Development and analysis of a road traffic monitoring system based on machine vision technologies and cluster analysis methods
https://doi.org/10.46973/0201-727X_2024_4_134
Abstract
This article presents a traffic monitoring system based on the principles of machine vision. The system is based on simple webcams mounted above the roadbed that capture images of vehicles. Further, using image processing algorithms and machine learning methods, the system determines the number and classification of vehicles on the road. The system includes several key modules: a background subtraction module, a foreground segmentation module, a contour acquisition module, a contour training and classification module, a property allocation module and a clustering module. Each of these modules performs specific functions aimed at ensuring accurate and reliable vehicle detection. The system has been tested on traffic images. The test results confirm the system's ability to adapt to various conditions and scenarios, which is critically important for video surveillance and traffic management systems. The article also discusses the prospects for further development of the system, including the possibility of using more complex neural network architectures and integration with other systems.
About the Authors
I. N. Pugachev
Khabarovsk Federal Research Center Far Eastern Branch of the Russian Academy of Sciences (KhRC FEB RAS);
Far Eastern State Transport University (FESTU)
Russian Federation
Russian Federation
Pugachev Igor Nikolaevich, Deputy Director for Research;
Chair «Surveying and Design of Railways and Highways», Doctor of Engineering Sciences, Professor
V. S. Tormozov
Pacific National University
Russian Federation
Russian Federation
Tormozov Vladimir Sergeevich, Candidate of Engineering Sciences, Associate Professor of the Higher School of Cybernetics and Digital Technologies
References
1. Bouwmans, T. Background Modeling using Mixture of Gaussians for Foreground Detection / T. Bouwmans, F. El Baf, B. Vachon. – A Survey. – Recent Patents on Computer Science. – November 2008. – DOI 10.2174/1874479610801030219.
2. Smids, M. Background Subtraction for Urban Traffic Monitoring using Webcams / M. Smids. – P. 1–43. – Universiteit van Amsterdam, FNWI, 2006.
3. Synergy of approaches to improving intelligent transport systems of cities in Russia and Belarus / I. N. Pugachev, D. V. Kapsky, D. V. Navoy [et al.]. – Khabarovsk : Pacific State University, 2020. – 230 p. – ISBN 978-5-7389-3154-3.
4. Pugachev, I. N. Improving methods for assessing the quality and safety of road traffic / I. N. Pugachev, N. G. Sheshera, A. V. Kamenchukov. – Khabarovsk : Publishing house of the Pacific State University, 2018. – 160 p.
5. Burkov, S. M. Tasks of system analysis and methodology for the formation of an intelligent control system for the city transport complex / S. M. Burkov, G. Ya. Markelov, I. N. Pugachev // Bulletin of the Pacific State University. – 2013. – No. 4. – P. 83–90. – ISSN 1996-3440.
6. Pham, D. L. Current methods in medical image segmentation / D. L. Pham, C. Xu, J. L. Prince // Annu Rev Biomed Eng. 2000;2:315-37. – DOI 10.1146/annurev.bioeng.2.1.315.
7. Koenderink, J. J. The structure of images / J. J. Koenderink // Biol Cybern. 1984 ; 50(5) : 363-70. – DOI 10.1007/BF00336961.
8. Tormozov, V. S. Counting and recognition of cars on satellite images / V. S. Tormozov // Scientific notes of PSU. – 2017. – Vol. 8. – No. 3. – P. 126–134. – ISSN 2079-8490.
9. Barrow, H. G. Interpreting line drawings as threedimensional surfaces / H. G. Barrow, J. M. Tenenbaum // Artificial Intelligence, 17(1–3), 75–116. – DOI 10.1016/0004-3702(81)90021-7.
10. Tormozov, V. S. Method of detection and classification of vehicles on ultra-high-resolution satellite images / V. S. Tormozov // Industrial ACS and controllers. – 2019. – No. 6. – P. 18–24. – DOI 10.25791/asu.06.2019.678.
11. Pugachev, I. N. Methodology for counting vehicles using high spatial resolution satellite images / I. N. Pugachev, G. Ya. Markelov, V. S. Tormozov // Bulletin of the Pacific State University. – 2017. – No. 2 (45). – P. 13–20. – EDN ZEGASL. – ISSN 1996-3440.
12. Pugachev, I. N. Acceleration of the algorithm for detecting vehicles on satellite images using the hypothesis filtering procedure / I. N. Pugachev, G. Ya. Markelov, V. S. Tormozov // Bulletin of the Russian New University. Series : Complex Systems : Models, Analysis and Control. – 2019. – No. 1. – P. 130–139. – DOI 10.25586/RNU.V9187.19.01.P.130.
13. Vezhnevets, A. Avoiding boosting overfitting by removing confusing samples / A. Vezhnevets, O. Barinova // Lecture Notes in Computer Science. – 2007. – Vol. 4701 LNAI. – P. 430–441. – DOI 10.1007/978-3-540-74958-5_40.
14. Suzuki, S. Topological Structural Analysis of Digitized Binary Images by Border Following / S. Suzuki, K. Abe // Computer Vision, Graphics, and Image Processing. Volume 30, Issue 1, April 1985. – P. 32–46. – URL: https://doi.org/10.1016/0734-189X(85)90016-7.
15. Zolkin, A. L. Intelligent software and information system for diagnostics and forecasting the technical condition of traction electric motors / A. L. Zolkin, V. S. Tormozov, D. V. Gridina // Proceedings of the Samara Scientific Center of the Russian Academy of Sciences. – 2020. – Vol. 22. – No. 4. – P. 92–97. – DOI 10.37313/1990-5378-2020-22-4-92-97.
16. Shadow detection algorithms for traffic flow analysis : a comparative study / A. Prati, I. Mikic, C. Grana, M. M. Trivedi. – ITSC 2001. 2001 IEEE Intelligent Transportation Systems. Proceedings (Cat. No.01TH8585), Oakland, CA, USA, 2001. – P. 340–345. – DOI 10.1109/ITSC.2001.948680.
17. Tormozov, V. S. Improving the performance of the algorithm for detecting and classifying vehicles in satellite images by reducing the search area using geoinformation about roads / V. S. Tormozov // Bulletin of the Russian New University. Series : Complex systems : Models, Analysis and Control. – 2019. – No. 2. – P. 56–63. – DOI 10.25586/RNU.V9187.19.02.P.056.
18. Lukyanitsa, A. A. Digital processing of video images / A. A. Lukyanitsa, A. G. Shishkin. – Мoscow : ISS-Press, 2009. – 518 p. – ISBN 978-5-9901899-1-1.
19. Ng, J. Y. Image-based Vehicle Classification System / J. Y. Ng, Y. H. Tay // The 11th Asia-Pacific ITS Forum and Exhibition (ITS-AP 2011), Kaoshiung, Taiwan. June 8–11, 2011. – URL: https://doi.org/10.48550/arXiv.1204.2114.
20. Numerical evaluation of the traffic flow indicators using super-resolution satellite imagery / N. Pugachev, G. Ya. Markelov, V. S. Tormozov, A. O. Nosenko // In the collection : 2019 International Multi-Conference on Industrial Engineering and Modern Technologies, FarEastCon 2019. – 2019. – DOI 10.1109/FarEastCon.2019.8934802.
21. Pugachev, I. N. Training and using a convolutional neural network for detecting and classifying vehicles in high-resolution satellite images / I. N. Pugachev, G. Ya. Markelov, V. S. Tormozov // Industrial ACS and Controllers. – 2019. – No. 10. – P. 20–25. – DOI 10.25791/asu.10.2019.933.
Review
For citations:
Pugachev I.N., Tormozov V.S. Development and analysis of a road traffic monitoring system based on machine vision technologies and cluster analysis methods. Vestnik Rostovskogo Gosudarstvennogo Universiteta Putej Soobshcheniya. 2024;(4):134-145. (In Russ.) https://doi.org/10.46973/0201-727X_2024_4_134
Views:
12
JATS XML
Email this article 