A framework for reliable traffic surrogate safety assessment based on multi-object tracking data

Markus Steinmaßl; Moritz Beeking; Natasha Troth; Karl Rehrl

doi:10.55329/vydx2624

Authors

Markus Steinmaßl Salzburg Research Forschungsgesellschaft mbH, Austria https://orcid.org/0000-0001-9407-9570
Moritz Beeking Salzburg Research Forschungsgesellschaft mbH, Austria https://orcid.org/0000-0002-7870-8127
Natasha Troth Salzburg Research Forschungsgesellschaft mbH, Austria https://orcid.org/0009-0006-7619-9062
Karl Rehrl Salzburg Research Forschungsgesellschaft mbH, Austria https://orcid.org/0000-0003-4052-5867

DOI:

https://doi.org/10.55329/vydx2624

Keywords:

intersection safety, multi-object tracking, post-encroachment time, surrogate safety assessment, time-to-collision, trajectory quality

Abstract

Multiple object tracking (MOT) systems enable the recording of traffic situations and the movements of road users in high detail. These data form the basis for safety-related analyses such as surrogate safety assessment (SSA), which often involves detecting, quantifying, and analysing conflict situations. Due to the rarity of actual conflicts even occasional data errors can significantly affect SSA outcomes. Consequently, high-quality data are essential. However, a gap remains between MOT and SSA research, particularly regarding the impact of data quality on the reliability of SSA results. This study addresses that gap by proposing a framework that explicitly accounts for the effects of data quality to ensure reliable SSA outcomes. Since it treats the data-generating MOT system as a black box, the framework can also be applied by practitioners using historical datasets or in cases of restricted access to the MOT system. Using the surrogate safety measures (SSMs) time-to-collision (TTC) and post-encroachment time (PET), we illustrate how data inaccuracies affect conflict detection and show how the proposed framework can reveal critical data limitations. We also demonstrate its ability to identify the need for data correction methods and to analyse the effects of such methods on SSA outcomes. Finally, our findings underline the importance of scenario-specific data evaluation for ensuring reliable SSA results and suggest that robustness against data inaccuracies should be considered a key criterion when selecting SSMs.

Downloads

Download data is not yet available.

Author Biographies

Markus Steinmaßl, Salzburg Research Forschungsgesellschaft mbH, Austria

Markus Steinmaßl received his MSc. degree in Data Science from the Paris Lodron University Salzburg in 2020. He has worked as a data scientist and researcher in the Mobility & Transport Analytics group at Salzburg Research in Salzburg, Austria, since 2018. The focus of his research is on methods for the analysis of traffic data and data quality, especially trajectories of road users.

CRediT contribution: Conceptualization, Data curation, Formal analysis, Funding acquisition, Investigation, Methodology, Project administration, Software, Validation, Visualization, Writing—original draft, Writing—review & editing.

Moritz Beeking, Salzburg Research Forschungsgesellschaft mbH, Austria

Moritz Beeking received his MSc. degree in Computer Science with a minor in Physics and a specialization on Cognitive Systems and Robotics in 2021 from the Karlsruhe Institute of Technology (KIT) in Karlsruhe, Germany. Currently he works as a data scientist in the Mobility & Transport Analytics group at Salzburg Research in Salzburg, Austria. He’s also pursuing a PhD with the Intelligent Vehicles group at the Technical University of Delft in the Netherlands. His research focuses on the processing of data collected by sensor-equipped bicycles, especially using neural network based perception methods for LiDAR data.

CRediT contribution: Funding acquisition, Methodology, Project administration, Resources, Writing—review & editing.

Natasha Troth, Salzburg Research Forschungsgesellschaft mbH, Austria

Natasha Troth received her MSc. degree in Web Development, with a minor in Data Science, from the Salzburg University of Applied Sciences, Austria, in 2022. Since then, she has been employed at Salzburg Research in Salzburg, Austria, where she works as a software developer, data scientist, and research associate. She is part of the Mobility & Transport Analytics group, where her research focuses on the processing and analysis of traffic data to support data-driven mobility solutions.

CRediT contribution: Investigation, Methodology, Writing—review & editing.

Karl Rehrl, Salzburg Research Forschungsgesellschaft mbH, Austria

Karl Rehrl has been a researcher at Salzburg Research since 2002 and head of the Mobility & Transport Analytics group since 2004. In 2011, he received his PhD degree in Geoinformation and Surveying from the Technical University of Vienna. In 2023 he received the Venia Docendi in the subject Applied Geoinformation from the Technical University in Vienna. His main areas of research are location based services, spatio-temporal data analytics and intelligent transportation systems with a focus on mobility data analytics, data modelling, data quality and field testing.

CRediT contribution: Conceptualization, Funding acquisition, Project administration, Supervision, Writing—review & editing.

References

Abdel-Aty, M., Wang, Z., Zheng, O., & Abdelraouf, A. (2023). Advances and applications of computer vision techniques in vehicle trajectory generation and surrogate traffic safety indicators. Accident Analysis & Prevention, 191, 107191. DOI: https://doi.org/10.1016/j.aap.2023.107191

Allen, B. L., Shin, B. T., & Cooper, P. J. (1978). Analysis of Traffic Conflicts and Collisions. Transportation Research Record, (HS-025 846)

Anuj, L., & Krishna, M. T. G. (2017). Multiple camera based multiple object tracking under occlusion: A survey. 2017 International Conference on Innovative Mechanisms for Industry Applications (ICIMIA), 432-437. DOI: https://doi.org/10.1109/ICIMIA.2017.7975652

Arun, A., Haque, M. M., Bhaskar, A., Washington, S., & Sayed, T. (2021). A systematic mapping review of surrogate safety assessment using traffic conflict techniques. Accident Analysis & Prevention, 153, 106016. DOI: https://doi.org/10.1016/j.aap.2021.106016

Berndt, D. J., & Clifford, J. (1994). Using dynamic time warping to find patterns in time series. Proceedings of the 3rd International Conference on Knowledge Discovery and Data Mining, 359-370.

Cohen, J. (1960). A coefficient of agreement for nominal scales. Educational and Psychological Measurement, 20(1), 37-46.Publisher: SAGE Publications Inc. DOI: https://doi.org/10.1177/001316446002000104

Darzian Rostami, A., Katthe, A., Sohrabi, A., & Jahangiri, A. (2020). Predicting Critical Bicycle-Vehicle Conflicts at Signalized Intersections. Journal of Advanced Transportation, 1-16. DOI: https://doi.org/10.1155/2020/8816616

Frey, B. J., & Dueck, D. (2007). Clustering by Passing Messages Between Data Points. Science, 315(5814), 972-976. DOI: https://doi.org/10.1126/science.1136800

Hayward, J. C. (1971). Near misses as a measure of safety at urban intersections. The Pennsylvania State University, Master dissertation

Huang, Y.-L., & Chen, Y.-H. (2025). Estimating intersections’ near-crash conflicts with the drone-based image-recording data. Traffic Safety Research, 9, e000084. DOI: https://doi.org/10.55329/snjp4746

Jandial, A., Merdrignac, P., Shagdar, O., & Fevrier, L. (2020). Implementation and evaluation of intelligent roadside infrastructure for automated vehicle with I2V communication. Vehicular ad-hoc networks for smart cities, Springer Singapore. 3-18. DOI: https://doi.org/10.1007/978-981-15-3750-9_1

Jiménez-Bravo, D. M., Lozano Murciego, Á., Sales Mendes, A., Sánchez San Blás, H., & Bajo, J. (2022). Multi-object tracking in traffic environments: A systematic literature review. Neurocomputing, 494, 43-55. DOI: https://doi.org/10.1016/j.neucom.2022.04.087

Johnsson, C., Laureshyn, A., & D’Agostino, C. (2021). A relative approach to the validation of surrogate measures of safety. Accident Analysis & Prevention, 161, 106350. DOI: https://doi.org/10.1016/j.aap.2021.106350

Johnsson, C., Laureshyn, A., & De Ceunynck, T. (2018). In search of surrogate safety indicators for vulnerable road users: A review of surrogate safety indicators. Transport Reviews, 38(6), 765-785. DOI: https://doi.org/10.1080/01441647.2018.1442888

Lu, C., He, X., van Lint, H., Tu, H., Happee, R., & Wang, M. (2021). Performance evaluation of surrogate measures of safety with naturalistic driving data. Accident Analysis & Prevention, 162, 106403. DOI: https://doi.org/10.1016/j.aap.2021.106403

Luo, W., Xing, J., Milan, A., Zhang, X., Liu, W., & Kim, T.-K. (2021). Multiple Object Tracking: A Literature Review. Artificial Intelligence, 293 103448 DOI: https://doi.org/10.1016/j.artint.2020.103448

Mansell, R., Persaud, B., Milligan, C., & Pushka, A. (2024). Investigating factors that affect conflicts between bicyclists and right turning vehicles at signalized intersections. Traffic Safety Research, 6, e000040. DOI: https://doi.org/10.55329/pytz4050

Mohamed, M. G., & Saunier, N. (2018). The impact of motion prediction methods on surrogate safety analysis: A case study of left-turn and opposite-direction interactions at a signalized intersection in Montreal. Journal of Transportation Safety & Security, 10(4), 265-287. DOI: https://doi.org/10.1080/19439962.2016.1255690

Nikolaou, D., Ziakopoulos, A., & Yannis, G. (2023). A Review of Surrogate Safety Measures Uses in Historical Crash Investigations. Sustainability, 15(9), 7580. DOI: https://doi.org/10.3390/su15097580

nuScenes (2025). nuScenes detection task benchmark.

Punzo, V., Borzacchiello, M. T., & Ciuffo, B. (2011). On the assessment of vehicle trajectory data accuracy and application to the Next Generation SIMulation (NGSIM) program data. Transportation Research Part C: Emerging Technologies, 19(6), 1243-1262. DOI: https://doi.org/10.1016/j.trc.2010.12.007

Puscar, F. M., Sayed, T., Bigazzi, A. Y., & Zaki, M. H. (2017). Multimodal Safety Assessment of an Urban Intersection by Video Analysis of Bicycle, Pedestrian, and Motor Vehicle Traffic Conflicts and Violations. 97th Annual Meeting of the Transportation Research Board, 1-14.

Rath, P. K., Harrison, B., Lu, D., Yang, Y., Wishart, J., & Yu, H. (2024). Evaluating Safety Metrics for Vulnerable Road Users at Urban Traffic Intersections Using High-Density Infrastructure LiDAR System. WCX SAE World Congress Experience, 2024-01-2641. DOI: https://doi.org/10.4271/2024-01-2641

Sengupta, A., Ilgin Guler, S., Gayah, V. V., & Warchol, S. (2024). Evaluating the reliability of automatically generated pedestrian and bicycle crash surrogates. Accident Analysis & Prevention, 203 107614 DOI: https://doi.org/10.1016/j.aap.2024.107614

Shi, S., Cui, J., Jiang, Z., Yan, Z., Xing, G., Niu, J., & Ouyang, Z. (2022). VIPS: Real-time perception fusion for infrastructure-assisted autonomous driving. Proceedings of the 28th Annual International Conference on Mobile Computing And Networking, 133-146. DOI: https://doi.org/10.1145/3495243.3560539

Van der Horst, A. R. A. (1990). A time-based analysis of road user behaviour in normal and critical encounters. Delft University of Technology, Doctoral dissertation

Vignarca, D., Vignati, M., Arrigoni, S., & Sabbioni, E. (2023). Infrastructure-Based Vehicle Localization through Camera Calibration for I2V Communication Warning. Sensors, 23(16), 7136. DOI: https://doi.org/10.3390/s23167136

Xing, L., He, J., Abdel-Aty, M., Cai, Q., Li, Y., & Zheng, O. (2019). Examining traffic conflicts of upstream toll plaza area using vehicles’ trajectory data. Accident Analysis & Prevention, 125 174-187. DOI: https://doi.org/10.1016/j.aap.2019.01.034

Yang, K., Yu, R., Wang, X., Quddus, M., & Xue, L. (2018). How to determine an optimal threshold to classify real-time crash-prone traffic conditions?. Accident Analysis & Prevention, 117 250-261. DOI: https://doi.org/10.1016/j.aap.2018.04.022

Zhao, J., Ma, R., & Wang, M. (2024). A behaviourally underpinned approach for two-dimensional vehicular trajectory reconstruction with constrained optimal control. Transportation Research Part C: Emerging Technologies, 159, 104489. DOI: https://doi.org/10.1016/j.trc.2024.104489

Zhao, J., Harris, A., & Sartipi, M. (2023). Quality Assessment of Large-Scale Vehicle and Pedestrian Trajectories at Intersections. Transportation Research Record: Journal of the Transportation Research Board, 036119812311601. DOI: https://doi.org/10.1177/03611981231160177

Zheng, L., Ismail, K., & Meng, X. (2014). Traffic conflict techniques for road safety analysis: Open questions and some insights. Canadian Journal of Civil Engineering, 41(7), 633-641. DOI: https://doi.org/10.1139/cjce-2013-0558