Sparse and Semi-supervised Visual Mapping with the S^3GP

Williams, Oliver J.; Blake, A.; Cipolla, Roberto

doi:10.1109/cvpr.2006.285

Cited by 94 publications

(91 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The shape-based method detects the pupil or iris contour, and as the shape of the pupil or iris contour becomes elliptical according to the gaze direction, it predicts the corresponding shape of a three-dimensional (3D) spherical eye model and calculates the gaze [24]. The appearance-based method, which is adopted in some cases, uses an input image as input, treats it with a classifier, and conducts the mapping directly on the screen coordinates [25][26][27]. Therefore, this method can be applied to low-resolution images without camera calibration and geometry data.…”

Section: Related Workmentioning

confidence: 99%

Fuzzy-System-Based Detection of Pupil Center and Corneal Specular Reflection for a Driver-Gaze Tracking System Based on the Symmetrical Characteristics of Face and Facial Feature Points

Lee¹,

Yoon²,

Hong³

et al. 2017

Symmetry

View full text Add to dashboard Cite

Abstract:Recently, many studies have actively dealt with the issue of driver-gaze tracking for monitoring the forward gaze and physical condition. Driver-gaze tracking is an effective method of measuring a driver's inattention that is one of the major causes of traffic accidents. Among many gaze-tracking methods, the corneal specular reflection (SR)-based method becomes ineffective, unlike in an indoor environment, when a driver's head rotates, which makes SR disappear from input images or disperses SR in the lachrymal gland or eyelid, thereby increasing the gaze-tracking error. Besides, since a driver's eyes in a vehicle environment need to be captured in a wide range covering his head rotation, the eye region is captured in a relatively low resolution compared to face-only images taken in indoor environments at the same resolution, making pupil and corneal SR difficult to detect accurately. To solve these problems, we propose a fuzzy-system-based method for detecting a driver's pupil and corneal SR for gaze tracking in a vehicle environment. Unlike existing studies detecting pupil and corneal SR in both eyes, the method proposed in this research uses the results of a fuzzy system based on two features considering the symmetrical characteristics of face and facial feature points to determine the status of a driver's head rotation. Based on the output of the fuzzy system, the proposed method excludes the eye region, which is very likely to have a high error rate of detection due to excessive head rotation, from the detection process of the pupil and corneal SR. Accordingly, the proposed method detects pupil and corneal SR only in the eye region that apparently has a low detection error rate, thereby achieving accurate detection. We use 20,654 images capturing 15 subjects (including subjects wearing glasses), who gaze at pre-set fifteen regions in a vehicle, to measure the detection accuracy of the pupil and corneal SR for each region and the gaze tracking accuracy. Our experimental results show that the proposed method performs better than existing methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Fuzzy-System-Based Detection of Pupil Center and Corneal Specular Reflection for a Driver-Gaze Tracking System Based on the Symmetrical Characteristics of Face and Facial Feature Points

Lee¹,

Yoon²,

Hong³

et al. 2017

Symmetry

View full text Add to dashboard Cite

show abstract

“…First, the most popular, considered light corneal reflections or glints on corneal surface caused by dedicated light sources [43,46,47]. Another approach tended to evaluate geometric characteristics of eye components (pupil, iris, sclera, limbus) interrelations and analyzed them in order to estimate gaze direction [47,[52][53][54][55].…”

Section: Related Workmentioning

confidence: 99%

“…Nguyen [53] and Williams [54] have localized eyes in the camera derived calibration images and then calibration samples based, Gaussian process was used to calculate the predictive distribution, transforming eyes images into gaze point on the screen. For training the distribution function, neural networks were used.…”

Section: Related Workmentioning

confidence: 99%

Single web camera robust interactive eye-gaze tracking method

Wojciechowski¹,

Fornalczyk²

2015

Bulletin of the Polish Academy of Sciences Technical Sciences

View full text Add to dashboard Cite

Abstract. Eye-gaze tracking is an aspect of human-computer interaction still growing in popularity,. Tracking human gaze point can help control user interfaces and may help evaluate graphical user interfaces. At the same time professional eye-trackers are very expensive and thus unavailable for most of user interface researchers and small companies. The paper presents very effective, low cost, computer vision based, interactive eye-gaze tracking method. On contrary to other authors results the method achieves very high precision (about 1.5 deg horizontally and 2.5 deg vertically) at 20 fps performance, exploiting a simple HD web camera with reasonable environment restrictions. The paper describes the algorithms used in the eye-gaze tracking method and results of experimental tests, both static absolute point of interest estimation, and dynamic functional gaze controlled cursor steering.

show abstract

“…Tan et al [15] employ Local Linear Embedding to learn the eye image manifold. Williams et al [18] use a sparse Gaussian process interpolation method on filtered visible spectrum images. Typically, these methods do not require camera calibration since the mapping is made directly from the image pixels.…”

Section: Introduction and Related Workmentioning

confidence: 99%

Estimating Point of Regard with a Consumer Camera at a Distance

Mansanet

Albiol

Paredes

et al. 2013

Pattern Recognition and Image Analysis

View full text Add to dashboard Cite

Abstract. In this work, we have studied the viability of a novel technique to estimate the POR that only requires video feed from a consumer camera. The system can work under uncontrolled light conditions and does not require any complex hardware setup. To that end we propose a system that uses PCA feature extraction from the eyes region followed by non-linear regression. We evaluated three state of the art non-linear regression algorithms. In the study, we also compared the performance using a high quality webcam versus a Kinect sensor. We found, that despite the relatively low quality of the Kinect images it achieves similar performance compared to the high quality camera. These results show that the proposed approach could be extended to estimate POR in a completely non-intrusive way.

show abstract

Sparse and Semi-supervised Visual Mapping with the S^3GP

Cited by 94 publications

References 10 publications

Fuzzy-System-Based Detection of Pupil Center and Corneal Specular Reflection for a Driver-Gaze Tracking System Based on the Symmetrical Characteristics of Face and Facial Feature Points

Fuzzy-System-Based Detection of Pupil Center and Corneal Specular Reflection for a Driver-Gaze Tracking System Based on the Symmetrical Characteristics of Face and Facial Feature Points

Single web camera robust interactive eye-gaze tracking method

Estimating Point of Regard with a Consumer Camera at a Distance

Contact Info

Product

Resources

About