Search for: All records

The majority of eye-tracking systems require user-specific calibration to achieve suitable accuracy. Traditional calibration is performed by presenting targets at fixed locations that form a certain coverage of the device screen. If simple regression methods are used to learn a gaze map from the recorded data, the risk of overfitting is minimal. This is not the case if a gaze map is formed using neural networks, as is often employed in photosensor oculography (PSOG), which raises the question of careful design of calibration procedure. This paper evaluates different calibration data parsing approaches and the collection time-performance trade-off effect of grid density to build a calibration framework for PSOG with the use of video-based simulation framework. 

Photosensor oculography (PSOG) is a promising solution for reducing the computational requirements of eye tracking sensors in wireless virtual and augmented reality platforms. This paper proposes a novel machine learning-based solution for addressing the known performance degradation of PSOG devices in the presence of sensor shifts. Namely, we introduce a convolutional neural network model capable of providing shift-robust end-to-end gaze estimates from the PSOG array output. Moreover, we propose a transfer-learning strategy for reducing model training time. Using a simulated workflow with improved realism, we show that the proposed convolutional model offers improved accuracy over a previously considered multilayer perceptron approach. In addition, we demonstrate that the transfer of initialization weights from pre-trained models can substantially reduce training time for new users. In the end, we provide the discussion regarding the design trade-offs between accuracy, training time, and power consumption among the considered models.