A Feature-Based Gaze Estimation Algorithm for Natural Light Scenarios

摘要

We present an eye tracking system that works with regular webcams. We base our work on open source CVC Eye Tracker and we propose a number of improvements and a novel gaze estimation method. The new method uses features extracted from iris segmentation and it does not fall into the traditional categorization of appearance-based/model-based methods. Our experiments show that our approach reduces the gaze estimation errors by 34% in the horizontal direction and by 12% in the vertical direction compared to the baseline system.