Multi-Camera Person Tracking: Integrating YOLOv8 with ByteTrack
| International Journal of Electrical and Electronics Engineering |
| © 2024 by SSRG - IJEEE Journal |
| Volume 11 Issue 10 |
| Year of Publication : 2024 |
| Authors : Nirali Anand Pandya, Narendrasinh C. Chauhan |
10.14445/23488379/IJEEE-V11I10P106
How to Cite?
Nirali Anand Pandya, Narendrasinh C. Chauhan, "Multi-Camera Person Tracking: Integrating YOLOv8 with ByteTrack," SSRG International Journal of Electrical and Electronics Engineering, vol. 11, no. 10, pp. 53-60, 2024. Crossref, https://doi.org/10.14445/23488379/IJEEE-V11I10P106
Abstract:
Accurate and efficient person tracking in complex, multi-camera environments remains challenging. This paper proposes a novel approach that integrates the strengths of YOLOv8, an advanced model for object detection, with ByteTrack, an advanced multi-object tracking algorithm. The proposed framework is evaluated on the challenging Multi-camera Pedestrians Video Dataset to assess its performance in complex real-world scenarios. Experimental results demonstrate the effectiveness of the proposed method in accurately tracking pedestrians across multiple cameras, outperforming existing state-of-the-art techniques. Integrating YOLOv8 and ByteTrack enables robust pedestrian detection and tracking, even in challenging conditions such as occlusions, varying illumination, and camera perspectives. The proposed approach holds significant potential for intelligent surveillance systems, crowd analysis, and autonomous vehicle applications.
Keywords:
Multi-camera Person tracking, YOLOv8, Bytetrack, Object detection, Deep Neural Network.
References:
[1] Saad M. Khan, and Mubarak Shah, “Tracking Multiple Occluding People by Localizing on Multiple Scene Planes,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 31, no. 3, pp. 505-519, 2009.
[CrossRef] [Google Scholar] [Publisher Link]
[2] O. Javed, K. Shafique, and M. Shah, “Appearance Modeling for Tracking in Multiple Non-Overlapping Cameras,” 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), San Diego, CA, USA, vol. 2, pp. 26-33, 2005.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Liliang Zhang et al., “Is Faster R-CNN Doing Well for Pedestrian Detection?,” Computer Vision – ECCV 2016, pp. 443-457, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Joseph Redmon et al., “You Only Look Once: Unified, Real-Time Object Detection,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, pp. 779-788, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Alexey Bochkovskiy, Chien-Yao Wang, and Hong-Yuan Mark Liao, “YOLOv4: Optimal Speed and Accuracy of Object Detection,” arXiv Preprint, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Yifu Zhang et al., “ByteTrack: Multi-Object Tracking by Associating Every Detection Box,” Computer Vision - ECCV 2022, pp. 1-21, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Nicolai Wojke, Alex Bewley, and Dietrich Paulus, “Simple Online and Realtime Tracking with a Deep Association Metric,” 2017 IEEE International Conference on Image Processing (ICIP), Beijing, China, pp. 3645-3649, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Alex Bewley et al., “Simple Online and Realtime Tracking,” 2016 IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, USA, pp. 3464-3468, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Ivan Krasin et al., Openimages: A Public Dataset for Large-Scale Multi-Label and Multi-Class Image Classification, 2020. [Online]. Available: https://github.com/openimages/dataset
[10] Francois Fleuret et al., “Multicamera People Tracking with a Probabilistic Occupancy Map,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 30, no. 2, pp. 267-282, 2008.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Temitope Ibrahim Amosa et al., “Multi-Camera Multi-Object Tracking: A Review of Current Trends and Future Advances,” Neurocomputing, vol. 552, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[12] B. Dwyer, J. Nelson, and T. Hansen, Roboflow (Version 1.0), 2024. [Online]. Available: https://roboflow.com/research#cite
[13] Abhishek Balasubramaniam, and Sudeep Pasricha, “Object Detection in Autonomous Vehicles: Status and Open Challenges,” arXiv Preprint, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[14] M. Sami Zitouni et al., “Advances and Trends in Visual Crowd Analysis: A Systematic Survey and Evaluation of Crowd Modelling Techniques,” Neurocomputing, vol. 186, pp. 139-159, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Joseph Redmon, Ali Farhadi, “Yolov3: An Incremental Improvement,” arXiv Preprint, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Xingkui Zhu et al., “TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-Captured Scenarios” 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Montreal, BC, Canada, pp. 2778-2788, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Chuyi Li et al., “YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications,” arXiv Preprint, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Chien-Yao Wang, Alexey Bochkovskiy, Hong-Yuan Mark Liao, “YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors,” 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada, pp. 7464-7475, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Anton Milan et al., “MOT16: A Benchmark for Multi-Object Tracking,” arXiv Preprint, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Laura Leal-Taixé et al., “Motchallenge 2015: Towards a Benchmark for Multi-Target Tracking,” arXiv Preprint, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Zhong-Qiu Zhao et al., “Object Detection with Deep Learning: A Review,” IEEE Transactions on Neural Networks and Learning Systems, vol. 30, no. 11, pp. 3212-3232, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Dillon Reis et al., “Real-Time Flying Object Detection with YOLOv8,” arXiv Preprint, 2023.
[CrossRef] [Google Scholar] [Publisher Link]