A Real-time Object Tracking Strategy for a Mobile Terminal Based on a Lightweight Visual Model

Bohan Qiu; Ao Liu

doi:10.71222/ycx3p873

Authors

Bohan Qiu School of Information Technology, Beijing Institute of Technology Zhuhai, Zhuhai, China Author
Ao Liu College of Science, Mathematics and Technology, Wenzhou-Kean University, Wenzhou, China Author

DOI:

https://doi.org/10.71222/ycx3p873

Keywords:

object tracking, lightweight models, mobile devices, feature fusion, computer vision

Abstract

Due to the increasing popularity of mobile intelligent terminals and the rapid advancement of computer vision technology, real-time object tracking technology on mobile devices has become a demand in fields such as augmented reality, intelligent security, and unmanned systems. Target tracking algorithms often have difficulties in achieving efficient and real-time performance on mobile devices due to limitations such as limited computing resources and high power consumption. Therefore, it is urgent to improve its comprehensive performance through a lightweight visual model and an optimization strategy. This paper focuses on the application of a lightweight visual model in mobile real-time object tracking. Firstly, it analyzes the basic process of object tracking and its practical application scenarios, and introduces the structural characteristics and technical advantages of various lightweight models. To address the challenges of limited computing resources, the need for real-time performance, and the ability to adapt to varying scene complexities when deployed on mobile devices, a feature extraction approach is introduced that combines multi-scale, lightweight feature fusion with a dynamic adjustment system. It will improve the model's efficiency and performance when running on mobile devices. Additionally, to address the obstacles caused by illumination changes and target occlusion in complex scenes, an adaptive feature calibration method and a tracking state correction mechanism are proposed, which significantly enhance the system's robustness and tracking accuracy. The experimental results demonstrate that the proposed strategy enables efficient and stable real-time object tracking on mobile devices, providing a feasible technical path for applications.

References

1. S. Sun, N. Akhtar, H. Song, A. Mian, and M. Shah, "Deep affinity network for multiple object tracking," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 43, no. 1, pp. 104–119, 2019.

2. W. Luo, J. Xing, A. Milan, X. Zhang, W. Liu, and T. K. Kim, "Multiple object tracking: A literature review," Artificial Intelligence, vol. 293, p. 103448, 2021.

3. B. Yan, H. Peng, K. Wu, D. Wang, J. Fu, and H. Lu, "Lighttrack: Finding lightweight neural networks for object tracking via one-shot architecture search," in *Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition*, pp. 15180–15189, 2021.

4. X. Weng, J. Wang, D. Held, and K. Kitani, "3D multi-object tracking: A baseline and new evaluation metrics," in 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 10359–10366, Oct. 2020.

5. G. Ciaparrone, F. L. Sánchez, S. Tabik, L. Troiano, R. Tagliaferri, and F. Herrera, "Deep learning in video multi-object tracking: A survey," Neurocomputing, vol. 381, pp. 61–88, 2020.

6. G. Chandan, A. Jain, and H. Jain, "Real time object detection and tracking using deep learning and OpenCV," in *2018 International Conference on Inventive Research in Computing Applications (ICIRCA)*, pp. 1305–1308, Jul. 2018.

7. H. Fan, L. Lin, F. Yang, P. Chu, G. Deng, S. Yu, et al., "Lasot: A high-quality benchmark for large-scale single object tracking," in *Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition*, pp. 5374–5383, 2019.

8. Y. Cai, J. Liu, J. Tang, and G. Wu, "Robust object modeling for visual tracking," in Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9589–9600, 2023.

9. P. Mittal, "A comprehensive survey of deep learning-based lightweight object detection models for edge devices," Artificial Intelligence Review, vol. 57, no. 9, p. 242, 2024.

10. K. Hao, Z. Deng, B. Wang, Z. Jin, Z. Li, and X. Zhao, "Lightweight multiobject ship tracking algorithm based on trajectory association and improved YOLOv7tiny," Expert Systems with Applications, vol. 259, p. 125129, 2025.

11. C. Y. Tsai and Y. K. Su, "MobileNet-JDE: A lightweight multi-object tracking model for embedded systems," Multimedia Tools and Applications, vol. 81, no. 7, pp. 9915–9937, 2022.

12. S. B. J. Khan, P. Zhang, M. M. Kamal, and A. K. J. Saudagar, "LightTrack-ReID: A lightweight and occlusion-robust framework for multi-object tracking," PloS One, vol. 21, no. 3, p. e0342246, 2026.