Dynamic accommodation measurement using Purkinje reflections and ML algorithms
This addresses the need for accurate eye-tracking in AR and ophthalmology, though it appears incremental as it builds on existing Purkinje reflection methods.
The researchers tackled the problem of dynamic gaze and accommodation measurement by developing a prototype device using Purkinje reflections, achieving better than 0.25D accuracy in predicting accommodation from 4 to 1 diopters.
We developed a prototype device for dynamic gaze and accommodation measurements based on 4 Purkinje reflections (PR) suitable for use in AR and ophthalmology applications. PR1&2 and PR3&4 are used for accurate gaze and accommodation measurements, respectively. Our eye model was developed in ZEMAX and matches the experiments well. Our model predicts the accommodation from 4 diopters to 1 diopter with better than 0.25D accuracy. We performed repeatability tests and obtained accurate gaze and accommodation estimations from subjects. We are generating a large synthetic data set using physically accurate models and machine learning.