ABOUT METHODS FOR COLLECTING AND ANALYZING TRAFFIC FLOW CHARACTERISTICS
Marina S. Moseva, Moscow Technical University of Communications and Informatics, Moscow, Russia, m.s.moseva@mtuci.ru
Abstract
The ever-increasing motorization leads to the need to solve problems related to the optimal movement of transport, ensuring its safety and improving the environmental situation. According to Rosstat statistics, the number of own cars in the constituent entities of the Russian Federation (per 1,000 people) is increasing every year. The issues of optimal control of the movement of vehicles remain topical. Modeling of traffic flows allows you to determine the “bottlenecks” of the existing road network. In most situations, the best solution to the above problems is to improve the existing transport system. This approach is quite expensive. In this regard, studies related to the development and application of modern and promising technologies in the creation of intelligent transport systems of various levels and purposes are relevant both today and in the future. The collection and analysis of data on traffic flows allows you to verify the models, as well as make decisions about the further management of the movement of vehicles. With the development of computer technology and information technology, methods for accumulating and processing information about traffic flows have been improved. Today it becomes possible to receive, process data and make decisions in real time. This study is devoted to an overview of existing methods for monitoring and collecting characteristics about the state of traffic flows. A review of modern technologies and sensors used to collect traffic information is made. The method for collecting data on road users is described. An algorithm for classifying vehicles depending on the brand of the vehicle has been developed. The description of the vehicle tracking algorithm is given. The method for calculating the main characteristics of the traffic flow (speed, density, intensity) based on data from the video sequence is described.
Keywords: traffic flow monitoring, vehicle classification, neural network algorithm, calculation of traffic flow characteristics.
References
1. The number of own cars per 1000 people in the constituent entities of the Russian Federation. [Electronic resource]: Federal State Statistics Service. 2021. URL: https://rosstat.gov.ru/folder/23455 (accessed 03.09.2021).
2. Availability of vehicles in the Russian Federation. [Electronic resource]: Federal State Statistics Service. 2021. URL: https://rosstat.gov.ru/folder/23455 (accessed 03.09.2021).
3. GOST R 56829-2015 Intelligent transport systems. Terms and Definitions. Moscow: Standartinform, 2018. 10 p.
4. M.G. Gorodnichev (2015). Informational and Mathematical Aspects of the Leader-Following Model: Cand. … cand. tech. Sciences: 05.13.17 / Gorodnichev Mikhail Gennadevich. Moscow. 120 p.
5. N.O. Brailovsky, B.I. Granovsky (1978). Modeling of transport systems. Moscow: Transport. 125 p.
6. S.A. Rajab, A. Mayeli, and H.H. Refai. (2014). Vehicle classification and accurate speed calculation using multi-element piezoelectric sensor,” in 2014 IEEE Intelligent Vehicles Symposium Proceedings. IEEE, pp. 894-899.
7. C. Xu, Y. Wang, X. Bao, and F. Li (2018). Vehicle classification using an imbalanced dataset based on a single magnetic sensor. Sensors, vol. 18, no. 6, p. 1690.
8. M. Stocker, M. Ronkko, and M. Kolehmainen (2014). Situational knowledge representation for traffic observed by a pavement vibration sensor network. IEEE Transactions on Intelligent Transportation Systems, vol. 15, no. 4, pp. 1441-1450.
9. S. Meta and M. G. Cinsdikici (2010). Vehicle-classification algorithm based on component analysis for single-loop inductive detector. IEEE Transac- tions on Vehicular Technology, vol. 59, no. 6, pp. 2795-2805.
10. B. Yang and Y. Lei (2015). Vehicle detection and classification for low-speed congested traffic with anisotropic magnetoresistive sensor. IEEE Sensors Journal, vol. 15, no. 2, pp. 1132-1138.
11. W. Ma, D. Xing, A. McKee, R. Bajwa, C. Flores, B. Fuller, and P. Varaiya (2014). A wireless accelerometer-based automatic vehicle classification prototype system. IEEE Transactions on Intelligent Transportation Systems, vol. 15, no. 1, pp. 104-111.
12. J. George, L. Mary, and K. Riyas (2013). Vehicle detection and classification from acoustic signal using ANN and KNN. Control Communication and Computing (ICCC), 2013 International Conference. IEEE, pp. 436-439.
13. H. Lee and B. Coifman (2015). Using LIDAR to validate the performance of vehicle classification stations. Journal of Intelligent Transportation Systems, vol. 19, no. 4, pp. 355-369.
14. E. Odat, J. S. Shamma, and C. Claudel (2017). Vehicle classification and speed estimation using combined passive infrared/ultrasonic sensors. IEEE Transactions on Intelligent Transportation Systems.
15. M. Won, S. Zhang, and S. H. Son (2017). WiTraffic: Low-cost and non-intrusive traffic monitoring system using WiFi. 2017 26th International Conference on Computer Communication and Networks (ICCCN). IEEE, pp. 1-9.
16. T. Tang, S. Zhou, Z. Deng, L. Lei, and H. Zou (2017). Arbitrary-oriented vehicle detection in aerial imagery with single convolutional neural networks. Remote Sensing, vol. 9, no. 11, p. 1170.
17. Z. Chen, T. Ellis, and S. A. Velastin (2012). Vehicle detection, tracking and clas- sification in urban traffic. 2012 15th International IEEE Conference on Intelligent Transportation Systems. IEEE, pp. 951-956.
18. C.M. Bautista, C.A. Dy, M.I. Manalac, R. A. Orbe, and M. Cordel (2016). Convolutional neural network for vehicle detection in low resolution traffic videos. Region 10 Symposium (TENSYMP), IEEE, pp. 277-281.
19. B. Chidlovskii, G. Csurka, and J. Rodriguez-Serrano (2014). Vehicle type classification from laser scans with global alignment kernels. 17th International IEEE Conference on Intelligent Transportation Systems (ITSC). IEEE, pp. 2840-2845.
20. K. He, G. Gkioxari, P. Dollar and R. Girshick (2017). Mask R-CNN. 2017 IEEE International Conference on Computer Vision (ICCV), 2017, pp. 2980-2988. doi: 10.1109/ICCV.2017.322
21. J. Lin, W. D. Qi, and P. Liu (2020). Bias-compensation Kalman filter algorithm for AoA-ToA target tracking. Information and Control, vol. 49, no. 6, pp. 657-666.
22. D. Liu, Y. B. Zhao, Z. Q. Yuan et al. (2020). Target tracking methods based on a signal-to-noise ratio model. Frontiers of Information Technology & Electronic Engineering, vol. 21, no. 12, pp. 1804-1814.
23. F.L. Chen, Q.H. Ding, and H.B. Luo (2021). Anti-occlusion real time target tracking algorithm employing spatio-temporal context. Infrared and Laser Engineering, vol. 50, no. 1, Article ID 20200105, pp. 1-11.
Information about author:
Marina S. Moseva, Department of Mathematical Cybernetics and Information Technologies, Moscow Technical University of Communications and Informatics, Moscow, Russia