Computer Vision-Based Traffic and Pedestrian Analysis Using Video Feeds

Author

Assistant Professor Smita Mangesh Junnarkar,Sunil Manoj

Abstract

 Urban roads are shared by vehicles and pedestrians, and planners need dependable measurements of how both groups use that space. Manual counting is slow and expensive, and many sensor-based methods cover only one kind of road user. This paper presents a computer vision pipeline that analyzes ordinary video feeds to detect, track, and count vehicles and pedestrians in a single pass. The system combines a pretrained YOLO object detector, a multi-object tracker that assigns persistent identities, and a lightweight analytics layer that performs virtual line counting, zone occupancy estimation, and proximity-based interaction indicators. The pipeline is implemented in Python with OpenCV and is exposed through a Streamlit dashboard that runs on a standard Windows laptop without specialized hardware. The paper describes the design rationale, the processing stages, an evaluation protocol based on detection, tracking, and counting metrics, and the practical limits that arise from occlusion, camera geometry, illumination, and the use of a model that has not been fine-tuned to local traffic. Privacy and ethical safeguards are also discussed, including the decision to analyze only aggregate movement and to avoid face or license plate recognition. The work shows that a modular, open-source pipeline can serve as an accessible starting point for traffic and pedestrian analytics in academic and small-scale civic settings.

Keywords

computer vision, traffic analysis, pedestrian detection, YOLO, object tracking, OpenCV, video analytics, intelligent transportation systems

Full Text:

Download Paper PDF

References

[1] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2016, pp. 779–788.

[2] J. Redmon and A. Farhadi, “YOLOv3: An incremental improvement,” arXiv:1804.02767, 2018.

[3] A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, “YOLOv4: Optimal speed and accuracy of object detection,” arXiv:2004.10934, 2020.

[4] C.-Y. Wang, A. Bochkovskiy, and H.-Y. M. Liao, “YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition (CVPR), 2023, pp. 7464–7475.

[5] G. Jocher, A. Chaurasia, and J. Qiu, “Ultralytics YOLOv8,” software, 2023. [Online]. Available: https://github.com/ultralytics/ultralytics

[6] T.-Y. Lin et al., “Microsoft COCO: Common objects in context,” in Proc. European Conf. Computer Vision (ECCV), 2014, pp. 740–755.

[7] A. Bewley, Z. Ge, L. Ott, F. Ramos, and B. Upcroft, “Simple online and realtime tracking,” in Proc. IEEE Int. Conf. Image Processing (ICIP), 2016, pp. 3464–3468.

[8] N. Wojke, A. Bewley, and D. Paulus, “Simple online and realtime tracking with a deep association metric,” in Proc. IEEE Int. Conf. Image Processing (ICIP), 2017, pp. 3645–3649.

[9] Y. Zhang et al., “ByteTrack: Multi-object tracking by associating every detection box,” in Proc. European Conf. Computer Vision (ECCV), 2022, pp. 1–21.

[10] S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards real-time object detection with region proposal networks,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 39, no. 6, pp. 1137–1149, 2017.

[11] P. Dollár, C. Wojek, B. Schiele, and P. Perona, “Pedestrian detection: An evaluation of the state of the art,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 34, no. 4, pp. 743–761, 2012.

[12] W. Liu et al., “SSD: Single shot multibox detector,” in Proc. European Conf. Computer Vision (ECCV), 2016, pp. 21–37.

[13] K. Bernardin and R. Stiefelhagen, “Evaluating multiple object tracking performance: The CLEAR MOT metrics,” EURASIP J. Image and Video Processing, vol. 2008, Art. no. 246309, 2008.

[14] C. Stauffer and W. E. L. Grimson, “Adaptive background mixture models for real-time tracking,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 1999, pp. 246–252.

[15] Z. Zivkovic, “Improved adaptive Gaussian mixture model for background subtraction,” in Proc. Int. Conf. Pattern Recognition (ICPR), 2004, vol. 2, pp. 28–31.

[16] N. Buch, S. A. Velastin, and J. Orwell, “A review of computer vision techniques for the analysis of urban traffic,” IEEE Trans. Intelligent Transportation Systems, vol. 12, no. 3, pp. 920–939, 2011.

[17] N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2005, pp. 886–893.

[18] Y. Zhao et al., “DETRs beat YOLOs on real-time object detection,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition (CVPR), 2024.

[19] R. E. Kalman, “A new approach to linear filtering and prediction problems,” J. Basic Engineering, vol. 82, no. 1, pp. 35–45, 1960.

[20] H. W. Kuhn, “The Hungarian method for the assignment problem,” Naval Research Logistics Quarterly, vol. 2, no. 1–2, pp. 83–97, 1955.

[21] N. Aharon, R. Orfaig, and B.-Z. Bobrovsky, “BoT-SORT: Robust associations multi-pedestrian tracking,” arXiv:2206.14651, 2022.

[22] E. Ristani, F. Solera, R. Zou, R. Cucchiara, and C. Tomasi, “Performance measures and a data set for multi-target, multi-camera tracking,” in ECCV Workshops, 2016, pp. 17–35.

[23] J. Luiten et al., “HOTA: A higher order metric for evaluating multi-object tracking,” Int. J. Computer Vision, vol. 129, no. 2, pp. 548–578, 2021.

[24] A. Milan, L. Leal-Taixé, I. Reid, S. Roth, and K. Schindler, “MOT16: A benchmark for multi-object tracking,” arXiv:1603.00831, 2016.

[25] L. Wen et al., “UA-DETRAC: A new benchmark and protocol for multi-object detection and tracking,” Computer Vision and Image Understanding, vol. 193, Art. no. 102907, 2020.

[26] A. Geiger, P. Lenz, and R. Urtasun, “Are we ready for autonomous driving? The KITTI vision benchmark suite,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2012, pp. 3354–3361.

[27] G. Bradski, “The OpenCV library,” Dr. Dobb's Journal of Software Tools, 2000.

[28] Government of India, Ministry of Law and Justice, “The Digital Personal Data Protection Act, 2023,” 2023.

Share your valuable work from Social Media Buttons