Low Cost Eye Tracking: The Current Panorama

Abstract

Despite the availability of accurate, commercial gaze tracker devices working with infrared (IR) technology, visible light gaze tracking constitutes an interesting alternative by allowing scalability and removing hardware requirements. Over the last years, this field has seen examples of research showing performance comparable to the IR alternatives. In this work, we survey the previous work on remote, visible light gaze trackers and analyze the explored techniques from various perspectives such as calibration strategies, head pose invariance, and gaze estimation techniques. We also provide information on related aspects of research such as public datasets to test against, open source projects to build upon, and gaze tracking services to directly use in applications. With all this information, we aim to provide the contemporary and future researchers with a map detailing previously explored ideas and the required tools.

Figure 1

The common software structure for visible light gaze trackers. The methods start by locating the eyes. To make the estimation more stable, spatiotemporal tracking may be utilized at this step. Later, the location information is used to extract features, fit 2D or 3D models to the eyes, or just extract the eye region image. In the case of model-based methods, the fitted model is used to calculate the gaze geometrically, whereas in the other methods, a mapping function is necessary to calculate the gaze angle or point.

Figure 2

Number of works from different categories of eye trackers according to the publication year.