A Novel Integrated Eye-Tracking System With Stereo Stimuli for 3-D Gaze Estimation

Jinglin Sun, Zhipeng Wu, Han Wang, Peiguang Jing, Yu Liu

Abstract: Eye-tracking technology is increasingly used in applications such as 3-D displays and human–computer interaction (HCI). However, most current eye trackers focus on 2-D point-of-gaze (PoG) estimation and cannot provide accurate gaze depth. Concerning future applications such as HCI with 3-D displays, we propose an integrated binocular eye-tracking device with stereo stimuli to provide highly accurate 3-D PoG estimation. In our device, the 3-D stereo imaging system can provide users with a friendly and immersive 3-D visual experience without wearing any accessories. The eye-capturing system can directly record the users’ eye movements under 3-D stimuli without disturbance, which can realize front views of eye images while ensuring the user’s wide field of view (FOV). A regression-based 3-D eye-tracking model is built based on collected eye movement data under stereo stimuli. Our model estimates users’ 2-D gaze with features defined by eye region landmarks and further estimates 3-D gaze with a multisource feature set constructed by comprehensive eye movement features and disparity features from stereo stimuli. Two test stereo scenes with different depths of field are designed to verify the model’s effectiveness. Experimental results of fourfold cross-validation show that the average error for 2-D gaze estimation was <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$0.\mathrm{65}^{\circ} $ </tex-math></inline-formula> . For 3-D gaze estimation, the average errors are 1.69 cm over the workspace volume 50 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\times $ </tex-math></inline-formula> 30 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\times $ </tex-math></inline-formula> 75 cm3 and 0.14 m over the workspace volume 2.4 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\times $ </tex-math></inline-formula> 4.0 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\times $ </tex-math></inline-formula> 7.9 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\text{m}^{3}$ </tex-math></inline-formula> . Two preliminary validation experiments also demonstrate that our system has broad application prospects, such as 3-D vision technologies and medical applications related to neurological diseases.