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

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.