evaluation of concrete structures based on terrestrial laser scanning,” Autom. Constr., Vol.35, pp. 263-274, 2013. https://doi.org/10.1016/j.autcon.2013.05.022
11. [11] T. Mizoguchi, A. Ishii, and H. Nakamura, “Individual tree species classification based on terrestrial laser scanning using curvature estimation and convolutional neural network,” Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci., Vol.XLII-2/W13, pp. 1077-1082, 2019. https://doi.org/10.5194/isprs-archives-xlii-2-w13-1077-2019
12. [12] Y. Midorikawa and H. Masuda, “Extraction of rotational surfaces and generalized cylinders from point-clouds using section curves,” Int. J. Automation Technol., Vol.12, No.6, pp. 901-910, 2018. https://doi.org/10.20965/ijat.2018.p0901
13. [13] R. Akiyama, H. Date, S. Kanai, and K. Yasutake, “Ceiling equipment extraction from TLS point clouds for reflected ceiling plan creation,” Int. J. Automation Technol., Vol.18, No.5, pp. 603-612, 2024. https://doi.org/10.20965/ijat.2024.p0603
14. [14] D. Griffiths and J. Boehm, “A review on deep learning techniques for 3D sensed data classification,” Remote Sens., Vol.11, Issue 12, Article No.1499, 2019. https://doi.org/10.3390/rs11121499
15. [15] R. Q. Charles, H. Su, M. Kaichun, and L. J. Guibas, “PointNet: Deep learning on point sets for 3D classification and segmentation,” 2017 IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 77-85, 2017. https://doi.org/10.1109/cvpr.2017.16
16. [16] C. R. Qi, L. Yi, H. Su, and L. J. Guibas, “PointNet++: Deep hierarchical feature learning on point sets in a metric space,” Proc. 31st Int. Conf. Neural Inf. Process. Syst., pp. 5105-5114, 2017.
17. [17] E. Sanchez Castillo, D. Griffiths, and J. Boehm, “Semantic segmentation of terrestrial lidar data using co-registered RGB data,” Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci., Vol.XLIII-B2-2021, pp. 223-229, 2021. https://doi.org/10.5194/isprs-archives-xliii-b2-2021-223-2021
18. [18] F. Remondino, “Heritage recording and 3D modeling with photogrammetry and 3D scanning,” Remote Sens., Vol.3, Issue 6, pp. 1104-1138, 2011. https://doi.org/10.3390/rs3061104
19. [19] M. Pepe, V. S. Alfio, and D. Costantino, “UAV platforms and the SfM-MVS approach in the 3D surveys and modelling: A review in the cultural heritage field,” Appl. Sci., Vol.12, Issue 24, Article No.12886, 2022. https://doi.org/10.3390/app122412886
20. [20] N. Saovana, N. Yabuki, and T. Fukuda, “Automated point cloud classification using an image-based instance segmentation for structure from motion,” Autom. Constr., Vol.129, Article No.103804, 2021. https://doi.org/10.1016/j.autcon.2021.103804
21. [21] E. Pellis et al., “2D to 3D label propagation for the semantic segmentation of heritage building point clouds,” Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci., Vol.XLIII-B2-2022, pp. 861-867, 2022. https://doi.org/10.5194/isprs-archives-xliii-b2-2022-861-2022
22. [22] L. Windrim and M. Bryson, “Forest tree detection and segmentation using high resolution airborne LiDAR,” IEEE/RSJ Int. Conf. Intell. Robots Syst. (IROS), pp. 3898-3904, 2019. https://doi.org/10.1109/iros40897.2019.8967885
23. [23] A. Boulch, J. Guerry, B. L. Saux, and N. Audebert, “SnapNet: 3D point cloud semantic labeling with 2D deep segmentation networks,” Comput. Graph., Vol.71, pp. 189-198, 2018. https://doi.org/10.1016/j.cag.2017.11.010
24. [24] Y. Wen et al., “Semantic BIM enrichment for firefighting assets: Fire-ART dataset and panoramic image-based 3D reconstruction,” ISPRS J. Photogramm. Remote Sens., Vol.231, pp. 679-703, 2026. https://doi.org/10.1016/j.isprsjprs.2025.11.015
25. [25] O. Ronneberger, P. Fischer and T. Brox, “U-Net: Convolutional networks for biomedical image segmentation,” Proc. 18th Int. Conf. Med. Image Comput. and Comput.-Assist. Interv. (MICCAI), Part 3, pp. 234-241, 2015. https://doi.org/10.1007/978-3-319-24574-4_28
26. [26] K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” Int. Conf. Learn. Represent., 2014.
27. [27] J. Deng et al., “ImageNet: A large-scale hierarchical image database,” 2009 IEEE Conf. Comput. Vis. Pattern Recognit., pp. 248-255, 2009. https://doi.org/10.1109/cvpr.2009.5206848