A Robust Extrinsic Calibration Method for Non-Contact Gaze Tracking in the 3-D Space

Kang, Mun-Cheon; Yoo, Cheol-Hwan; Uhm, Kwang-Hyun; Lee, Dae-Hong; Ko, Sung-Jea

doi:10.1109/access.2018.2867235

Cited by 7 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Like the methods presented in Fig. 14, the n-order polynomial function or other more complex mathematic tools [40] can also be used to build the corresponding relationships for this calibration method. With the accumulation of experiment data, the model in Fig.…”

Section: E Discussionmentioning

confidence: 99%

Calibration of Imaging Sensor and Fiber Optic Taper-Caused Distortion in an X-Ray Intensified CMOS Camera

et al. 2019

View full text Add to dashboard Cite

An integrated calibration method of the imaging sensor and the fiber optic taper-caused distortion in an intensified Complementary Metal-Oxide-Semiconductor (CMOS) camera for the X-ray capture application is proposed. Generally, four kinds of distortions need to be corrected in this system: the column noise, the inconsistent pixel intensity response of whole frame, the nonlinear intensity response of each pixel, and the geometry distortion of whole frame. To conquer these problems, first, the column noise is estimated and subtracted from the captured image. The multiple measurement data processing method and the strip noise estimation technique are used. Second, a kind of two-step correction technique of the pixel intensity response is proposed to solve middle two distortion problems. The first step builds the ideal intensity response line for all pixels in image; and the second step estimates and compensates the correction error for each pixel by a polynomial function. Third a polynomial fitting method is also utilized to correct the geometry distortion. The RANdom SAmple Consensus (RANSC) computation mechanism is used to improve the calibration precision further. The optic indices of fiber optic taper and camera are considered to assist the selection of key parameters of these calibration method above. Many experiment results have proved the correctness and effectiveness of proposed method.INDEX TERMS Distortion correction, X-ray image sensor, CMOS, fiber optic taper, RANSAC.

show abstract

Section: E Discussionmentioning

confidence: 99%

Calibration of Imaging Sensor and Fiber Optic Taper-Caused Distortion in an X-Ray Intensified CMOS Camera

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Wang 等 [20] 利用 Kinect 传感器的 3D 点云数据, 作为 3D 注视点估计的辅助信息. Kang 等 [21] 使用立体摄像机拍摄前方行车环境, 获取各物体的 3D 坐标, 并选择与估计的 3D 视线的角度最小的场景点作为 3D 注视点, 用于研究驾驶员对交通标识牌的注视估计. Lee 等 [22] 使用立体摄像机以及多层感知网络对注视深度进行估计.…”

Section: 相关工作unclassified

Long Distance 3D Gaze Estimation Combined with Radar Target Detection

Zhang¹,

Duan²,

Zhu³

et al. 2020

J Comput-Aided Design Comput Graphics

View full text Add to dashboard Cite

The 3D gaze estimation method based on 2D mapping and two lines of sight intersection has high accuracy in angle estimation. However, there are still large errors in the estimation of gaze distance. Thus, a 3D gaze estimation method based on an auxiliary millimeter wave radar target detection is proposed. First, it uses a movable calibration object to form a virtual calibration plane to calibrate the 2D planar fixation point.Next, the 2D fixation points of the right and left eyes on the calibration plane are calculated by the two-dimensional mapping function, and the 3D gaze direction is calculated combining the position of the eyes. Finally, the candidate point which has the smallest error from the gaze angle is selected from the target points detected by radar. A virtual plane is constructed at the distance of this point, by which the left and right lines of sight are intercept, the midpoint of the two intercept points is the estimation result of 3D fixation point. An experimental device is designed to fuse millimeter wave radar, camera and mobile calibration target. The 3D gaze point is tested in the range of 4.0~10.2 m. Experiments shows that with this method, the average angle error is 0.9°, the average Euclidean distance error is 130 mm. The result is better than binocular data geometric mapping method and depth camera aided estimation method.

show abstract

Reducing Error Rate for Eye-Tracking System by Applying SVM

Ahmed

Nasrin

2022

Lecture Notes on Data Engineering and Communications Technologies

View full text Add to dashboard Cite

A Robust Extrinsic Calibration Method for Non-Contact Gaze Tracking in the 3-D Space

Cited by 7 publications

References 20 publications

Calibration of Imaging Sensor and Fiber Optic Taper-Caused Distortion in an X-Ray Intensified CMOS Camera

Calibration of Imaging Sensor and Fiber Optic Taper-Caused Distortion in an X-Ray Intensified CMOS Camera

Long Distance 3D Gaze Estimation Combined with Radar Target Detection

Reducing Error Rate for Eye-Tracking System by Applying SVM

Contact Info

Product

Resources

About