Starburst: A robust algorithm for video-based eye tracking

Knowing the user’s point of gaze has significant potential to enhance current humancomputer interfaces. The primary obstacle of integrating eye movements into interfaces is the availability of a reliable, low-cost open-source eye-tracking system. Towards making such a system available to interface designers, we have developed a hybrid eye-tracking algorithm that integrates feature-based and model-based approaches and made it available in an open-source package. We refer to this algorithm as “starburst” because of the way in which pupil features are detected. This starburst algorithm is more accurate than pure feature-based approaches yet is significantly less time consuming than pure model-based approaches. The current implementation is tailored to tracking eye movements in infrared video obtained from an inexpensive head-mounted eye-tracking system. A validation study shows that the technique can reliably estimate eye position with an accuracy of approximately one degree of visual angle even in the presence of significant image noise.