Implicit Calibration Using Probable Fixation Targets

Abstract

Proper calibration of eye movement signal registered by an eye tracker seems to be one of the main challenges in popularizing eye trackers as yet another user input device. Classic calibration methods taking time and imposing unnatural behavior of users have to be replaced by intelligent methods that are able to calibrate the signal without conscious cooperation with users. Such an implicit calibration requires some knowledge about the stimulus a person is looking at and takes into account this information to predict probable gaze targets. The paper describes one of the possible methods to perform implicit calibration: it starts with finding probable fixation targets (PFTs), then uses these targets to build a mapping - probable gaze path. Various possible algorithms that may be used for finding PFTs and mapping are presented in the paper and errors are calculated utilizing two datasets registered with two different types of eye trackers. The results show that although for now the implicit calibration provides results worse than the classic one, it may be comparable with it and sufficient for some applications.

X-AWARE: ConteXt-AWARE Human-Environment Attention Fusion for Driver Gaze Prediction in the Wild

“…For their proposed person-free calibration, they used a hard expectation maximisation algorithm with good results. Recently, in the study performed in [19], the detection of probable eye targets for implicit calibration in order to take advantage of static, surrounding objects was introduced. Here instead, we utilised end-to-end deep learning from the raw images that include the cabin environment, in conjunction with Generic, optical Car Part Recognition and Detection (GoCaRD ) [37] features, in an attempt to allow for a similar neurally learnable implicit calibration.…”