Estimating Gaze Depth Using Multi-Layer Perceptron

Lee, Young-Ho; Shin, Choonsung; Plopski, Alexander; Itoh, Yuta; Piumsomboon, Thammathip; Dey, Arindam; Lee, Gun; Kim, Seungwon; Billinghurst, Mark

doi:10.1109/isuvr.2017.13

Cited by 15 publications

(11 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Eye-tracking techniques have high accuracy in performing gaze estimation in the x and y direction, but not in depth [57]. Some applications (such as VR/AR systems) requires accurate measurements of the x-and y-direction of the eye gaze, particularly the focal depth information.…”

Section: ) 3d Classification-based Methods For Gaze Estimationmentioning

confidence: 99%

“…The experimental results show that the method produced a gaze depth accuracy of 90.1% for the individual models and 89.7% for the generalized model. Lee, et al [57] proposed an NN-based technique for determining gaze depth in a head-mounted eye tracker. They used a binocular eye tracker with two cameras to capture gaze information of subjects looking at fixed points at distances from 1m to 5m.…”

Section: ) 3d Classification-based Methods For Gaze Estimationmentioning

confidence: 99%

See 1 more Smart Citation

Convolutional Neural Network-Based Methods for Eye Gaze Estimation: A Survey

Akinyelu

Blignaut

2020

IEEE Access

View full text Add to dashboard Cite

Eye tracking is becoming a very important tool across many domains, including humancomputer-interaction, psychology, computer vision, and medical diagnosis. Different methods have been used to tackle eye tracking, however, some of them are inaccurate under real-world conditions, while some require explicit user calibration which can be burdensome. Some of these methods suffer from poor image quality and variable light conditions. The recent success and prevalence of deep learning have greatly improved the performance of eye-tracking. The availability of large-scale datasets has further improved the performance of deep learning-based methods. This paper presents a survey of the current state-of-the-art on deep learning-based gaze estimation techniques, with a focus on Convolutional Neural Networks (CNN). This paper also provides a survey on other machine learning-based gaze estimation techniques. This study aims to empower the research community with valuable and useful insights that can enhance the design and development of improved and efficient deep learning-based eye-tracking models. This study also provides information on various pre-trained models, network architectures, and open-source datasets that are useful for training deep learning models.

show abstract

Section: ) 3d Classification-based Methods For Gaze Estimationmentioning

confidence: 99%

Section: ) 3d Classification-based Methods For Gaze Estimationmentioning

confidence: 99%

Convolutional Neural Network-Based Methods for Eye Gaze Estimation: A Survey

Akinyelu

Blignaut

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…3) Method for assessing line of sight based on threedimensional classification: Eye-tracking technology provides high precision in assessing eye tracking in the x and y directions but does not depend on depth [33] Experimental results show that in the case of the model, the line-of-sight accuracy obtained by this method is 90.1%, and the line-of-sight accuracy obtained using the generalized model is 89.7%. [33] have suggested a neural network-depend method for estimating the depth of field of a forehead eye searcher. They utilized a two ocular eye searcher with 2 cameras to catch gaze details from an object observed at a fixed point of 1-5 meters.…”

Section: Machine Learning Based Classification Methodsmentioning

confidence: 99%

Research on Eye Pupil Location and Eye Tracking by Designing a Fully Conventional Neural Network (FCNN)

Raza¹,

Wang²,

Xue³

et al. 2020

Int. j. technol. eng. stud.

View full text Add to dashboard Cite

Eye-tracking has become a significant tool in various areas, incorporating interaction of humans with a computer, computer vision, psychology, and medical diagnostics. Various protocols have been utilized to track the gaze. Although, some may not be accurate in the real world, while others may need explicit custom calibration, which can cause problems. Few of these techniques are associated with low image grades and varying lighting situations. The latest success and popularity of deep studying has dramatically increased the effectiveness of eye-tracking. The convenience of huge datasets additionally improves the function of deep learning-depend techniques. This technical paper introduces the latest deep studying-depend gaze assessment technology with a concentration on Fully Convolution Neural Networks (FCNN). This technical paper also gives an overview of other machine-based eye assessment methods. This research objective to enable the research population to generate significant and useful horizons that can improve the structure and growth of better, more effective deep learning depends on eye-tracking methods. This paper also gives information on different pertained models, network structures, and open origin datasets to help train deep learning models.

show abstract

“…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. Takemura 等 [23] 使用头戴式眼动设备获取眼动信息, 并利用视觉…”

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

Estimating Gaze Depth Using Multi-Layer Perceptron

Cited by 15 publications

References 13 publications

Convolutional Neural Network-Based Methods for Eye Gaze Estimation: A Survey

Convolutional Neural Network-Based Methods for Eye Gaze Estimation: A Survey

Research on Eye Pupil Location and Eye Tracking by Designing a Fully Conventional Neural Network (FCNN)

Long Distance 3D Gaze Estimation Combined with Radar Target Detection

Contact Info

Product

Resources

About