Application of existing algorithms for classification and clustering of laser reflection points (k-Means, DBSCAN, SVM) to solve territorial planning problems
https://doi.org/10.21822/2073-6185-2023-50-1-75-80
Abstract
Objective. The aim of the study is to generalize the experience of using and reveal the features of methods for classifying and clustering images obtained by laser scanning.
Method. The study is based on the use of algorithms for recognition, clustering and classification of data obtained using laser scanning.
Result. A brief review of existing algorithms used for clustering images obtained by laser scanning has been carried out. The possibility of using sequentially the K-means and DBSCAN algorithms for clustering in relation to objects of various shapes is shown. The possibilities of using algorithms for the classification and clustering of laser reflection points (k-Means, DBSCAN, SVM) in the framework of solving territorial planning problems are analyzed.
Conclusion. The use of the presented algorithms makes it possible to form data arrays that, when superimposed on each other subsequently and further processed, make it possible to obtain even more accurate representations of objects and territories in territorial planning documents, and in the future, based on the use of machine learning methods and processing of data matrices available in memory, get more accurate information about objects on the ground.
About the Authors
D. A. Gura
Kuban State Technological University
Russian Federation
Russian Federation
Dmitry A. Gura, Cand. Sci. (Eng), Assoc. Prof., Department of Cadastre and Geoengineering
2 Moskovskaya St., Krasnodar 350072
O. S. Boltovnina
Kuban State Technological University
Russian Federation
Russian Federation
Olga S. Boltovnina, Student, Department of Cadastre and Geoengineering
2 Moskovskaya St., Krasnodar 350072
References
1. Town Planning Code of the Russian Federation of December 29, 2004 N 190-FZ (as amended on December 30, 2021)(as amended and supplemented, effective from January 1, 2022). Consultant. URL: http://www.consultant.ru/document/cons_doc_LAW_51040/fe0cad704c69e3b97bf615f0437ecf1996a5767
2. Bogdanov A.N., Aleshutin I.A. Terrestrial laser scanning in construction and vim-technologies. Proceedings of the Kazan State University of Architecture and Civil Engineering, 2018; 4 (46): 326-332.[In Russ]
3. D. A. Gorokhov, D. S. Ozhigin, S. B. Ozhigina, N. A. Dorosh, D. A. Kulygin, and Yu. Instrumental observations of the deformations of technogenic objects. Interexpo Geo-Siberia, 2017; 1(1): 135-139. [In Russ]
4. Karkishchenko A.N. Levashev S.P. Object recognition method based on laser scanning data based on spectral graph theory. Izvestiya SFedU. Technical science. 2019; 3 (205): 72-85.[In Russ]
5. Kiyamov I.K., Mingazov R.Kh., Muzafarov A.F., Ibragimov R.A., Sibgatullin A.A. Laser scanning technology in 3D design. Oil and Gas Exposition, 2013; 7 (32): 41-43 .[In Russ]
6. Kovach N.S. Mapping of linear engineering objects according to laser scanning data. Bulletin of Moscow University. Series 5. Geography, 2013; 1: 47-54.[In Russ]
7. Koshan E.K. Possibilities, advantages and disadvantages of terrestrial laser scanning. Interexpo GeoSiberia, 2017; 9(1): 27-30.[In Russ]
8. Lenchenkova E.P. Modeling the route of the railway track based on the results of mobile laser scanning. Bulletin of the Petersburg University of Railway Transport, 2018; 15(3): 408-413.[In Russ]
9. Levashev S.P. Recognition of 3D objects based on spectral invariants using deep machine learning. Bulletin of the Southern Federal University. Technical sciences, 2019; 3 (205): 20-31.[In Russ]
10. Pantyukhin D.V., Nguyen Dang Tao, Vu Viet Thang Application of a neural network of the multilayer perceptron type for recognizing the type of attack on an information system on the example of the KDD'99 base. XI All-Russian Scientific Conference "Neurocomputers and their applications", March 17, 2015 , MSUPU.[In Russ]
11. Seredovich V.A., Ivanov A.V., Seredovich A.V., Gorokhova E.I., Borodulina I.V., Romanovich E.V. Application of terrestrial laser scanning to control the construction and overhaul of highways. Interexpo GeoSiberia, 2010; 1(3): 69-72.[In Russ]
12. Seredovich V.A., Altyntsev M.A., Egorov A.K. Determination of the evenness index of the road surface according to mobile laser scanning data. Vestnik SSUGiT (Siberian State University of Geosystems and Technologies), 2017; 22(3): 33-44.[In Russ]
13. Sozykin A.V. Overview of learning methods for deep neural networks. Bulletin of SUSU. Series: Numerical Mathematics and Informatics. 2017. №3. URL: https://cyberleninka.ru/article/n/obzor-metodovobucheniya-glubokih-neyronnyh-setey (date of access: 12/13/2022)[In Russ]
14. Kholodov P. N., Titov K. M., Podverbny V. A. Modeling the plan of the axis of the railway track and its changes during operation. Sovremennye tekhnologii. System analysis. Modeling, 2019;1(61):74-81[In Russ]
15. Sholomitsky A.A., Lagutina E.K., Soboleva E.L. Application of laser scanning for monitoring of largespan structures. Bulletin of SGUGiT (Siberian State University of Geosystems and Technologies), 2018; 23(2): 43-57[In Russ]
16. Shokina M.O. Application of the k-means++ algorithm for clustering sequences with an unknown number of clusters. New information technologies in automated systems, 2017; 20: 160-163.[In Russ]
17. Cho M., Alahari K., Ponce J. Learning graphs to match, in IEEE Interational Conference on Computer Vision (ICCV), 2013; 25-32.
18. Chavel I. Riemannian Geometry: A Modern Introduction. Cambridge University Press, Cambridge, 2006; 98: 471.
19. Krizhevsky A., Sutskever I., Hinton G.E. ImageNet classification with deep convolutional neural networks. NIPS'12 Proceedings of the 25th International Conference on Neural Information Processing Systems. Lake Tahoe, USA, 2012; 1097-1105.
20. Macrini D., Siddiqi K., Dickinson S. From Skeletons to Bone Graphs: Medial Abstraction for Object Recog-nition. 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR. Anchorage, Alaska, USA, 2008; 1-8.
Review
For citations:
Gura D.A., Boltovnina O.S. Application of existing algorithms for classification and clustering of laser reflection points (k-Means, DBSCAN, SVM) to solve territorial planning problems. Herald of Dagestan State Technical University. Technical Sciences. 2023;50(1):75-80. (In Russ.) https://doi.org/10.21822/2073-6185-2023-50-1-75-80
Views:
218
Email this article 
