The Impact of Weather, Lighting, and Camera Viewpoint on the Traffic Monitoring Performance of YOLO-SORT

Enas Elshebli; Erdos Ferenc; Anwar Khan; Vijayakumar Varadarajan

doi:10.48084/etasr.18369

Authors

Enas Elshebli Szechenyi Istvan University, Gyor, Hungary
Erdos Ferenc Szechenyi Istvan University, Gyor, Hungary
Anwar Khan Department of Electronics, University of Peshawar, Peshawar, KPK, Pakistan
Vijayakumar Varadarajan University of Technology Sydney, Australia | Swiss School of Business and Management, Geneva, Switzerland

Volume: 16 | Issue: 4 | Pages: 37151-37164 | August 2026 | https://doi.org/10.48084/etasr.18369

Received: 24 February 2026 | Revised: 31 March 2026 | Accepted: 17 April 2026 | Online: 3 June 2026

Corresponding author: Enas Elshebli

Abstract

This study investigates the condition sensitivity of a camera-based traffic monitoring pipeline that combines YOLOv8s detection with SORT tracking for real-time vehicle counting. Video data were collected from a pedestrian bridge above a two-lane highway in Győr, Hungary, under multiple weather conditions (clear, rainy, foggy), lighting (day, night) conditions, and viewpoint (central, moderate shift, maximum available shift) configurations. Pixels-per-meter calibration, normalized trajectories, and bounding-box dimensions across angles, and a trajectory-based count line produced event-level ground truth. Performance was evaluated using minute-level precision, recall, and F1-score, with condition-wise and angle-wise differences assessed via Wilcoxon signed-rank tests with Holm's correction and associated effect sizes. Across all angles, the pipeline maintained high F1-scores, with nighttime conditions yielding the highest and most stable performance, supported by consistent street lighting and lower traffic flow. Fog produced the most persistent degradation, while rain mainly caused brief precision dips during onset. Aggregated across conditions, no statistically significant differences were observed between viewpoints, indicating that within the studied range of angles, environmental factors dominate over camera orientation. Overall, the results suggest that YOLOv8s and SORT can support accurate real-time vehicle counting in CCTV-like deployments while remaining sensitive to reduced visibility and peak-traffic occlusions.

Keywords:

traffic monitoring, vehicle detection and tracking, YOLO, SORT, camera viewpoint analysis, real-time video analytics

References

[1] G. Hoxha, A. Fandaj, and X. Bajrami, "Quality of Automatic Traffic Volume Counting by Cameras and Impact on the Qualitative Indicators of Traffic," Infrastructures, vol. 8, no. 3, Feb. 2023, Art. no. 44.

[2] P. Zheng and M. Mike, "An Investigation on the Manual Traffic Count Accuracy," Procedia - Social and Behavioral Sciences, vol. 43, pp. 226–231, 2012.

[3] M. Majumder and C. Wilmot, "Automated Vehicle Counting from Pre-Recorded Video Using You Only Look Once (YOLO) Object Detection Model," Journal of Imaging, vol. 9, no. 7, June 2023, Art. no. 131.

[4] C. J. Lin, S. Y. Jeng, and H. W. Lioa, "A Real-Time Vehicle Counting, Speed Estimation, and Classification System Based on Virtual Detection Zone and YOLO," Mathematical Problems in Engineering, vol. 2021, pp. 1–10, Nov. 2021.

[5] S. Kumar et al., "Fusion of Deep Sort and Yolov5 for Effective Vehicle Detection and Tracking Scheme in Real-Time Traffic Management Sustainable System," Sustainability, vol. 15, no. 24, Dec. 2023, Art. no. 16869.

[6] S. Feng, X. Cai, L. Li, W. Wang, and S. Ying, "A review of research on vehicle detection in adverse weather environments," Journal of Traffic and Transportation Engineering (English Edition), vol. 12, no. 5, pp. 1452–1483, Oct. 2025.

[7] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You Only Look Once: Unified, Real-Time Object Detection," in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016, pp. 779–788.

[8] J. Redmon and A. Farhadi, "YOLO9000: Better, Faster, Stronger," in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017, pp. 6517–6525.

[9] W. Liu et al., "SSD: Single Shot MultiBox Detector," in Computer Vision – ECCV 2016, vol. 9905, B. Leibe, J. Matas, N. Sebe, and M. Welling, Eds. Springer International Publishing, 2016, pp. 21–37.

[10] Z. Tian, C. Shen, H. Chen, and T. He, "FCOS: Fully Convolutional One-Stage Object Detection," in 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Oct. 2019, pp. 9626–9635.

[11] S. Ren, K. He, R. Girshick, and J. Sun, "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 6, pp. 1137–1149, June 2017.

[12] T. Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollar, "Focal Loss for Dense Object Detection," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 42, no. 2, pp. 318–327, Feb. 2020.

[13] M. Tan, R. Pang, and Q. V. Le, "EfficientDet: Scalable and Efficient Object Detection," in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020, pp. 10778–10787.

[14] J. Huang et al., "Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors," in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017, pp. 3296–3297.

[15] A. Bewley, Z. Ge, L. Ott, F. Ramos, and B. Upcroft, "Simple online and realtime tracking," in 2016 IEEE International Conference on Image Processing (ICIP), Sept. 2016, pp. 3464–3468.

[16] N. Wojke, A. Bewley, and D. Paulus, "Simple online and realtime tracking with a deep association metric," in 2017 IEEE International Conference on Image Processing (ICIP), Sept. 2017, pp. 3645–3649.

[17] Y. Zhang et al., "ByteTrack: Multi-object Tracking by Associating Every Detection Box," in Computer Vision – ECCV 2022, vol. 13682, S. Avidan, G. Brostow, M. Cissé, G. M. Farinella, and T. Hassner, Eds. Springer Nature Switzerland, 2022, pp. 1–21.

[18] M. Humayun, F. Ashfaq, N. Z. Jhanjhi, and M. K. Alsadun, "Traffic Management: Multi-Scale Vehicle Detection in Varying Weather Conditions Using YOLOv4 and Spatial Pyramid Pooling Network," Electronics, vol. 11, no. 17, Sept. 2022, Art. no. 2748.

[19] R. Wang et al., "Real-time vehicle target detection in inclement weather conditions based on YOLOv4," Frontiers in Neurorobotics, vol. 17, Mar. 2023, Art. no. 1058723.

[20] R. Kejriwal, R. H J, A. Arora, and Mohana, "Vehicle Detection and Counting using Deep Learning basedYOLO and Deep SORT Algorithm for Urban Traffic Management System," in 2022 First International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT), Feb. 2022, pp. 1–6.

[21] S. Bose, C. D. Ramesh, and M. H. Kolekar, "Vehicle Classification and Counting for Traffic Video Monitoring Using YOLO-v3," in 2022 International Conference on Connected Systems & Intelligence (CSI), Aug. 2022, pp. 1–8.

[22] M. Guo, S. Song, W. Zhao, L. Chen, J. Zhou, and T. Zhang, "A Traffic Flow Monitoring System Based on YOLOv8 and DeepSORT for Real-Time Vehicle Tracking," in 2025 IEEE International Conference on Pattern Recognition, Machine Vision and Artificial Intelligence (PRMVAI), June 2025, pp. 1–5.

[23] B. Sathiyaprasad, P. A. R. Reddy, and D. M. Venkatesh, "TrackNCount - Intelligent Vehicle Tracking, Counting, and Speed Estimation Using YOLOv8 and DeepSORT Algorithms," in 2025 6th International Conference on Mobile Computing and Sustainable Informatics (ICMCSI), Jan. 2025, pp. 1738–1744.

[24] Z. Chu, "D-YOLO a robust framework for object detection in adverse weather conditions." arXiv, 2024.

[25] H. Abbasi, M. Amini, and F. R. Yu, "Fog-Aware Adaptive YOLO for Object Detection in Adverse Weather," in 2023 IEEE Sensors Applications Symposium (SAS), July 2023, pp. 1–6.

[26] X. Meng, Y. Liu, L. Fan, and J. Fan, "YOLOv5s-Fog: An Improved Model Based on YOLOv5s for Object Detection in Foggy Weather Scenarios," Sensors, vol. 23, no. 11, June 2023, Art. no. 5321.

[27] Q. Zhang, W. Guo, and M. Lin, "LLD-YOLO: a multi-module network for robust vehicle detection in low-light conditions," Signal, Image and Video Processing, vol. 19, no. 4, Apr. 2025, Art. no. 271.

[28] Y. Miao, F. Liu, T. Hou, L. Liu, and Y. Liu, "A Nighttime Vehicle Detection Method Based on YOLO v3," in 2020 Chinese Automation Congress (CAC), Nov. 2020, pp. 6617–6621.

[29] N. Ho, M. Pham, N. D. Vo, and K. Nguyen, "Vehicle Detection at Night Time," in 2020 7th NAFOSTED Conference on Information and Computer Science (NICS), Nov. 2020, pp. 250–255.

[30] M. Chaman et al., "A Real-Time Vehicle Detection System for ADAS in Autonomous Vehicles Using YOLOv11 Deep Neural Network on Embedded Edge Platforms," Engineering, Technology & Applied Science Research, vol. 15, no. 5, pp. 28077–28082, Oct. 2025.

[31] X. Li, L. Chen, T. Huang, A. Yang, and W. Liu, "YOLO-edge: real-time vehicle detection for edge devices," Cluster Computing, vol. 28, no. 5, Aug. 2025, Art. no. 289.

[32] Z. Han, Z. Yue, and L. Liu, "3L-YOLO: A Lightweight Low-Light Object Detection Algorithm," Applied Sciences, vol. 15, no. 1, Dec. 2024, Art. no. 90.

[33] Y. Gu, L. Chen, and T. Su, "Research on Small Object Detection in Degraded Visual Scenes: An Improved DRF-YOLO Algorithm Based on YOLOv11," World Electric Vehicle Journal, vol. 16, no. 11, Oct. 2025, Art. no. 591.

[34] "YOLOv10: Real-Time End-to-End Object Detection," Ultralytics Docs, May 25, 2024. https://docs.ultralytics.com/models/yolov10.

[35] "Ultralytics YOLO11," Ultralytics Docs, Sept. 30, 2024. https://docs.ultralytics.com/models/yolo11.

[36] "YOLO12: Attention-Centric Object Detection," Ultralytics Docs, Feb. 20, 2025. https://docs.ultralytics.com/models/yolo12.

[37] J. Yang, H. Xie, X. Zhang, J. Chen, and S. Sun, "Enhancing Mine Safety with YOLOv8-DBDC: Real-Time PPE Detection for Miners," Electronics, vol. 14, no. 14, July 2025, Art. no. 2788.

[38] Y. Qin, J. Dong, W. Li, L. Zhang, K. Feng, and Z. Wang, "PSD-YOLO: An Enhanced Real-Time Framework for Robust Worker Detection in Complex Offshore Oil Platform Environments," Sensors, vol. 25, no. 20, Oct. 2025, Art. no. 6264.

[39] "Hikvision Global - Leading the future of AIoT." https://www.hikvision.com/en/.

[40] F. Wilcoxon, "Individual Comparisons by Ranking Methods," Biometrics Bulletin, vol. 1, no. 6, Dec. 1945, Art. no. 80.

[41] S. Holm, "A Simple Sequentially Rejective Multiple Test Procedure," Scandinavian Journal of Statistics, vol. 6, no. 2, pp. 65–70, 1979.

[42] T. C. Vu et al., "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, vol. 2, no. 2, pp. 255–268, June 2025.

[43] D. Stiller et al., "Open webcam data for traffic monitoring: YOLOv8 detection of road users before and during COVID-19," Transportation Research Interdisciplinary Perspectives, vol. 36, Mar. 2026, Art. no. 101774.