UMET: UEYE Mobile Eye-Tracking Integrating Lightweight Calibration Model and Efficient Fixation Point Prediction

Eye tracking has demonstrated significant potential in applications such as mobile human-computer interaction and behavioral analysis. However, traditional desktop-based eyetracking systems impose strict requirements on deployment environments and user posture, which limits their applicability in mobile scenarios. To address the challenges of accuracy, efficiency, and usability in existing mobile eye-tracking solutions, this paper proposes UEYE Mobile Eye-Tracking (UMET), a lightweight eye-tracking system designed for mobile terminal. UMET integrates UEYE Glasses with a lightweight calibration model and efficient fixation prediction algorithms, enabling real-time gaze estimation under low-power and low-latency constraints. A dual-modal stability verification mechanism based on natural head movements is introduced to support robust calibration in unconstrained environments. Extensive experiments with 30 participants show that UMET achieves a mean angular fixation error of approximately 1.4° across viewing distances of 30-60 cm, while maintaining an average prediction latency below 0.7 ms. Compared with representative mobile gaze-tracking methods reported in the literature, UMET delivers competitive or superior gaze accuracy with significantly lower computational complexity. These results demonstrate that UMET provides an effective and practical solution for high-frequency mobile eye tracking, with strong potential for deployment in real-world mobile and interactive applications.