Preliminary Assessment of Potentially Conflicting Vehicle Interactions Based on Predicted Proximity Parameters

The paper addresses the problem of the preliminary identification of potentially conflicting vehicle interactions based on trajectory data from video monitoring. The need to move beyond the analysis of recorded road traffic accidents towards an examination of the actual interaction parameters of road users is substantiated. An approach is proposed based on a comparison of the minimum predicted distance between vehicles with a critical distance and a safe following distance. The main stages of input data formation predicted proximity calculation, and classification of the level of potential conflict are examined

1. Hauer E. Traffic conflicts and exposure. Accident Analysis & Prevention, 1982, vol. 14, no. 5, pp. 359–364. Available at: https://doi.org/10.1016/0001–4575(82)90014–8.

2. Perkins S. R., Harris J. L. Traffic conflict characteristics — accident potential at intersections. Highway Research Record, 1968, no. 225, pp. 35–43. Available at: https://onlinepubs.trb.org/Onlinepubs/hrr/1968/225/225–004.pdf.

3. Asmussen E. Joint International Study for the Calibration of Traffic Conflicts Techniques. In: Asmussen E. (ed.) International Calibration Study of Traffic Conflict Techniques. Berlin; Heidelberg, Springer, 1984. NATO ASI Series, vol. 5. Available at: https://doi.org/10.1007/978–3–642–82109–7_1.

4. Laureshyn A., Varhelyi A. The Swedish Traffic Conflict Technique: Observer’s Manual. Lund, Lund University, Faculty of Engineering, Department of Technology and Society, Traffic and Roads, 2018. Available at: https://lucris.lub.lu.se/ws/files/51195704/TCT_Manual_2018.pdf.

5. Svensson Å. Further development and validation of the Swedish Traffic Conflict Technique. Lund, Lund University, Institute of Technology, Department of Traffic Planning and Engineering, 1992.

6. Mishra A., Chen K., Poddar S., Posadas E., Rangarajan A., Ranka S. Using Video Analytics to Improve Traffic Intersection Safety and Performance. Vehicles, 2022, vol. 4, no. 4, pp. 1288–1313. Available at: https://doi.org/10.3390/vehicles4040068.

7. Liu J., Zhao H., Zheng G., Chen Z., Li X. LLTrack: Parallel Association Framework for 2-D Multi-Object Tracking. IEEE Access, 2026, vol. 14, pp. 75849–75864. DOI: 10.1109/ACCESS. 2026.3692961. Available at: https://ieeexplore.ieee.org/document/11516625.

8. Roy S., Abdelhadi A., Gaweesh S. M. Video- Based Surrogate Safety Analysis for Conflict Detection at Intersections Using CCTV Footage and Extreme Value Theory, 2025. Available at: https://doi.org/10.21203/rs.3.rs‑7894809/v1.

9. Li S., Yoon H. — S. Vehicle Localization in 3D World Coordinates Using Single Camera at Traffic Intersection. Sensors, 2023, vol. 23, no. 7, article 3661. Available at: https://doi.org/10.3390/s23073661.

10. Kalita D., Lyakhov P. Moving Object Detection Based on a Combination of Kalman Filter and Median Filtering. Big Data and Cognitive Computing, 2022, vol. 6, no. 4, p. 142. DOI: 10.3390/bdcc6040142. EDN QZOXJI.

11. Zhankaziev S. V., Dronsejko V. V., Donets N. A. Kategorizatsiya uchastkov skorostnykh avtomobilnykh dorog dlya modelirovaniya konfliktnosti [Categorisation of motorway sections for traffic conflict modelling]. Avtomobil. Doroga. Infrastruktura [Automobile. Road. Infrastructure], 2025, no. 2(44). EDN PDKOZC. (In Russ.)

12. Dronsejko V. V., Merkovich A. M., Zamytskikh A. V., Maksimychev O. I. Predikativnyj podkhod k analizu konfliktnosti v transportnom potoke [A predictive approach to conflict analysis in traffic flow]. Mir transporta i tekhnologicheskikh mashin [World of Transport and Technological Machines], 2023, no. 3–1(82), pp. 86–92. DOI: 10.33979/2073–7432–2023–3–1(82)-86–92. EDN VUPKVF. (In Russ.)