Gavas Rahul, Roy Sangheeta, Chatterjee Debatri, Tripathy Soumya Ranjan, Chakravarty Kingshuk, Sinha Aniruddha, Lahiri Uttama
Annu Int Conf IEEE Eng Med Biol Soc. 2017 Jul;2017:746-750. doi: 10.1109/EMBC.2017.8036932.
Eye movement analysis finds tremendous usefulness in various medical screening applications and rehabilitation. Infrared sensor based eye trackers are becoming popular but these are expensive and need repeated calibration. Moreover, with multiple calibration also, there persists some noises called, variable and systematic, resulting in inaccurate gaze tracking. This study aims to build an one time calibration module to avoid the overhead of multiple calibration and to design an algorithm to remove both the types of errors effectively. The proposed approach is used for correcting the gaze tracking data for Digit Gazing task and standard recall-recognition test, where an accuracy of 90% and 82% are achieved respectively for detecting the gaze positions against the raw eye gaze data. Results also show that it is possible to perform accurate gaze tracking with one-time calibration method provided the experimental setup is not altered.
眼动分析在各种医学筛查应用和康复中具有巨大的实用性。基于红外传感器的眼动追踪器正变得越来越流行，但这些设备价格昂贵且需要反复校准。此外，即使进行多次校准，仍会存在一些称为可变误差和系统误差的噪声，导致注视跟踪不准确。本研究旨在构建一个一次性校准模块，以避免多次校准的开销，并设计一种算法来有效消除这两种类型的误差。所提出的方法用于校正数字注视任务和标准回忆 - 识别测试的注视跟踪数据，在针对原始眼动注视数据检测注视位置时，分别实现了90%和82%的准确率。结果还表明，只要实验设置不变，使用一次性校准方法就有可能进行准确的注视跟踪。
