Decision support system for detecting traffic violations based on vehicle’s trajectory

The paper proposes the approach for detecting the traffic violations based on illegal vehicle’s trajectory on video streams. As an example of such violations, illegal left turn is considered. This approach was implemented in a decision support system. YOLO neural network was employed as an object detector as part of the approach, LPRNet network for license plate recognition, and Ramer-Douglas-Pecker algorithm for the trajectory thinning. Using the example of the illegal left turn, a number of classifiers was studied: SVM, GaussianNB, KNeighbors, Decision Tree, Random Forest сlassifiers. These classifiers can be utilized to identify trajectories that violate road traffic regulations. Numerical experiments demonstrate that the SVM has about 95 % of classification accuracy among other algorithms. The computational cost also decreased due to the use of the trajectory thinning algorithm and lightweight neural network models. The capabilities of decision support system integration into the Centre for Automated Recording of Traffic Offences were illustrated by the example of left turn detection.

1. Minnikhanov R.N., Makhmutova A.M., Sabirov A.I. ITS Environment of the Republic of Tatarstan to ensure road safety. Sovremennaja nauka = Modern Science. 2021;(3):92–96. (In Russ.).

2. Gabdurahmanov L.R., Minnikhanov R.N., Tinchurin R.F. Intelligent transport systems as a modern concept of road safety. Nauchnyj portal MVD Rossii = Scientific portal of the Russia Ministry of the Interior. 2022;(1):41–50. (In Russ.).

3. Anikin I.V., Minnikhanov R.N., Dagaeva M.V., Makhmutova A.Z., Mardanova A.R. Analysis of vehicle trajectories on streaming video. Vestnik NCBZhD = Journal «Vestnik NTsBZhD». 2021;(4):24–33. (In Russ.).

4. Anikin I.V., Mardanova A.R. Identification of vehicle’s trajectory anomalies on streaming video. Matematicheskie metody v tehnologijah i tehnike = Mathematical methods in technology and technique. 2021;(1):83–87. (In Russ.).

5. Minnikhanov R.N., Anikin I.V., Mardanova A.R., Dagaeva M.V., Makhmutova A.Z., Kadyrov A.R. Evaluation of the Approach for the Identification of Trajectory Anomalies on CCTV Video from Road Intersections. Mathematics. 2022;10(388):1–20.

6. Koetsier C., Busch S., Sester M. Trajectory Extraction for Analysis of Unsafe Driving Behaviour. ISPRS-Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. 2019;42:1573–1578.

7. Ahmed S.A., Dogra D.P., Kar S., Roy P.P. Trajectory-Based Surveillance Analysis: A Survey. IEEE Trans. Circuits Syst. Video Technol. 2019;29:1985–1997.

8. Chandola V., Banerjee A., Kumar V., Anomaly Detection: A Survey. ACM Comput. Surv. 2009;41:1–58.

9. Santhosh K.K., Dogra D.P., Roy P.P. Anomaly Detection in Road Traffic Using Visual Surveillance: A Survey. ACM Comput. Surv. 2021;54:1–26.

10. Redmon J., Divvala S., Girshick R., Farhadi A. You Only Look Once: Unified, Real-Time Object Detection. 2016. Available from: https://export.arxiv.org/abs/1506.02640v5 (accessed on 10.09.2022).

11. Lowe D.G. Object recognition from local scale-invariant features. Proceedings of the International Conference on Computer Vision. 1999;2:1150–1157.

12. Ester M., Kriegel H.P., Sander J., XiaoweiXu A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise. Proceedings of 2nd International Conference on Knowledge Discovery and Data Mining. 1996:226–231.

13. Zherzdev S., Gruzdev A. LPRNet: License Plate Recognition via Deep Neural Networks; 2018. Available from: https://export.arxiv.org/abs/1806.10447 (accessed on 10.09.2022).

14. Douglas D.H., Peucker T.K. Algorithms for the reduction of the number of points required to represent a digitized line or its caricature. Cartogr. Int. J. Geogr. Inf. Geovisualization. 1973;10:112–122.

15. Liu S.W.T.T., Ngan H.Y.T., Ng M.K., Simske S.J. Accumulated Relative Density Outlier Detection for Large Scale Traffic Data. Electron. Imaging. 2018;9:1–10.

16. D’Acierno A., Saggese A., Vento M. Designing Huge Repositories of Moving Vehicles Trajectories for Efficient Extraction of Semantic Data. IEEE Trans. Intell. Transp. Syst. 2015;16:2038–2049.

17. Lam P., Wang L., Ngan H.Y.T., Yung N.H.C., Yeh A.G.O. Outlier Detection in Large-scale Traffic Data by Naïve Bayes Method and Gaussian Mixture Model Method. IS&T Int’l Sym. Electronic Imaging. 2017;6:73–78.

18. Khasanova A., Makhmutova A., Anikin I. Image denoising for video surveillance cameras based on deep learning techniques. Proceedings – 2021 International Conference on Industrial Engineering, Applications and Manufacturing, ICIEAM 2021. 2021:713–718.