Restricted accessResearch articleFirst published online 2025-12
Evaluating the Accuracy of Vehicle Tracking Data from Unmanned Aerial Vehicle Videos and Identifying Traffic Conflict Points to Develop a Conflict Frequency Predictive Model for Roundabout Safety Assessment under Mixed Traffic
In recent years, low-and-medium-income countries have been experiencing widespread use of unmanned aerial vehicles (UAVs) in the field of traffic engineering and management studies. However, the highly heterogeneous traffic mix poses challenges for UAV-based automated analyses. This study stands out by evaluating the accuracy of vehicle tracking data collected using UAVs for traffic safety assessment. High-resolution aerial imagery and precise ground truth data were obtained using a DJI Mavic Mini 3 Pro drone and Racelogic VBOX 3i Global Positioning System device. The YOLOv12x model was used for vehicle detection, while ByteTrack ensured continuous tracking across frames. Speed data extracted from UAV footage were validated against ground truth measurements and trajectory data from DataFromSky, showing low mean square error, root mean square error, normalized root mean square error, and mean absolute percentage error values. Conflict points at roundabouts were identified using surrogate safety measures such as modified time to collision and deceleration rate to avoid collision. The spatial distribution of the conflict points was visualized through a heatmap. A conflict frequency prediction model was developed using an AdaBoost algorithm with a negative binomial objective function, achieving high predictive accuracy. Feature importance analysis, along with the SHAP plot, identified the most critical geometric and traffic variables influencing conflict frequency. This work is unique in its application of advanced UAV technology combined with cutting-edge detection and tracking algorithms for comprehensive traffic safety analysis. By demonstrating the potential of UAVs in accurately monitoring traffic dynamics and identifying conflict points and conflict contributory factors, this study paves the way for innovative approaches to enhance road safety.
World Health Organization (WHO). Global Status Report on Road Safety 2023. World Health Organization, Geneva, 2023.
2.
Ministry of Road Transport and Highways (MoRTH). Road Accidents in India-2022. Ministry of Road Transport and Highways, Government of India, 2023.
3.
MajiA.NayakS.PandaM.BhuyanP. K.Service Level Modelling of Motorized Three-Wheelers at Un-Signalized Intersections under Heterogeneous Traffic Conditions. European Transport - Trasporti Europei, Vol. 88, No. 2, 2022, pp. 1–15. https://doi.org/10.48295/ET.2022.88.2.
4.
MajiA.GhoshI.Advanced Traffic Conflict Analysis for Safety Evaluation at Roundabouts under Mixed Traffic Using Extreme Value Theory. Accident Analysis and Prevention, Vol. 219, 2025, p. 108108. https://doi.org/10.1016/j.aap.2025.108108.
5.
MajiA.GhoshI.A Systematic Review on Roundabout Safety Incorporating the Safety Assessment Methodologies, Data Collection Techniques, and Driver Behavior. Safety Science, Vol. 181, 2025, p. 106661. https://doi.org/10.1016/j.ssci.2024.106661.
6.
VinayarajV. S.PerumalV.Developing Safety Performance Functions and Crash Modification Factors for Urban Roundabouts in Heterogeneous Non-Lane-Based Traffic Conditions. Transportation Research Record: Journal of the Transportation Research Board, 2023. 2677: 644–661.
7.
VinayarajV. S.PerumalV.Safety Evaluation of Urban Roundabouts in India: A Safety Performance Function-Based Approach. Traffic Safety Research, Vol. 3, 2022, pp. 1–16. https://doi.org/10.55329/bylj4120.
8.
HasanvandM.NasiriA. S. A.RahmaniO.ShaabanK.SamadiH.A Conflict-Based Safety Diagnosis of SCI Roundabouts Using a Surrogate Safety Measure Model. Sustainability (Switzerland), Vol. 15, No. 17, 2023, pp. 1–19. https://doi.org/10.3390/su151713166.
9.
ShawkyM.AlsobkyA.Al SobkyA.HassanA.Traffic Safety Assessment for Roundabout Intersections Using Drone Photography and Conflict Technique. Ain Shams Engineering Journal, Vol. 14, No. 6, 2023, p. 102115. https://doi.org/10.1016/j.asej.2023.102115.
10.
BhavsarY. M.ZaveriM. S.RavalM. S.ZaveriS. B.Vision-Based Investigation of Road Traffic and Violations at Urban Roundabout in India Using UAV Video: A Case Study. Transportation Engineering, Vol. 14, 2023, p. 100207. https://doi.org/10.1016/j.treng.2023.100207.
11.
GuX.Abdel-AtyM.XiangQ.CaiQ.YuanJ.Utilizing UAV Video Data for In-Depth Analysis of Drivers’ Crash Risk at Interchange Merging Areas. Accident Analysis and Prevention, Vol. 123, 2019, pp. 159–169. https://doi.org/10.1016/j.aap.2018.11.010.
12.
ZhouS.HeZ.ChenX.ChangW.An Anomaly Detection Method for UAV Based on Wavelet Decomposition and Stacked Denoising Autoencoder. Aerospace, Vol. 11, No. 5, 2024, p. 393. https://doi.org/10.3390/aerospace11050393.
13.
MajiA.PreethamK.GhoshI.JATAYU: A Large-Scale Indian UAV Dataset for Vehicle Detection and Tracking. Proc., International Conference on Electronics, Computing and Communication Technologies (IEEE CONNECT 2024), Bangalore, India, IEEE, New York, NY, 2024, pp. 1–6. https://doi.org/10.1109/CONECCT62155.2024.10677099.
14.
MajiA.Evaluating UAV Datasets for Vehicle Recognition in Mixed Traffic Conditions Using YOLO. Proc., IEEE 21st India Council International Conference (INDICON), Kharagpur, India, IEEE, New York, NY, 2024, pp. 1–6. https://doi.org/10.1109/INDICON63790.2024.10958351.
GuidoG.GallelliV.RoganoD.VitaleA.Evaluating the Accuracy of Vehicle Tracking Data Obtained from Unmanned Aerial Vehicles. International Journal of Transportation Science and Technology, Vol. 5, No. 3, 2016, pp. 136–151. https://doi.org/10.1016/j.ijtst.2016.12.001.
20.
PuriA.A Survey of Unmanned Aerial Vehicles (UAV) for Traffic Surveillance. Department of Computer Science and Engineering, University of South Florida, pp. 1–29.
21.
RedmonJ.FarhadiA.YOLOv3: An Incremental Improvement. Proc., IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, 2018.
22.
BochkovskiyA.WangC.-Y.LiaoH.-Y. M.YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv Preprint arXiv: arXiv:2004.10934, 2020.
RedmonJ.DivvalaS.GirshickR.FarhadiA.You Only Look Once: Unified, Real-Time Object Detection. Proc., IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, IEEE, New York, NY, 2016, pp. 779–788. https://doi.org/10.1109/CVPR.2016.91.
25.
LiS.ChenF.LiS.ChenF.SunZ.ZhuZ.ZhouL.TangK.Research on YOLOv8 Object Detection Algorithm in UAV Scenarios. Research Square (Research Square) [Internet], 2024. https://doi.org/10.21203/rs.3.rs-3995816/v1
26.
DuD.ZhuP.WenL.BianX.LingH.HuQ.PengT., et al. VisDrone-DET2019: The Vision Meets Drone Object Detection in Image Challenge Results. Proc., International Conference on Computer Vision Workshop, ICCVW 2019, Seoul, Korea, IEEE, New York, NY, 2019, pp. 213–226. https://doi.org/10.1109/ICCVW.2019.00030.
27.
LinH. Y.TuK. C.LiC. Y.VAID: An Aerial Image Dataset for Vehicle Detection and Classification. IEEE Access, Vol. 8, 2020, pp. 212209–212219. https://doi.org/10.1109/ACCESS.2020.3040290.
28.
RazakarivonyS.JurieF.Vehicle Detection in Aerial Imagery: A Small Target Detection Benchmark. Journal of Visual Communication and Image Representation, Vol. 34, 2016, pp. 187–203. https://doi.org/10.1016/j.jvcir.2015.11.002.
29.
KrajewskiR.BockJ.KloekerL.EcksteinL.The HighD Dataset: A Drone Dataset of Naturalistic Vehicle Trajectories on German Highways for Validation of Highly Automated Driving Systems. Proc., IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC, Maui, HI, IEEE, New York, NY, 2018, pp. 2118–2125. https://doi.org/10.1109/ITSC.2018.8569552.
30.
WangJ.TengX.LiZ.YuQ.BianY.WeiJ.VSAI: A Multi-View Dataset for Vehicle Detection in Complex Scenarios Using Aerial Images. Drones, Vol. 6, No. 7, 2022, p. 161. https://doi.org/10.3390/drones6070161.
31.
MaW.ZhongH.WangL.JiangL.Abdel-AtyM.MAGIC Dataset: Multiple Conditions Unmanned Aerial Vehicle Group-Based High-Fidelity Comprehensive Vehicle Trajectory Dataset. Transportation Research Record: Journal of the Transportation Research Board, 2022. 2676: 793–805. https://doi.org/10.1177/03611981211070549.
32.
HuY.LiY.HuangH.LeeJ.YuanC.ZouG.A High-Resolution Trajectory Data Driven Method for Real-Time Evaluation of Traffic Safety. Accident Analysis and Prevention, Vol. 165, 2022, p. 106503. https://doi.org/10.1016/j.aap.2021.106503.
33.
XieK.OzbayK.YangH.LiC.Mining Automatically Extracted Vehicle Trajectory Data for Proactive Safety Analytics. Transportation Research Part C: Emerging Technologies, Vol. 106, 2019, pp. 61–72. https://doi.org/10.1016/j.trc.2019.07.004.
34.
YangD.OzbayK.XieK.YangH.ZuoF.ShaD.Proactive Safety Monitoring: A Functional Approach to Detect Safety-Related Anomalies Using Unmanned Aerial Vehicle Video Data. Transportation Research Part C: Emerging Technologies, Vol. 127, 2021, p. 103130. https://doi.org/10.1016/j.trc.2021.103130.
35.
ZouZ.YangS.ZhaoL.Dual-Loop Control and State Prediction Analysis of QUAV Trajectory Tracking Based on Biological Swarm Intelligent Optimization Algorithm. Scientific Reports, Vol. 14, No. 1, 2024, pp. 1–25. https://doi.org/10.1038/s41598-024-69911-5.
36.
MajiA.GhoshI.ChandraS.Development of Conflict-Based Safety Performance Function for Safety Evaluation of Urban Roundabouts in India. Canadian Journal of Civil Engineering, Vol. 52, No. 4, 2024, pp. 498–515. https://doi.org/10.1139/cjce-2024-0314.
37.
LeonardiS.DistefanoN.Turbo-Roundabouts as an Instrument for Improving the Efficiency and Safety in Urban Area: An Italian Case Study. Sustainability (Switzerland), Vol. 15, No. 4, 2023, P. 3223. https://doi.org/10.3390/su15043223.
38.
GiuffrèT.GranàA.TrubiaS.Safety Evaluation of Turbo-Roundabouts with and without Internal Traffic Separations Considering Autonomous Vehicles Operation. Sustainability (Switzerland), Vol. 13, No. 16, 2021, p. 8810. https://doi.org/10.3390/su13168810.
39.
GuidoG.VitaleA.GallelliV.Investigating Rear-End Potential Conflicts for Roundabout Turning Movements. Modern Traffic and Transportation Engineering Research (MTTER), Vol. 2, No. 4, 2013, pp. 20–26.
40.
GuoY.SayedT.EssaM.Real-Time Conflict-Based Bayesian Tobit Models for Safety Evaluation of Signalized Intersections. Accident Analysis and Prevention, Vol. 144, 2020, p. 105660. https://doi.org/10.1016/j.aap.2020.105660.
41.
ArunA.HaqueM. M.BhaskarA.WashingtonS.Transferability of Multivariate Extreme Value Models for Safety Assessment by Applying Artificial Intelligence-Based Video Analytics. Accident Analysis and Prevention, Vol. 170, 2022, p. 106644. https://doi.org/10.1016/j.aap.2022.106644.
42.
FuC.SayedT.Random Parameters Bayesian Hierarchical Modeling of Traffic Conflict Extremes for Crash Estimation. Accident Analysis and Prevention, Vol. 157, 2021, p. 106159. https://doi.org/10.1016/j.aap.2021.106159.
43.
ZhengD.QinX.TillmanR.NoyceD. A.Negotiation-Based Conflict Exposure Methodology in Roundabout Crash Pattern Analysis. In 89th Annual Meeting of the Transportation Research Board, Washington, D.C., 2010. https://trid.trb.org/view/910063.
44.
ChenY.PersaudB.SacchiE.BassaniM.Investigation of Models for Relating Roundabout Safety to Predicted Speed. Accident Analysis and Prevention, Vol. 50, 2013, pp. 196–203. https://doi.org/10.1016/j.aap.2012.04.011.
45.
AnjanaS.AnjaneyuluM. V. L. R.Development of Safety Performance Measures for Urban Roundabouts in India. Journal of Transportation Engineering, Vol. 141, No. 1, 2014, p. 04014066. https://doi.org/10.1061/(ASCE)TE.1943.
46.
BagdadeJ.PersaudB.McIntoshK.YassinJ.LyonC. A.RedingerC.WhittenJ.ButchW. A.Evaluating the Performance and Safety Effectiveness of Roundabouts. The Michigan Department of Transportation, Lansing, 2011.
47.
DixonK.ZhengJ.Developing Safety Performance Measures for Roundabout Applications in the State of Oregon. FHWA-OR-RD-13-08, Vol. SPR 733. Federal Highway administration, Washington, D.C., 2013.
48.
MandavilliS.McCarttA. T.RettingR. A.Crash Patterns and Potential Engineering Countermeasures at Maryland Roundabouts. Traffic Injury Prevention, Vol. 10, No. 1, 2009, pp. 44–50. https://doi.org/10.1080/15389580802485938.
49.
DanielsS.BrijsT.NuytsE.WetsG.Externality of Risk and Crash Severity at Roundabouts. Accident Analysis and Prevention, Vol. 42, No. 6, 2010, pp. 1966–1973. https://doi.org/10.1016/j.aap.2010.06.001.
50.
BurdettB.BillA. R.NoyceD. A.Evaluation of Roundabout-Related Single-Vehicle Crashes. Transportation Research Record: Journal of the Transportation Research Board, 2017. 2637: 17–26.
51.
RodegerdtsL.BloggM.WempleE.MyersE.KyteE.DixonM.ListG.FlanneryA.TroutbeckR.BrilonW.WuN.PersaudB.LyonC.HarkeyD.CarterD.NCHRP Report 572: Roundabouts in the United States. Transportation Research Board (The National Academies), Washington, D.C., 2007.
52.
KimS.ChoiJ.Safety Analysis of Roundabout Designs Based on Geometric and Speed Characteristics. KSCE Journal of Civil Engineering, Vol. 17, No. 6, 2013, pp. 1446–1454. https://doi.org/10.1007/s12205-013-0177-4.
53.
KamlaJ.ParryT.DawsonA.Roundabout Accident Prediction Model Random-Parameter Negative Binomial Approach. Transportation Research Record: Journal of the Transportation Research Board, 2016. 2585: 11–19.
WangY.SuQ.WangC.PratoC. G.Investigating Yielding Behavior of Heterogeneous Vehicles at a Semi-Controlled Crosswalk. Accident Analysis and Prevention, Vol. 161, 2021, p. 106381. https://doi.org/10.1016/j.aap.2021.106381.
58.
PandeA.ChandS.SaxenaN.DixitV.LoyJ.WolshonB.KentJ. D.A Preliminary Investigation of the Relationships between Historical Crash and Naturalistic Driving. Accident Analysis and Prevention, Vol. 101, 2017, pp. 107–116. https://doi.org/10.1016/j.aap.2017.01.023.
59.
OnanA.Mining Opinions from Instructor Evaluation Reviews: A Deep Learning Approach. Computer Applications in Engineering Education, Vol. 28, No. 1, 2020, pp. 117–138. https://doi.org/10.1002/cae.22179.
60.
OsamaA.SayedT.ZakiM. H.ShaabanK.An Inclusive Framework for Automatic Safety Evaluation of Roundabouts. Journal of Transportation Safety and Security, Vol. 8, No. 4, 2016, pp. 377–394. https://doi.org/10.1080/19439962.2015.1107795.
61.
Bulla-CruzL. A.LaureshynA.LyonsL.Event-Based Road Safety Assessment: A Novel Approach towards Risk Microsimulation in Roundabouts. Measurement: Journal of the International Measurement Confederation, Vol. 165, 2020, p. 108192. https://doi.org/10.1016/j.measurement.2020.108192.
62.
VasconcelosL.NetoL.SecoÁ. M.SilvaA. B.Validation of the Surrogate Safety Assessment Model for Assessment of Intersection Safety. Transportation Research Record: Journal of the Transportation Research Board, 2014. 2432: 1–9.
