Motion-Pattern-Based Multi-Object Tracking for Real-Time Edge Computing Deployment
DOI:
https://doi.org/10.32890/jict2026.25.2.5Keywords:
Computer vision, embedded systems, energy efficiency, object tracking, real-time processingAbstract
Real-time object tracking in embedded systems requires algorithms that balance processing performance with energy efficiency for practical deployment. This study evaluates the performance of the TG-Lite algorithm on Jetson Nano embedded hardware for surveillance applications requiring a minimum processing rate of 10 frames per second (FPS). The methodology involves comprehensive performance analysis, measuring frame-processing rates, energy consumption patterns, and system resource utilisation across video-file and live-stream scenarios. TG-Lite achieves 15.51 FPS processing capability with 11.24 watts (W) power consumption, meeting real-time processing requirements for embedded surveillance deployment. The algorithm demonstrates consistent performance across different input conditions, maintaining stable processing rates on both video files (10.86 FPS) and live streams (15.51 FPS). TG-Lite exhibits efficient resource utilisation, with moderate central processing unit (CPU) usage (17.4% average) and effective graphics processing unit (GPU) acceleration. The energy analysis reveals TG-Lite's 1.38 frames-per-watt efficiency, indicating effective allocation of computational resources for real-time processing demands. Performance evaluation shows that TG-Lite maintains stable tracking continuity, with an average track length of 35.8 frames and a consistent confidence distribution pattern. These results demonstrate the suitability of the proposed approach for embedded computer vision applications under the evaluated edge constraints.
References
Aharon, N., Orfaig, R., & Bobrovsky, B.-Z. (2022). BoT-SORT: Robust associations multi-pedestrian tracking. http://arxiv.org/abs/2206.14651
An, Y., Wu, J., Cui, Y., & Hu, H. (2023). Multi-object tracking based on a novel feature image with multi-modal information. IEEE Transactions on Vehicular Technology, 72(8), 9909–9921. https://doi.org/10.1109/TVT.2023.3259999
Ansari, M. A., & Singh, D. K. (2022). ESAR, an expert shoplifting activity recognition system. Cybernetics and Information Technologies, 22(1), 190–200. https://doi.org/10.2478/cait-2022-0012
Bewley, A., Ge, Z., Ott, L., Ramos, F., & Upcroft, B. (2016). Simple online and realtime tracking. Proceedings - International Conference on Image Processing, ICIP, 2016-August, 3464–3468. https://doi.org/10.1109/ICIP.2016.7533003
Cao, J., Pang, J., Weng, X., Khirodkar, R., & Kitani, K. (2023). Observation-centric SORT: Rethinking SORT for robust multi-object tracking. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2023-June, 9686–9696. https://doi.org/10.1109/ CVPR52729.2023.00934
Du et al. (2023a). StrongSORT: Make DeepSORT Great Again. IEEE Transactions on Multimedia, 25, 8725–8737. https://doi.org/10.1109/TMM.2023.3240881
Ganesh, S. V., Wu, Y., Liu, G., Kompella, R., & Liu, L. (2023). Fast and resource-efficient object tracking on edge devices: A measurement study. https://arxiv.org/pdf/2309.02666 Global Road Safety | Transportation Safety | CDC. (n.d.). https://www.cdc.gov/transportation-safety/global/index.html
Guan et al. (2025). Multi-object tracking review: Retrospective and emerging trend. Artificial Intelligence Review, 58(8), 1–46. https://doi.org/10.1007/S10462-025-11212-Y/TABLES/8
Khalil, M. M., Saleh, S. N., Tawfik, N. S., & Elagamy, M. N. (2025). EF-StrongSORT: An enhanced feature StrongSORT model for multi-object tracking. IEEE Access, 13, 53608–53620. https://doi.org/10.1109/ACCESS.2025.3554706
Li, X., Chen, C., Lou, Y., Abdallah, M., Kim, K. T., & Bagchi, S. (2024). HopTrack: A real-time multi-object tracking system for embedded devices. https://arxiv.org/pdf/2411.00608v1
Murat, A. A., & Kiran, M. S. (2025). A comprehensive review on YOLO versions for object detection. Engineering Science and Technology, an International Journal, 70, 102161. https://doi.org/10.1016/J.JESTCH.2025.102161
Nasir, R., Jalil, Z., Nasir, M., Alsubait, T., Ashraf, M., & Saleem, S. (2025). An enhanced framework for real-time dense crowd abnormal behavior detection using YOLOv8. Artificial Intelligence Review, 58(7), 1–50. https://doi.org/10.1007/S10462-025-11206-W/TABLES/15
OECD Urban Studies. (2023). Smart city data governance. OECD Publishing, OECD Urban Studies. https://doi.org/10.1787/E57CE301-EN
Precedence Research (2026). Edge computing market size to hit USD 5,132.29 Bn by 2034. https://www.precedenceresearch.com/edge-computing-market
Quasim, M. T., Khan, M. A., Algarni, F., & Alshahrani, M. M. (2021). Fundamentals of smart cities. Lecture Notes in Intelligent Transportation and Infrastructure, Part F1386, 3–16. https://doi.org/10.1007/978-3-030-60922-1_1
Rasheed, A. F., & Zarkoosh, M. (2025). Optimized YOLOv8 for multi-scale object detection. Journal of Real-Time Image Processing, 22(1), 1–12. https://doi.org/10.1007/S11554-024-01582-X/FIGURES/9
Sapkota et al. (2025). YOLO advances to its genesis: A decadal and comprehensive review of the You Only Look Once (YOLO) series. Artificial Intelligence Review, 58(9), 1–83. https://doi.org/10.1007/S10462-025-11253-3/TABLES/8
Satyajit Sinha. (2023, September 24). Number of connected IoT devices growing 13% to 18.8 billion. IoT Analytics. https://iot-analytics.com/number-connected-iot-devices/
Tsai, C. Y., & Su, Y. K. (2022). MobileNet-JDE: A lightweight multi-object tracking model for embedded systems. Multimedia Tools and Applications, 81(7), 9915–9937. https://doi.org/10.1007/S11042-022-12095-9/FIGURES/12
Varghese, R., & Sambath, M. (2024). YOLOv8: A novel object detection algorithm with enhanced performance and robustness. 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems, ADICS 2024. https://doi.org/10.1109/ADICS58448. 2024.10533619
Wojke, N., Bewley, A., & Paulus, D. (2017). Simple online and realtime tracking with a deep association metric. Proceedings - International Conference on Image Processing, ICIP, 2017-September, 3645–3649. https://doi.org/10.1109/ICIP.2017.8296962
World Health Organization. (2023, December 13). Global status report on road safety 2023: Summary. World Health Organization. https://www.who.int/publications/i/item/9789240086456 World Smart Cities Outlook 2024 | UN-Habitat. (n.d.). https://unhabitat.org/world-smart-cities-outlook-2024
Zhang et al. (2022). ByteTrack: Multi-object tracking by associating every detection box. Lecture Notes in Computer Science, 13682 LNCS, 1–21. https://doi.org/10.1007/978-3-031-20047-2_1
Zhang, Y., Wang, C., Wang, X., Zeng, W., & Liu, W. (2021). FairMOT: On the fairness of detection and re-identification in multiple object tracking. International Journal of Computer Vision, 129(11), 3069–3087. https://doi.org/10.1007/s11263-021-01513-4
Published
Issue
Section
License
Copyright (c) 2026 Journal of Information and Communication Technology
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
Research impact
Harvested 2026-09-26Counts differ between services because each indexes a different body of literature. None of them is the whole picture.
2002 - 2020
