Real-Time Multi-Input Object Tracking and Speed Estimation via YOLOv8 and Kalman Filters for Smart Environments

G. HariHaran; Gunjan Singh

doi:10.55524/ijirem.2025.12.6.19

Abstract

This?‍?‌‍?‍‌?‍?‌‍?‍‌ work presents a real-time, multi-input, multi-object tracking, and speed estimation system that uses YOLOv8 deep learning detector fused with Kalman Filter-based predictive tracking. By coupling cutting-edge detection accuracy with strong motion prediction, the article deals with problems of occlusions, noisy detections, variable motion, and heterogeneous video sources that are typical of smart environments. Kalman Filters are implemented to allow stable identity assignment, trajectory smoothing, and frame-consistent speed estimation while YOLOv8 is the primary detection tool due to its anchor-free, multi-scale design, and rapid inference. The multi-video-stream-compatible system, which can also be used in the area of intelligent surveillance, traffic monitoring, and automated analytics by CCTV, webcams, recorded footage, and image uploads, has different potential usages. Encrypted logging is present to guarantee the security of Meta data storage in privacy-sensitive environments. The?‍?‌‍?‍‌?‍?‌‍?‍‌ results of the research presented in the paper reveal the potential of the system to carry out object identity retention, multi-object trajectory management, and on-the-fly calculation of motion parameters, thus providing a scalable and flexible platform for smart cities and industrial applications. Such a system is a significant move forward to the eventual establishment of a real-time tracking system framework that is resilient, modular, and respectful of privacy, hence making a substantial incremental development towards the evolution of these systems in dynamic smart ‍?‌‍?‍‌?‍?‌‍?‍‌environments.

Keywords

YOLOv8, Kalman Filter, Multi-object Tracking, Smart Environments, Speed Estimation.

References

Bewley, Z. Ge, L. Ott, F. Ramos, and B. Upcroft, “Simple online and realtime tracking,” in Proc. IEEE Int. Conf. Image Processing (ICIP), Phoenix, AZ, USA, 2016, pp. 3464–3468. Available from: https://doi.org/10.1109/ICIP.2016.7533003
Y. Bar-Shalom and X. R. Li, Estimation and Tracking: Principles, Techniques, and Software. Norwood, MA, USA: Artech House, 1993. Available from: https://cir.nii.ac.jp/crid/1971149384843963944
Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, “YOLOv4: Optimal speed and accuracy of object detection,” arXiv preprint, arXiv:2004.10934, 2020. Available from: https://doi.org/10.48550/arXiv.2004.10934
Farahi, H. Arefi, and M. Abedini, “Probabilistic Kalman filter for moving object tracking,” J. Visual Commun. Image Represent., vol. 67, p. 102739, 2020. Available from: https://doi.org/10.1016/j.image.2019.115751
M. S. Grewal and A. P. Andrews, Kalman Filtering: Theory and Practice Using MATLAB, 2nd ed. New York, NY, USA: Wiley-Interscience, 2001.
R. Girshick, “Fast R-CNN,” in Proc. IEEE Int. Conf. Computer Vision (ICCV), Santiago, Chile, 2015, pp. 1440–1448.
S. Hajinazar et al., “Multi-modal sensor fusion for highly accurate vehicle motion state estimation,” Sensors, vol. 23, no. 14, p. 6290, 2023. Available from: https://doi.org/10.3390/s23146290
W. Huang, B. Chen, and M. Newaz, “Multi-sensor fusion for target tracking in autonomous vehicles,” Sensors, vol. 19, no. 20, p. 4467, 2019. Available from: https://doi.org/10.3390/s19204467
Jocher, “YOLOv8 documentation,” Ultralytics, May 18, 2020. Available from: https://ieeexplore.ieee.org/abstract/document/11207062
Jocher et al., “YOLOv5,” 2021. Available from: https://github.com/ultralytics/yolov5
R. E. Kalman, “A new approach to linear filtering and prediction problems,” J. Basic Eng., vol. 82, no. 1, pp. 35–45, 1960. Available from: https://doi.org/10.1115/1.3662552
Keylabs, “Real-time object detection with YOLOv8,” Feb. 26, 2024. Available from: https://keylabs.ai/blog/real-time-object-detection-with-yolov8
W. Liu et al., “SSD: Single shot multibox detector,” in Proc. Eur. Conf. Computer Vision (ECCV), Amsterdam, Netherlands, 2016, pp. 21–37. Available from: https://link.springer.com/chapter/10.1007/978-3-319-46448-0_2
Y. Liu et al., “Improved non-maximum suppression for embedded single-shot detectors,” IEEE Trans. Intell. Veh., vol. 4, no. 3, pp. 345–354, 2019.
Moksyakov, L. Chen, and J. Zhao, “Multi-object tracking in smart cities using YOLOv8 and Kalman filter algorithms,” Sensors, vol. 23, no. 4, p. 9812, 2024.
MathWorks, “Introduction to Kalman filters for object tracking,” 2013. Available from: https://www.mathworks.com/help/vision/examples/target-tracking-using-kalman-filter.html
Milan, L. Leal-Taixe, I. Reid, S. Roth, and K. Schindler, “MOT17 dataset,” arXiv preprint, arXiv:1706.05567, 2017. Available from: https://tinyurl.com/ye5j6ahs
Najda et al., “Multi-modal sensor fusion and object tracking for autonomous driving: A systematic survey,” IEEE Trans. Intell. Transp. Syst., vol. 25, no. 2, pp. 1425–1443, 2024. Available from: https://ieeexplore.ieee.org/abstract/document/10113239
Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in Proc. IEEE Conf. Computer Vision Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016, pp. 779–788. Available from: https://tinyurl.com/4z5ddna4
Roboflow, “What is YOLOv8? A complete guide,” Nov. 10, 2025.
Redmon and A. Farhadi, “YOLOv3: An incremental improvement,” arXiv preprint, arXiv:1804.02767, 2018.
S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards real-time object detection with region proposal networks,” in Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), vol. 28, 2015, pp. 91–99. Available from: https://ieeexplore.ieee.org/abstract/document/7485869
S. Ren, K. He, R. Girshick, and J. Sun, “Improvements to the R-CNN framework for object detection,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 6, pp. 1137–1142, 2017. Available from: https://tinyurl.com/3rrzezmz
W. Sheng et al., “Multi-objective pedestrian tracking method based on YOLOv8 and improved DeepSORT,” Math. Biosci. Eng., vol. 21, no. 2, pp. 1791–1805, 2024. Available from: https://doi.org/10.3934/mbe.2024077
Scaler, “Kalman filter in computer vision,” 2023. Available from: https://www.scaler.com/topics/kalman-filter-in-computer-vision/
Ultralytics, “Kalman filter (KF) explained,” 2025.
R. Varghese, “YOLOv8: A novel object detection algorithm with advanced accuracy and speed,” IEEE Access, vol. 12, pp. 16245–16262, 2024. Available from: https://ieeexplore.ieee.org/abstract/document/10533619
R. Verma et al., “Real-time vehicle tracking using LiDAR and mono-camera sensor fusion,” IEEE Sensors J., vol. 22, no. 19, pp. 18438–18447, 2022.
Wang, Y. Lu, and Y. You, “YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors,” arXiv preprint, arXiv:2207.02696, 2022. Available from: https://tinyurl.com/45ar747s
Yadav, R. Kumar, and P. Singh, “Object detection and tracking using YOLOv8 and Kalman filters,” Int. J. Comput. Appl., vol. 75, no. 12, pp. 55–61, 2023.
Zheng et al., “Research on vehicle tracking method based on YOLOv8 and adaptive Kalman filtering,” Open J. Appl. Sci., vol. 13, no. 9, pp. 1204–1222, 2023.
Y. Zeng, B. Zhou, and S. Yu, “Anchor-free object detection with feature pyramid networks,” in Proc. IEEE Conf. Computer Vision Pattern Recognition (CVPR), Salt Lake City, UT, USA, 2018, pp. 7867–7876.

Cites this article as

G. HariHaran, G. Singh, "Real-Time Multi-Input Object Tracking and Speed Estimation via YOLOv8 and Kalman Filters for Smart Environments", International Journal of Innovative Research in Engineering and Management (IJIREM), Vol-12, Issue-6, Page No-104-110, 2025. Available from: https://doi.org/10.55524/ijirem.2025.12.6.19