Appearance-Based Gaze Tracking with Free Head Movement

Lai, Chih-Chuan; Chen, Yuting; Chen, Kuan-Wen; Chen, Shen-Chi; Shih, Sheng-Wen; Hung, Yi‐Ping

doi:10.1109/icpr.2014.327

Cited by 14 publications

(12 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lai et al [ 8 ] use random forests to learn the neighborhood structure for their joint head pose and eye appearance feature (HPEA). Gaze is estimated with linear interpolation using the neighbors in the random forest, yielding an accuracy of around 4.8° (horizontal and vertical combined).…”

Section: Methods For Single Camera Remote Gaze Trackingmentioning

confidence: 99%

“…Even in a more recent survey [ 6 ] where both infrared (IR) and visible light methods are considered, the latter group is considered as just an alternative, and its subcategories are left unclear. Other categorization schemes also build on this ambiguity: appearance-based versus feature-based [ 7 , 8 ] and appearance-based versus model-based [ 9 , 10 ]. It should also be noted that the “appearance-based” name is still being used to refer to all visible light methods [ 11 , 12 ], adding to the confusion.…”

Section: Categorization and Structure Of Visible Light Gaze Trackementioning

confidence: 99%

“…The naive approach to solving the problem of head movements is adding more training data. Nguyen et al [ 37 , 53 ] propose repeating the calibration up to 10 times, while Lai et al [ 8 ] require 34,000 training samples per user.…”

Section: Dealing With Head Posementioning

confidence: 99%

See 2 more Smart Citations

Low Cost Eye Tracking: The Current Panorama

Onur

Vilariño

2016

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Despite the availability of accurate, commercial gaze tracker devices working with infrared (IR) technology, visible light gaze tracking constitutes an interesting alternative by allowing scalability and removing hardware requirements. Over the last years, this field has seen examples of research showing performance comparable to the IR alternatives. In this work, we survey the previous work on remote, visible light gaze trackers and analyze the explored techniques from various perspectives such as calibration strategies, head pose invariance, and gaze estimation techniques. We also provide information on related aspects of research such as public datasets to test against, open source projects to build upon, and gaze tracking services to directly use in applications. With all this information, we aim to provide the contemporary and future researchers with a map detailing previously explored ideas and the required tools.

show abstract

Section: Methods For Single Camera Remote Gaze Trackingmentioning

confidence: 99%

Section: Categorization and Structure Of Visible Light Gaze Trackementioning

confidence: 99%

See 1 more Smart Citation

Low Cost Eye Tracking: The Current Panorama

Onur

Vilariño

2016

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…The resulting dense data set is subsequently used to cross-train a random forest-based algorithm to estimate the gaze from newly observed eye images captured under head movement. Lai et al [149] employ a randomforest based technique as well, trained on image data collected by requesting the user to hold a fixed gaze and perform different head rotations, in order to select neighbours on a low-dimensional manifold given the observed head pose and eye appearance features. The selected neighbouring features under similar eye and head rotation angles are then used as input to an ALR technique, as previously described in Section 5.2.1, in order to estimate the gaze direction.…”

Section: Compensation For Head Rotationmentioning

confidence: 99%

Unobtrusive and pervasive video-based eye-gaze tracking

Cristina

Camilleri

2018

Image and Vision Computing

View full text Add to dashboard Cite

Eye-gaze tracking has long been considered a desktop technology that finds its use inside the traditional office setting, where the operating conditions may be controlled. Nonetheless, recent advancements in mobile technology and a growing interest in capturing natural human behaviour have motivated an emerging interest in tracking eye movements within unconstrained real-life conditions, referred to as pervasive eye-gaze tracking. This critical review focuses on emerging passive and unobtrusive video-based eyegaze tracking methods in recent literature, with the aim to identify different research avenues that are being followed in response to the challenges of pervasive eye-gaze tracking. Different eye-gaze tracking approaches are discussed in order to bring out their strengths and weaknesses, and to identify any limitations, within the context of pervasive eye-gaze tracking, that have yet to be considered by the computer vision community.

show abstract

“…Moreover, as they usually require a controlled environment to prevent undesired reflections in the eyes, their applicability during day time is precluded. Other common approaches employ 3D techniques [14] (using multiple cameras or depth sensors) and wearable devices such as helmets or glasses [15], being cumbersome for the users. Universal gaze tracking from completely unobtrusive, Contents lists available at ScienceDirect journal homepage: www.elsevier.com/locate/image remotely located low-cost sensors (e.g.…”

Section: Introductionmentioning

confidence: 99%