Evaluating AI-Based Video Analytics for Traffic Engineering: Accuracy, Calibration, and Practical Use
Downloads
This paper examines the potential and reliability of AI-based video analytics for solving key traffic engineering problems. The objectives were to compare several commercially available tools for collecting traffic data and, through practical examples, to show that AI-processed data can be used for the development, calibration, and validation of traffic models. Four AI-based video analytics (StreetLogic Pro, DataFromSky, CVEDIA RT Studio, and Camlytics Single) were tested using field video recordings at a signalized intersection on an urban arterial in Split, Croatia. Detection accuracy, usability, and sensitivity to camera placement and recording conditions are analyzed, and selected microscopic parameters (saturation flow rate and control delay) were obtained and compared with values derived from HCM procedures. DataFromSky and CVEDIA RT Studio achieved 97–99% vehicle detection accuracy and provided detailed trajectory data suitable for scientific applications, while StreetLogic Pro achieved 100% accuracy for operational vehicle counting. AI-based estimates of saturation flow rate and control delay differed by less than 1% and 5%, respectively, from traditional field measurements. The main novelty of this research lies in its practical comparison of AI-based video analytics tools combined with a worked example of using AI-derived data to calibrate analytical models, providing practical guidance for researchers and practitioners in traffic engineering.
Downloads
[1] Albright, D. (1991). History of Estimating and Evaluating Annual Traffic Volume Statistics. Transportation Research Record: Journal of the Transportation Research Board, 1305, 103–107.
[2] North America Traffic. (2026). The history of traffic signals. North America Traffic, Port Colborne, Canada. Available online: https://www.northamericatraffic.com/blog/title/the-history-of-traffic-signals/id/322/ (accessed on March 2026).
[3] Rožić, P. (2006). Use of traffic flow theory in road traffic counting. Građevinar, 58(1), 25-34.
[4] Trafficlogix. (2022). The history of radar enforced speed limits. Trafficlogix, New York, United States. Available online: https://trafficlogix.com/the-history-of-radar-enforced-speed-limits (accessed on March 2026).
[5] Garner, J. E., Lee, C. E., & Huang, L. (1990). Infrared sensors for counting, classifying, and weighing vehicles. Texas State Department of Highways and Public Transportation Final Report (FHWA), 1162-1F.
[6] Loureiro, P. F. Q., Rossetti, R. J. F., & Braga, R. A. M. (2009). Video processing techniques for traffic information acquisition using uncontrolled video streams. IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC, 127–133. doi:10.1109/ITSC.2009.5309595.
[7] Sun, S., Rappaport, T. S., Thomas, T. A., Ghosh, A., Nguyen, H. C., Kovacs, I. Z., Rodriguez, I., Koymen, O., & Partyka, A. (2016). Investigation of Prediction Accuracy, Sensitivity, and Parameter Stability of Large-Scale Propagation Path Loss Models for 5G Wireless Communications. IEEE Transactions on Vehicular Technology, 65(5), 2843–2860. doi:10.1109/TVT.2016.2543139.
[8] Solink. (2026). When did CCTV become common: History of the security. Solink, Ottawa, Canada. Available online: https://solink.com/resources/industry-insights/when-did-cctv-become-common (accessed on March 2026).
[9] Yavuz, M. N., & Özen, H. (2024). Calibration of Microscopic Traffic Simulation of Urban Road Network Including Mini-Roundabouts and Unsignalized Intersection Using Open-Source Simulation Tool. Scientific Journal of Silesian University of Technology. Series Transport, 122, 305–318. doi:10.20858/sjsutst.2024.122.17.
[10] Azam, M., Hassan, S.A., Puan, O.C. (2024). Calibration of VISSIM for an Urban Corridor under Heterogeneous Traffic Conditions. European Transport / Trasporti Europei, 98, 1–14. doi:10.48295/et.2024.98.6
[11] Afshari, A., Lee, J., Besenski, D., Dimitrijevic, B., & Spasovic, L. (2025). Calibrating Microscopic Traffic Simulation Model Using Connected Vehicle Data and Genetic Algorithm. Applied Sciences (Switzerland), 15(3), 1496. doi:10.3390/app15031496.
[12] Igene, M., Luo, Q., Jimee, K., Soltanirad, M., Bataineh, T., & Liu, H. (2024). Integrating LiDAR Sensor Data into Microsimulation Model Calibration for Proactive Safety Analysis. Sensors, 24(13), 4393. doi:10.3390/s24134393.
[13] Whitley, T., Tian, Y., & Xu, H. (2023). Headway Data Extraction and Highway Capacity Manual Capacity Function Calibration for Roundabouts with Roadside Lidar Data. Transportation Research Record, 2677(5), 495–505. doi:10.1177/03611981221132853.
[14] Lopukhova, E., Abdulnagimov, A., Voronkov, G., & Grakhova, E. (2024). Machine Learning-Driven Calibration of Traffic Models Based on a Real-Time Video Analysis. Applied Sciences (Switzerland), 14(11), 4864. doi:10.3390/app14114864.
[15] Lin, H., Yuan, Z., He, B., Kuai, X., Li, X., & Guo, R. (2022). A Deep Learning Framework for Video-Based Vehicle Counting. Frontiers in Physics, 10. doi:10.3389/fphy.2022.829734.
[16] Berwo, M. A., Khan, A., Fang, Y., Fahim, H., Javaid, S., Mahmood, J., Abideen, Z. U., & M.S, S. (2023). Deep Learning Techniques for Vehicle Detection and Classification from Images/Videos: A Survey. Sensors, 23(10), 4832. doi:10.3390/s23104832.
[17] Vu, T. C., Tran, T. D., Nguyen, T. V., Nguyen, D. T., Dinh, L. Q., Nguyen, M. D., Nguyen, H. T., & Nguyen, M. T. (2025). Vehicle Detection, Tracking and Counting in Traffic Video Streams Based on the Combination of YOLOv9 and DeepSORT Algorithms. Journal of Future Artificial Intelligence and Technologies, 2(2), 255–268. doi:10.62411/faith.3048-3719-115.
[18] Alkandary, K., Yildiz, A. S., & Meng, H. (2026). Enhancing Multi Object Tracking with CLIP: A Comparative Study on DeepSORT and StrongSORT. Electronics, 15(2), 265. doi:10.3390/electronics15020265.
[19] Yan, Z., Zhang, D., Lu, X., Liu, Q., Wang, Y., & Sun, J. (2022). Saturation Flow Rate at the Work Zone–Straddled Intersections with Interweaving Movements: Lane-Based Modeling Study. Journal of Transportation Engineering, Part A: Systems, 148(10), 04022088. doi:10.1061/jtepbs.0000718.
[20] Ke, R., Feng, S., Cui, Z., & Wang, Y. (2020). Advanced framework for microscopic and lane-level macroscopic traffic parameters estimation from UAV video. IET Intelligent Transport Systems, 14(7), 724–734. doi:10.1049/iet-its.2019.0463.
[21] National Academies of Sciences, Engineering, and Medicine. (2022). Highway capacity manual 7th edition: A guide for multimodal mobility analysis. National Academies Press, Washington, D.C., United States. Available online: doi:10.17226/26432.
[22] StreetLogic Pro. (2026). StreetLogic Pro. Available online: https://www.streetlogic.pro/ (accessed on March 2026).
[23] DataFromSky. (2026). DataFromSky. DataFromSky, Czech Republic. Available online: https://ai.datafromsky.com/picker (accessed on March 2026).
[24] CVEDIA. (2026). CVEDIA RT Studio. CVEDIA, United States. Available online: https://www.cvedia.com/cvedia-rt (accessed on March 2026).
[25] Camlytics. (2026). Camlytics service 3.X.X. specifications. Camlytics, United States. Available online: https://camlytics.com/docs/Camlytics%20Service%203.xxx%20Specs.pdf (accessed on March 2026).
[26] FindMySoft. (2026). Camlytics – software listing. FindMySoft. Available online: https://camlytics.findmysoft.com (accessed on March 2026).
[27] Adamec, V., Herman, D., Schullerova, B., & Urbanek, M. (2019). Modelling of Traffic Load by the DataFromSky System in the Smart City Concept. Smart Governance for Cities: Perspectives and Experiences, 135–152. doi:10.1007/978-3-030-22070-9_7.
[28] Apeltauer, J., Babinec, A., Herman, D., & Apeltauer, T. (2015). Automatic vehicle trajectory extraction for traffic analysis from aerial video data. In International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, 40(3W2), 9–15. doi:10.5194/isprsarchives-XL-3-W2-9-2015.
[29] Barmpounakis, E. N., Vlahogianni, E. I., Golias, J. C., & Babinec, A. (2019). How accurate are small drones for measuring microscopic traffic parameters? Transportation Letters, 11(6), 332–340. doi:10.1080/19427867.2017.1354433.
[30] Ali, Y., Sarkar, D. R., Rao, K. R., Chatterjee, N., & Bhaskar, A. (2024). Scrutinizing Data from Sky: An Examination of Its Veracity in Area Based Traffic Contexts. arXiv Preprint, arXiv:2404.17212. doi:10.48550/arXiv.2404.17212.
[31] The Agency for Coastal Liner Maritime Transport. (2026). Passenger and vehicle traffic, comparison 2025/2024. The Agency for Coastal Liner Maritime Transport, Croatia. Available online: https://agencija-zolpp.hr/wp-content/uploads/2026/02/Promet-putnika-i-vozila-2024-2025.pdf (accessed on March 2026).
[32] Pi, Y., Duffield, N., Behzadan, A. H., & Lomax, T. (2022). Visual recognition for urban traffic data retrieval and analysis in major events using convolutional neural networks. Computational urban science, 2(1), 2. doi:10.1007/s43762-021-00031-w.
[33] ACT Government Engineering Advisory Note. (2026). Traffic monitoring CCTV cameras at traffic signals. ACT Government, Canberra, Australia.
[34] Boston Transport Department. (2026). Specification for video monitoring system. Boston Transport Department, Boston, USA.
[35] Robotec. (2026). The importance of camera placement in driver monitoring systems. Robotec, Poland. Available online: https://www.robotec.ai/the-importance-of-camera-placement-in-driver-monitoring-systems (accessed on March 2026).
[36] Goodvision. (2026). Requirements for traffic camera video processing. Goodvision, Czech Republic. Available online: https://help.goodvisionlive.com/en/articles/3304475-requirements-for-traffic-camera-video-processing (accessed on March 2026).
[37] Vien, L. L., Ibrahim, W. H. W., & Mohd, A. F. (2005). Determination of Ideeal Saturation Flow at Signalized Intersections Under Malaysian Road Conditions. Journal of Transportation Science Society of Malaysia, 1, 26-37.
[38] Rouphail, N. M., Samandar, S., Chase, R., Yang, G., List, G., & Chun, G. (2020). Traffic Analysis Tools: Assessment, Comparison and Validation Study. US Department of Transportation, Federal Highway Administration (FHWA/NC/2020-30), Washington, D.C., United States.
- Authors retain all copyrights. It is noticeable that authors will not be forced to sign any copyright transfer agreements.
- This work (including HTML and PDF Files) is licensed under a Creative Commons Attribution 4.0 International License.
