Segmentation of Structural Elements from 3D Point Cloud Using Spatial Dependencies for Sustainability Studies
Abstract
:1. Introduction
- It accelerates the rate of estimation of the local saliency features in a noisy and large point cloud. This is done by decomposing the point cloud into well-defined voxels for reliable statistical computations using an optimum number of samples in voxels.
- It develops novel techniques for classifying the detected planar surfaces into well-defined structural elements using the spatial dependency and topology of structural forms.
2. Related Works
2.1. Literature Search
2.2. Point Cloud Geometry
2.3. Clustering and Segmentation Approaches
2.4. Deep Learning Application in Semantic Segmentation
3. Methodology
3.1. Overall Methodology
3.2. Spatial Subdivision of the Point Cloud
3.3. Planar Patch Detection
3.4. Merging Planar Patches
3.5. Search for Remote Coplanar Patches and Points
3.5.1. Determination of Principal Patches
- (a)
- The orthogonal distance and angular value between the approximate parallel patchesA tolerance (t) is used to define the maximal orthogonal distance between the two parallel patches, which is equivalent to the standard thickness of common structural elements. The value of t, where t ≤ 50 cm between the two neighboring parallel planar patches, is used to assign the candidate pairs of parallel patches. For two patches to be parallel, we consider the maximum angular value of not more than 5° between their normals (i & i+1).
- (b)
- Patch sizesThis part deals with the comparison of patch coverage by their surface areas. The two parallel patches (Ri & Ri+1) with surface areas (l × w, measured on their extreme edges), As(i) and As(i+1), respectively, are compared against one another to enhance the picking of true patches representing structural elements as opposed to occluding objects in the vicinity.Given two adjacent and parallel patches, we set a condition regarding a difference in their surface areas (dA) using Equation (3), such that the ratio dA/As(i) or dA/As(i+1) (whichever is larger between As(i) and As(i+1)) is not more than 20%. We opted to use the surface areas instead of the number of points in a patch, which is influenced by point density that varies depending on the distance between the sensor and an object [33].dA = |As(i) − As(i+1)|
- (c)
- Patch overlapIn consideration of Section 3.5.1a,b, which only deals with the adjacency and matching sizes between two parallel planar patches, however, the two patches may still represent surfaces from two different objects. To solve this, we introduce a patch-alignment criterion whereby the two parallel patches have to coherently overlap by more than 50% of their surface areas (As) as displayed in Figure 8.
3.5.2. Spanning of Principal Planes
3.5.3. Points Assignment to Principal Planes
- (a)
- Points-to-Plane-Approximation
- (b)
- Outlier testing
- (c)
- Coplanarity testing
3.6. Refining Pairs of Principal Patches
3.7. Plane Classification
- Horizontal Planes, ℿh (including nearly horizontal planes): comprises pairs of planes with their normal vectors, h, oriented at an angle (Ɵ) < 45° to the z-axis;
- Vertical Planes, ℿv (including nearly vertical planes): comprises pairs of planes with normal vectors, v, oriented at an angle (Ɵ) ≥ 45° to the z-axis.
3.7.1. Floor Slabs
- ℿh(0,j), for planes representing floors (upper skin of the slab), where j = {1, 2,…, n} corresponding to the floor levels;
- ℿh(i,0), for planes representing ceilings (bottom skin of the slab), where i = {2, 1,…, n} at a corresponding floor level.
3.7.2. Floor Beams
- The normals, v, of a particular pair of vertical planes (ℿv), should be perpendicular (or nearly so) to the normal direction, h, of a soffit’s plane, Ꝓh(i);
- The orthogonal distance between the pair of vertical planes (i.e., ℿV(i) ↔ ℿV(i+1)) is approximately equal to the breadth of the associated soffit’s plane, Ꝓh(i);
- The height of vertical planes (ℿv) should correspond to the distance between the ceiling’s plane (ℿh(i,0)) and the associated plane for the beam’s soffit (Ꝓh(i)).
3.7.3. Walls and Columns
4. Experimental Results
4.1. Overview
4.2. Dataset and Instrument
4.3. Evaluation Metrics
4.4. Preliminary Data Processing
4.5. Generation and Merging of Planar Patches
4.5.1. Spatial Sub-Division
4.5.2. Planar Patch Generation
4.5.3. Merging of Planar Patches
4.6. Plane Classification
4.6.1. Floor Slabs
4.6.2. Floor Beams
4.6.3. Walls and Columns
5. Discussion
5.1. Evaluation of Points Classification
5.2. Evaluation of Plane Extraction and Segmentation
5.3. Comparative Evaluation
5.4. Limitations and Future Works
6. Conclusions
Author Contributions
Funding
Acknowledgments
Conflicts of Interest
References
- Chao, W.; Yong, K.C. Performance Evaluation of Automatically Generated BIM from Laser Scanner Data for Sustainability Analyses. In Proceedings of the International Conference on Sustainable Design, Engineering, and Construction, Chicago, IL, USA, 10–13 May 2015; Volume 118, pp. 918–925. [Google Scholar] [CrossRef]
- Dixit, M.K. An Input-Output-based Hybrid Recurrent Embodied Energy Calculation Model for Commercial Facilities. In Proceedings of the CIB World Building Congress, Tampere, Finland, 31 May–3 June 2016. [Google Scholar]
- Yuanbo, G.; Ziteng, W.; Lei, S.; Jianan, Z. Calculating of CO2 emission factors for Chinese cement production based on inorganic carbon and organic carbon. J. Clean. Prod. 2019, 217, 503–509. [Google Scholar] [CrossRef]
- Ansah, M.K.; Xi, C.; Hongxing, Y.; Lin, L.; Patrick, T.I.L. Developing an automated BIM-based life cycle assessment approach for modularly designed high-rise buildings. Environ. Impact Assess. Rev. 2021, 90, 106618. [Google Scholar] [CrossRef]
- Cristiane, B.; Márcio, M.F. Comparative analysis between a complete LCA study and results from a BIM-LCA plug-in. Autom. Constr. 2018, 90, 188–200. [Google Scholar] [CrossRef]
- Abanda, F.H.; Oti, A.H.; Tah, J.H.M. Integrating BIM and new rules of measurement for embodied energy and CO2 assessment. J. Build. Eng. 2017, 12, 288–305. [Google Scholar] [CrossRef]
- Braun, A.; Tuttas, S.; Stilla, U.; Borrmann, A. Process and computer vision-based detection of as-built components on construction sites. In Proceedings of the ISARC—35th International Symposium on Automation and Robotics in Construction, Berlin, Germany, 20–25 July 2018. [Google Scholar] [CrossRef]
- Qian, W.; Min-Koo, K. Applications of 3D point cloud data in the construction industry: A fifteen-year review from 2004 to 2018. Adv. Eng. Inform. 2019, 39, 306–319. [Google Scholar] [CrossRef]
- Vincke, S.; Hernandez, R.L.; Bassier, M.; Vergauwen, M. Immersive visualization of construction site point cloud data, meshes and BIM models in a VR environment using a gaming engine. In Proceedings of the ISPRS—The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Prague, Czech Republic, 24–25 September 2019; Volume XLII-5/W2, pp. 77–83. [Google Scholar] [CrossRef]
- Poux, F.; Billen, R. Voxel-based 3D Point Cloud Semantic Segmentation: Unsupervised Geometric and Relationship Featuring vs. Deep Learning Methods. ISPRS Int. J. Geo Inf. 2019, 8, 213. [Google Scholar] [CrossRef]
- Poux, F.; Neuville, R.; Hallot, P.; Billen, R. Model for Semantically Rich Point Cloud Data. In Proceedings of the ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Melbourne, Australia, 26–27 October 2017; Volume IV-4/W5, pp. 107–115. [Google Scholar] [CrossRef] [Green Version]
- Hajian, H.; Becerik-Gerber, B. Scan to BIM: Factors affecting operational and computational errors and productivity loss. In Proceedings of the ISARC—27th International Symposium on Automation and Robotics in Construction, Bratislava, Slovakia, 25–27 June 2010; pp. 265–272. [Google Scholar] [CrossRef]
- Xuehan, X.; Antonio, A.; Burcu, A.; Daniel, H. Automatic creation of semantically rich 3D building models from laser scanner data. Autom. Constr. 2013, 31, 325–337. [Google Scholar] [CrossRef]
- Abner, M.C.A.; Manuel, M.O. A robust statistics approach for plane detection in unorganized point clouds. Pattern Recognit. 2020, 100, 107115. [Google Scholar] [CrossRef]
- Anh-Vu, V.; Linh, T.; Debra, F.L.; Michela, B. Octree-based region growing for point cloud segmentation. ISPRS J. Photogramm. Remote Sens. 2015, 104, 88–100. [Google Scholar] [CrossRef]
- Hyojoo, S.; Changwan, K. Semantic as-built 3D modeling of structural elements of buildings based on local concavity and convexity. Adv. Eng. Inform. 2017, 34, 114–124. [Google Scholar] [CrossRef]
- Hyunsoo, K.; Changwan, K. 3D as-built modeling from incomplete point clouds using connectivity relations. Autom. Constr. 2021, 130, 103855. [Google Scholar] [CrossRef]
- Maalek, R.; Lichti, D.D.; Ruwanpura, J. Robust Classification and segmentation of planar and linear features for construction site progress monitoring and structural dimension compliance control. In Proceedings of the ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, La Grande Motte, France, 28 September–3 October 2015; Volume II-3/W5. [Google Scholar] [CrossRef]
- Qian, W.; Min-Koo, K.; Jack, C.P.C.; Hoon, S. Automated quality assessment of precast concrete elements with geometry irregularities using terrestrial laser scanning. Autom. Constr. 2016, 68, 170–182. [Google Scholar] [CrossRef]
- Fatemeh, H. Point cloud segmentation and classification of structural elements in multi-planar masonry building facades. Autom. Constr. 2020, 118, 103232. [Google Scholar] [CrossRef]
- Andrey, D.; Mani, G. Segmentation of building point cloud models including detailed architectural/structural features and MEP systems. Autom. Constr. 2015, 51, 32–45. [Google Scholar] [CrossRef]
- Mura, C.; Mattausch, O.; Pajarola, R. Piecewise-planar reconstruction of multi-room interiors with Arbitrary wall arrangements. Comput. Graph. Forum. 2016, 35, 179–188. [Google Scholar] [CrossRef]
- Jean-Emmanuel, D.; François, G. A Fast and Accurate Plane Detection Algorithm for Large Noisy Point Clouds Using Filtered Normals and Voxel Growing. In Proceedings of the 3D Data Processing Visualization and Transmission, Paris, France, 20 May 2010. [Google Scholar]
- Maalek, R.; Lichti, D.D.; Ruwanpura, J.Y. Automatic Recognition of Common Structural Elements from Point Clouds for Automated Progress Monitoring and Dimensional Quality Control in Reinforced Concrete Construction. Remote Sens. 2019, 11, 1102. [Google Scholar] [CrossRef]
- Schnabel, R.; Wahl, R.; Klein, R. Efficient RANSAC for point-cloud shape detection. Comput. Graph. Forum 2007, 26, 214–226. [Google Scholar] [CrossRef]
- Sungchul, H.; Jaehoon, J.; Sangmin, K.; Hyoungsig, C.; Jeongho, L.; Joon, H. Semi-automated approach to indoor mapping for 3D as-built building information modeling. Comput. Environ. Urban Syst. 2015, 51, 34–46. [Google Scholar] [CrossRef]
- Li, L.; Yang, F.; Zhu, H.; Li, D.; Li, Y.; Tang, L. An Improved RANSAC for 3D Point Cloud Plane Segmentation Based on Normal Distribution Transformation Cells. Remote Sens. 2017, 9, 433. [Google Scholar] [CrossRef]
- Borrmann, D.; Elseberg, J.; Lingemann, K.; Nüchter, A. The 3D Hough Transform for plane detection in point clouds: A review and a new accumulator design. 3D Res. 2 2011, 3, 3. [Google Scholar] [CrossRef]
- Kultanen, P.; Xu, L.; Oja, E. Randomized Hough transform (RHT). In Proceedings of the Pattern Recognition, 10th International Conference, Atlantic City, NJ, USA, 16–21 June 1990. [Google Scholar] [CrossRef]
- Díaz-Vilariño, L.; Conde, B.; Lagüela, S.; Lorenzo, H. Automatic Detection and Segmentation of Columns in As-Built Buildings from Point Clouds. Remote Sens. 2015, 7, 15651–15667. [Google Scholar] [CrossRef]
- Nurunnabi, A.; Belton, D.; West, G. Robust segmentation for multiple planar surface extraction in laser scanning 3D point cloud data. In Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012), Tsukuba, Japan, 11–15 November 2012. [Google Scholar]
- Kang, C.; Wang, F.; Zong, M.; Cheng, Y.; Lu, T. Research on improved region growing point cloud algorithm. In Proceedings of the ISPRS—The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Guilin, China, 7 February 2020; Voloume XLII-3/W10, pp. 153–157. [Google Scholar] [CrossRef]
- Rabbani, T.; Heuvel, F.A.; Vosselman, G. Segmentation of point clouds using smoothness constraint. ISPRS Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. 2006, 36, 248–253. [Google Scholar]
- Rusu, R.B.; Cousins, S. 3D is here: Point Cloud Library (PCL). In Proceedings of the 2011 IEEE International Conference on Robotics and Automation, Shanghai, China, 9–13 May 2011. [Google Scholar]
- Valero, E.; Adan, A.; Cerrada, C. Automatic Construction of 3D Basic-Semantic Models of Inhabited Interiors Using Laser Scanners and RFID Sensors. Sensors 2012, 12, 5705–5724. [Google Scholar] [CrossRef] [Green Version]
- Xijiang, C.; Hao, W.; Derek, L.; Xianquan, H.; Ya, B.; Peng, L.; Hui, D. Extraction of indoor objects based on the exponential function density clustering model. Autom. Constr. 2022, 607, 1111–1135. [Google Scholar] [CrossRef]
- Qi, C.R.; Su, H.; Mo, K.; Guibas, L.J. PointNet: Deep learning on point sets for 3D classification and segmentation. In Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 21 June–26 July 2017; p. 77. [Google Scholar]
- Qi, C.R.; Yi, L.; Su, H.; Guibas, L.J. PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space. In Proceedings of the Conference on Neural Information Processing Systems (NIPS), Long Beach, CA, USA, 24 January 2019. [Google Scholar]
- Yue, W.; Yongbin, S.; Ziwei, L.; Sanjay, E.S.; Michael, M.B.; Justin, M.S. Dynamic Graph CNN for Learning on Point Clouds. ACM Trans. Graph. 2019, 38, 146. [Google Scholar] [CrossRef]
- Kim, H.; Yoon, J.; Sim, S.H. Automated bridge component recognition from point clouds using deep learning. Struct. Control Health Monit. 2020, 27, e2591. [Google Scholar] [CrossRef]
- Bolourian, N.; Nasrollahi, M.; Bahreini, F.; Hammad, A. Point Cloud-Based Concrete Surface Defect Semantic Segmentation. J. Comput. Civ. Eng. 2023, 37, 04022056. [Google Scholar] [CrossRef]
- Zhang, J.; Zhao, X.; Chen, Z.; Lu, Z. A Review of Deep Learning-Based Semantic Segmentation for Point Cloud. IEEE Access 2019, 7, 179118–179133. [Google Scholar] [CrossRef]
- Sandaker, B.N.; Kleven, B.; Wang, A.R. Structural typologies and the architectural space-Studies of the relationship between structure and space by application of structural types to multistory buildings. Archit. Struct. Constr. 2022, 2, 199–221. [Google Scholar] [CrossRef]
- Li, H.; Liu, Y.; Men, C. A novel 3D point cloud segmentation algorithm based on multi-resolution supervoxel and MGS. Int. J. Remote Sens. 2021, 42, 8492–8525. [Google Scholar] [CrossRef]
- Xu, Y.; Tong, X.; Stilla, U. Voxel-based representation of 3D point clouds: Methods, applications, and its potential use in the construction industry. Autom. Constr. 2021, 126, 103675. [Google Scholar] [CrossRef]
- Wang, M.; Tseng, Y. Incremental segmentation of lidar point clouds with an octree-structured voxel space. Photogramm. Rec. 2011, 26, 32–57. [Google Scholar] [CrossRef]
- Woo, H.; Kang, E.; Wang, S.; Lee, K.H. A new segmentation method for point cloud data. Int. J. Mach. Tools Manuf. 2002, 42, 167–178. [Google Scholar] [CrossRef]
- Frederico, A.L.; Manuel, M.O. Real-time detection of planar regions in unorganized point clouds. Pattern Recognit. 2015, 48, 2043–2053. [Google Scholar] [CrossRef]
- Shahid, S.S.; Toqeer, A.R.; Moazzam, A.K. Impact of sample size on principal component analysis ordination of an environmental data set: Effects on eigenstructure. Ekológia 2016, 35, 173–190. [Google Scholar] [CrossRef]
- Osborne, J.W.; Costello, A.B. Sample size and subject to item ratio in principal components analysis. Pract. Assess. Res. Eval. 2004, 9, 11. [Google Scholar] [CrossRef]
- Forcino, F.L. Multivariate assessment of the required sample size for community paleoecological research. Palaeogeogr. Palaeoclimatol. Palaeoecol. 2012, 315–316, 134–141. [Google Scholar] [CrossRef]
- Berkmann, J.; Caelli, T. Computation of surface geometry and segmentation using covariance techniques. IEEE Trans. Pattern Anal. Mach. Intell. 1994, 16, 1114–1116. [Google Scholar] [CrossRef]
- Golub, G.H.; Van Loan, C.F. An analysis of the total least squares problem. SIAM J. Numer. Anal. 1980, 17, 883–893. [Google Scholar] [CrossRef]
- Hui, C.; Man, L.; Wanquan, L.; Weina, W.; Peter, X.L. An approach to boundary detection for 3D point clouds based on DBSCAN clustering. Pattern Recognit. 2022, 124, 108431. [Google Scholar] [CrossRef]
- Rousseeuw, P.J.; Croux, C. Alternatives to the median absolute deviation. J. Am. Stat. Assoc. 1993, 88, 1273–1283. [Google Scholar] [CrossRef]
- Jianbing, H.; Chia-Hsiang, M. Automatic data segmentation for geometric feature extraction from unorganized 3-D coordinate points. IEEE Trans. Robot. Autom. 2001, 17, 268–279. [Google Scholar] [CrossRef]
- Zhang, X.; Shen, X.; Ouyang, T. Extension of DBSCAN in Online Clustering: An Approach Based on Three-Layer Granular Models. Appl. Sci. 2022, 12, 9402. [Google Scholar] [CrossRef]
- Ouyang, T. Structural rule-based modeling with granular computing. Appl. Soft Comput. 2022, 128, 109519. [Google Scholar]
- Sawant, K. Adaptive Methods for Determining DBSCAN Parameters. IJISET Int. J. Innov. Sci. Eng. Technol. 2014, 1, 55910147. [Google Scholar]
- Liu, P.; Zhou, D.; Wu, N. VDBSCAN: Varied Density Based Spatial Clustering of Applications with Noise. In Proceedings of the 2007 International Conference on Service Systems and Service Management, Chengdu, China, 9–11 June 2007; pp. 1–4. [Google Scholar] [CrossRef]
- Ram, G.S. Principles of Structural Design; Wood, Steel, and Concrete, 2nd ed.; CRC Press: Boca Raton, FL, USA, 2014. [Google Scholar]
- David, D.; Charles, D.W.; Arthur, N.H. Design of Concrete Structures, 15th ed.; McGraw-Hill Education: New York, NY, USA, 2016. [Google Scholar]
- Ochmann, S.; Vock, R.; Klein, R. Automatic reconstruction of fully volumetric 3D building models from oriented point clouds. ISPRS J. Photogramm. Remote Sens. 2019, 151, 251–262. [Google Scholar] [CrossRef]
- Linsen, L.; Muller, K.; Rosenthal, P. Splat-based ray tracing of point clouds. J. WSCG 2007, 15, 51–58. [Google Scholar]
- AIJ Standard for Structural Design of Reinforced Concrete Boxed-Shaped Wall Structures. Steering Committee for Wall Construction; Architectural Institute of Japan: Tokyo, Japan, 2022.
- Barker, H.A.; Fairbairns, R.F.; Lamont, R.C.; Maher, B.; Neild, A.P.; Willard, C.G. Standard Method of Measurement of Building Works for East Africa, 1st ed.; Quantity Surveyors-AAK: Nairobi, Kenya, 1976. [Google Scholar]
- Z+F Imager® 5016 Terrestrial Laser Scanner Datasheet and Key Performance Specifications. Available online: https://www.zofre.de/en/laser-scanners/3d-laser-scanner/z-f-imagerr-5016 (accessed on 1 December 2022).
- Olson, D.; Delen, D. Advanced Data Mining Techniques; Springer: Berlin/Heidelberg, Germany, 2008. [Google Scholar] [CrossRef]
- Salamanca, S.; Merchan, P.; Perez, E.; Adan, A.; Cerrada, C. Filling holes in 3D meshes using image restoration algorithms. In Proceedings of the 4th International Symposium on 3D Data Processing, Visualization, and Transmission (3DPVT), Atlanta, GA, USA, 18–20 June 2008. [Google Scholar]
- Macher, H.; Landes, T.; Grussenmeyer, P. From Point Clouds to Building Information Models: 3D Semi-Automatic Reconstruction of Indoors of Existing Buildings. Appl. Sci. 2017, 7, 1030. [Google Scholar] [CrossRef] [Green Version]
Experiment | No. of Scan Stations | No. of Points | Average Resolution Range | Average Range Error |
---|---|---|---|---|
Original Point cloud | 236 | 374,405,029 | 0.1 mm | 0.25 mm rms |
Test-data | N/A | 66,997,720 | 0.1 mm | 0.25 mm rms |
Metrics | Floor Slabs | Floor Beams | Walls | ||||
---|---|---|---|---|---|---|---|
Ceilings | Floors | 1 Slabs | Soffits | Vertical Sides | 1 Beams | ||
TP | 4 | 5 | 5 | 192.00 | 149.76 | 149.76 | 202.00 |
FP | 0 | 0 | 0 | 92.16 | 92.16 | 92.16 | 108.00 |
FN | 0 | 0 | 0 | 20.80 | 20.80 | 20.80 | 40.00 |
TN | 0 | 8 | 8 | 23.40 | 23.40 | 23.40 | 28.00 |
Precision | 1 | 1 | 1 | 0.68 | 0.62 | 0.62 | 0.65 |
Recall | 1 | 1 | 1 | 0.90 | 0.88 | 0.88 | 0.83 |
F1-score | 1 | 1 | 1 | 0.77 | 0.73 | 0.73 | 0.73 |
IoU | 1 | 1 | 1 | 0.63 | 0.57 | 0.57 | 0.58 |
Objects | Floor Slabs | Floor Beams | Walls | ||||||
---|---|---|---|---|---|---|---|---|---|
* Metrics | P | R | F1 | P | R | F1 | P | R | F1 |
Proposed method | 1 | 1 | 1 | 0.75 | 0.75 | 0.75 | 0.60 | 0.75 | 0.67 |
Density-based clustering [36] | 1 | 1 | 1 | 0.25 | 0.33 | 0.29 | 0.70 | 0.64 | 0.67 |
DGCNN with the neighbor network [17] | 1 | 1 | 1 | 0.67 | 0.67 | 0.67 | 0.70 | 0.70 | 0.70 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Ntiyakunze, J.; Inoue, T. Segmentation of Structural Elements from 3D Point Cloud Using Spatial Dependencies for Sustainability Studies. Sensors 2023, 23, 1924. https://doi.org/10.3390/s23041924
Ntiyakunze J, Inoue T. Segmentation of Structural Elements from 3D Point Cloud Using Spatial Dependencies for Sustainability Studies. Sensors. 2023; 23(4):1924. https://doi.org/10.3390/s23041924
Chicago/Turabian StyleNtiyakunze, Joram, and Tomo Inoue. 2023. "Segmentation of Structural Elements from 3D Point Cloud Using Spatial Dependencies for Sustainability Studies" Sensors 23, no. 4: 1924. https://doi.org/10.3390/s23041924
APA StyleNtiyakunze, J., & Inoue, T. (2023). Segmentation of Structural Elements from 3D Point Cloud Using Spatial Dependencies for Sustainability Studies. Sensors, 23(4), 1924. https://doi.org/10.3390/s23041924