In the eye of the beholder: A survey of gaze tracking techniques

Gaze tracking estimates and tracks the user's gaze by analyzing facial or eye features, it is an important way to realize automated vision-based interaction. This paper introduces the visual information used in gaze tracking, and discusses the commonly used gaze estimation methods and their research dynamics, including: 2D mapping-based methods, 3D model-based methods, and appearance-based methods. In this way, some key issues that need to be solved in these methods are considered, and their research trends are discussed. Their characteristics in system configuration, personal calibration, head motion, gaze accuracy and robustness are also compared. Finally, the applications of gaze tracking techniques are analyzed from various application factors and fields. This paper reviews the latest development of gaze tracking, focuses more on various gaze tracking algorithms and their existing challenges. The development trends of gaze tracking are prospected, which provides ideas for future theoretical research and practical applications.