UDC: 
DOI: 
10.22389/0016-7126-2020-961-7-47-55
1 Yunusov A.G.
2 Jdeed A.J.
3 Begliarov N.S.
4 Elshewy M.A.
Year: 
№: 
961
Pages: 
47-55

State University Of Land Use Planning

1, 
2, 
3, 
4, 
Abstract:
Laser scanning is considered as one of the most useful and fast technologies for modelling. On the other hand, the size of scan results can vary from hundreds to several million points. As a result, the large volume of the obtained clouds leads to complication at processing the results and increases the time costs. One way to reduce the volume of a point cloud is segmentation, which reduces the amount of data from several million points to a limited number of segments. In this article, we evaluated effect on the performance, the accuracy of various segmentation methods and the geometric accuracy of the obtained models at density changes taking into account the processing time. The results of our experiment were compared with reference data in a form of comparative analysis. As a conclusion, some recommendations for choosing the best segmentation method were proposed.
References: 
1.   Velizhev A. B., Shapovalov R. V., Potapov D., Tret'yak L., Konushin A. S. Avtomaticheskaya segmentatsiya oblakov tochek na osnove elementov poverkhnosti. GraphiCon, 2009, no. 5, pp. 241–245.
2.   Dzhadid A. Kontrol' kachestva trekhmernoi modeli pamyatnika arkhitektury, poluchennoi na osnove dannykh nazemnogo lazernogo skanirovaniya. Zemleustroistvo, kadastr i monitoring zemel', 2018, no. 2, pp. 56–63.
3.   Dzhdid A. D. Obzor metodov segmentatsii i klassifikatsii oblaka tochek arkhitekturnykh ob"ektov. Izv. vuzov. Geodeziya i aerofotos"emka, 2019, no. 1, pp. 52–59. DOI: 10.30533/0536-101X-2019-63-1-52-59.
4.   Komissarov A. V. Teoriya i tehnologiya lazernogo skanirovaniya dlya prostranstvennogo modelirovaniya territorij: Dis. na soisk. uch. step. d-ra tehn. nauk: 25.00.34. Novosibirsk: SGUGiT, 2015, 278 p.
5.   Kochneva A. A. Razrabotka modifitsirovannykh tsifrovykh modelei rel'efa po dannym vozdushnogo lazernogo skanirovaniya dlya proektirovaniya avtodorog: Dis. na soisk. uch. step. kand. tekhn. nauk: 25.00.32. SPb.: Sankt- Peterburgskii gosudarstvennyi gornyi universitet, 2018, 144 p.
6.   Litvinov K. F. Lazernoe skanirovanie arkhitekturnykh ob"ektov. Sb. dokladov XVIII Mezhdunar. nauch.-prakt. konf, 2012, no. 18, pp. 287–288.
7.   Seredovich V.A., Komissarov A.V., Komissarov D.V., Shirokova T.A. Nazemnoe lazernoe skanirovanie. Novosibirsk: SGGA, 2009, 261 p.
8.   Tulup'ev A. L., Nikolenko S. I. Samoobuchayushchiesya sistemy. Moskva: MTsNMO, 2009, 288 p.
9.   Shapovalov R. V., Velizhev A. B., Barinova O. V., Konushin A. S. Semanticheskaya segmentatsiya dannykh lazernogo skanirovaniya. Programmnye produkty i sistemy, 2012, no. 1, pp. 47–51.
10.   Boardman C. (2018) 3D Laser Scanning for Heritage. Historic England, England, Swindon, 119 p.
11.   Castillo E., Liang J., Zhao H. (2013) Point Cloud Segmentation and Denoising via Constrained Nonlinear Least Squares Normal Estimates. Innovations for Shape Analysis, no. 1, pp. 283-299. DOI: 10.1007/978-3-642-34141-0_13.
12.   Che E., Olsen M. (2017) Fast edge detection and segmentation of terrestrial laser scans through normal variation analysis. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, no. 4, pp. 51-57. DOI: 10.5194/isprs-annals-IV-2-W4-51-2017.
13.   Grilli E., Menna F., Remondino F. (2017) A review of point clouds segmentation and classification algorithms. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, no. 42, pp. 339-344. DOI: 10.5194/isprs-archives-XLII-2-W3-339-2017.
14.   Jagannathan A., Miller E. (2007) Three-dimensional surface mesh segmentation using curvedness-based region growing approach. IEEE Transactions on Pattern Analysis and Machine Intelligence, no. 29, pp. 2195-2204. DOI: 10.1109/TPAMI.2007.1125.
15.   Kucak R., Ozdemir E., Erol S. (2017) The segmentation of point clouds with K-means and ANN (artifical neural network). The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, no. 42, pp. 595-598. DOI: 10.5194/isprs-archives-XLII-1-W1-595-2017.
16.   Li L., Yang F., Zhu H., Li D., Li Y., Tang L. (2017) An improved RANSAC for 3D point cloud plane segmentation based on normal distribution transformation cells. Remote Sens, no. 9, pp. 433-449. DOI: 10.3390/rs9050433.
17.   Liu Y., Xiong Y. (2008) Automatic segmentation of unorganized noisy point clouds based on the gaussian map. Computer-Aided Design, no. 40, pp. 576-594. DOI: 10.1016/j.cad.2008.02.004.
18.   Lu X., Yao J., Tu J., Li K., Li L., Liu Y. (2016) Pairwise Linkage for Point Cloud Segmentation. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, no. 3, pp. 201-208. DOI: 10.5194/isprsannals-III-3-201-2016.
19.   Martino M., Hernandez G., Fiori M., Fernandez A. (2013) A new framework for optimal classifier design. Pattern Recognition-Elsevier, no. 8, pp. 2249-2255. DOI: 10.1016/j.patcog.2013.01.006.
20.   Nguyen A., Le B. (2013) 3D point cloud segmentation: A survey. Proceedings of the 6th International Conference on Robotics, Automation and Mechatronics. Manila, Philippines. pp. 255-230. DOI: 10.1109/RAM.2013.6758588.
21.   Rabbani T., Heuvelb F., Vosselman G. (2006) Segmentation of point clouds using smoothness constraint. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, no. 36, pp. 248-253.
22.   Sithole G., Vosselman G. (2004) Experimental comparison of filter algorithms for bare-Earth extraction from airborne laser scanning point clouds. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, no. 59, pp. 85-101. DOI: 10.1016/j.isprsjprs.2004.05.004.
Citation:
Yunusov A.G., 
Jdeed A.J., 
Begliarov N.S., 
Elshewy M.A., 
(2020) Assessment of automatic segmentation accuracy with various point cloud density. Geodesy and cartography = Geodezia i Kartografia, 81(7), pp. 47-55. (In Russian). DOI: 10.22389/0016-7126-2020-961-7-47-55