Systems and methods for improved ease and accuracy of gaze tracking

摘要

Methods for improving gaze tracking are presented. These methods eliminate the need for a separate initial calibration step to determine whether the subject is properly centrally fixated during testing. In one embodiment, whether the subject is centrally fixated is determined by identifying inlier and outlier gaze descriptors; the inliers are assumed to be associated with central fixation. This reduces the total time required for testing. These methods also improve the accuracy of gaze tracking during testing without the need for individual subject calibration. Instead, a database of reference eyes is used. The subject's eye can be compared to the reference eyes, and the mapping function for one or more reference matches can be used to estimate the subject's gaze direction. In another embodiment, previous calibration data from the same subject can be used to determine whether the subject is properly centrally fixated and/or the direction of the subject's gaze.

主权项

1. A method for determining when the gaze of a subject is centered during visual field testing, wherein the subject has been instructed to fixate on a central location throughout the test, comprising:
using one or more light sources to create one or more reflections from an ocular surface; displaying a series of test stimuli to the subject; collecting responses to the stimuli from the subject; imaging the subject's eye while each test stimulus is displayed; determining gaze descriptors for the eye for each test stimulus by analyzing the reflections of the light sources in the image, said gaze descriptors being defined by a vector extending from the reflection on the ocular surface to the center of the pupil of the eye; grouping all or a subset of the gaze descriptors into inlier or outlier gaze descriptors using an algorithm that assumes that the majority of the gaze descriptors correspond to the subject being fixated on the central location, with the inlier gaze descriptors corresponding to the subject's gaze being fixed on the central location and the outlier gaze descriptors corresponding to the subject's gaze being off-center from the central location; determining a zero calibration vector based on the inlier gaze descriptors; comparing the gaze descriptor determined for each test stimulus to the zero-calibration vector to determine the deviation of the gaze from the central location; and for any response to the stimuli where the associated deviation from the zero calibration vector exceeds a threshold performing one of the following steps: (a) disregarding the response; (b) flagging the response to a clinician; or (c) reassigning the response to a different location.