Search

Kappa-angle calibration shows its importance in gaze tracking due to the special structure of the eyeball. In a 3D gaze-tracking system, after the optical axis of the eyeball is reconstructed, the kappa angle is needed to convert the optical axis of the eyeball to the real gaze direction. At present, most of the kappa-angle-calibration methods use explicit user calibration. Before eye-gaze tracking, the user needs to look at some pre-defined calibration points on the screen, thereby providing some corresponding optical and visual axes of the eyeball with which to calculate the kappa angle. Especially when multi-point user calibration is required, the calibration process is relatively complicated. In this paper, a method that can automatically calibrate the kappa angle during screen browsing is proposed. Based on the 3D corneal centers and optical axes of both eyes, the optimal objective function of the kappa angle is established according to the coplanar constraint of the visual axes of the left and right eyes, and the differential evolution algorithm is used to iterate through kappa angles according to the theoretical angular constraint of the kappa angle. The experiments show that the proposed method can make the gaze accuracy reach 1.3 ° in the horizontal plane and 1.34 ° in the vertical plane, both of which are within the acceptable margins of gaze-estimation error. The demonstration of explicit kappa-angle calibration is of great significance to the realization of the instant use of gaze-tracking systems. [ABSTRACT FROM AUTHOR]

The image of the center of a 3-D circular target is not the center of its imaging ellipse due to the imaging distortion of the spatial circular targets; therefore, traditional 3-D gaze-estimation methods with the multi-camera-multi-light-source (MCMLS) systems generally replace the projection of the pupil center with the virtual image of the pupil center for 3-D gaze estimation. However, this introduces a large gaze-estimation error when the oblique angle between the optical axis of the eye and the camera optical axis is large. To eliminate the error caused by using the virtual image of the pupil center, a 3-D gaze-estimation method using an MCMLS system is developed in this study. We first estimate the cornea center and then determine the matching points of the pupil imaging ellipse using the special polar plane. After the cornea radius and the kappa angle are calibrated, the optical axis of the eye is reconstructed by the refraction planes constructed by the edge points of the pupil imaging ellipses. Thus, the 3-D gaze is estimated by the real-time calculated transformation matrix represented by the kappa angle. The feasibility and performance of the method have been analyzed by the simulations and the experiments. Since the estimation of the spatial pupil center or the construction of the refraction plane using the virtual image of the pupil center is not required, the proposed method mitigates the inherent errors caused by optical axis reconstruction in the traditional methods and simplifies the algorithm for gaze estimation, which has a practical value. [ABSTRACT FROM AUTHOR]

Multicamera or multilight-source is generally used to estimate the 3-D coordinates of the cornea center for 3-D gaze estimation in the existing gaze trackers. Although some model-based methods use one-camera systems to estimate 3-D gazes, which include some user-dependent eye parameters preset by fixed values, a one-camera-one-light-source system is still unable to achieve 3-D gaze estimation by considering individual differences. In this article, an iris feature-based method using one camera and one light source for 3-D gaze estimation is proposed. The iris radius and the kappa angle are determined during user calibration. The optical axis is reconstructed by the iris center and its normal vector from only the iris features. Therefore, with the real-time estimation of kappa angle, the 3-D gaze is estimated by an optimization method. Computer simulations and practical experiments have been performed to analyze the feasibility and robustness of the proposed method. This article’s innovation lies in achieving 3-D gaze estimation based on only one-camera and one-light source with calibrated eye-specific parameters, which breaks through the limitation of the existing methods using a 3-D cornea center on the system’s hardware requirements of 3-D gaze estimation. The simplified hardware system has great application values, especially in the portable mobile devices widely used today. Moreover, a binocular model is used to optimize the results of the point of regard, which improves the accuracy of 3-D gaze estimation effectively. [ABSTRACT FROM AUTHOR]

A paradigm shift is required to prevent the increasing automobile accident deaths that are mostly due to the inattentive behavior of drivers. Knowledge of gaze region can provide valuable information regarding a driver’s point of attention. Accurate and inexpensive gaze classification systems in cars can improve safe driving. However, monitoring real-time driving behaviors and conditions presents some challenges: dizziness due to long drives, extreme lighting variations, glasses reflections, and occlusions. Past studies on gaze detection in cars have been chiefly based on head movements. The margin of error in gaze detection increases when drivers gaze at objects by moving their eyes without moving their heads. To solve this problem, a pupil center corneal reflection (PCCR)-based method has been considered. However, the error of accurately detecting the pupil center and corneal reflection center is increased in a car environment due to various environment light changes, reflections on glasses surface, and motion and optical blurring of captured eye image. In addition, existing PCCR-based methods require initial user calibration, which is difficult to perform in a car environment. To address this issue, we propose a deep learning-based gaze detection method using a near-infrared (NIR) camera sensor considering driver head and eye movement that does not require any initial user calibration. The proposed system is evaluated on our self-constructed database as well as on open Columbia gaze dataset (CAVE-DB). The proposed method demonstrated greater accuracy than the previous gaze classification methods. [ABSTRACT FROM AUTHOR]