Robust eye tracking based on multiple corneal reflections for clinical applications

Mestre, Clara; Gautier, Josselin; Pujol, Jaume

doi:10.1117/1.jbo.23.3.035001

Cited by 16 publications

(15 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Head movements should directly affect the position of the P and CR images in the eye camera sensor of the eye tracker. We do not know the algorithms that calculate P and CR centers from the eye images in commercial eye trackers, but we do know that open-source algorithms for calculating the centre points often differ between P and CR images (Hosp et al,, 2020 ; Mestre et al,, 2018 , e.g).…”

Section: Results 3: Positions Of P and Cr Images On The Eye Camera Sensormentioning

confidence: 99%

Small head movements increase and colour noise in data from five video-based P–CR eye trackers

Holmqvist

Örbom

Zemblys³

2021

Behav Res

View full text Add to dashboard Cite

We empirically investigate the role of small, almost imperceptible balance and breathing movements of the head on the level and colour of noise in data from five commercial video-based P-CR eye trackers. By comparing noise from recordings with completely static artificial eyes to noise from recordings where the artificial eyes are worn by humans, we show that very small head movements increase levels and colouring of the noise in data recorded from all five eye trackers in this study. This increase of noise levels is seen not only in the gaze signal, but also in the P and CR signals of the eye trackers that provide these camera image features. The P and CR signals of the SMI eye trackers correlate strongly during small head movements, but less so or not at all when the head is completely still, indicating that head movements are registered by the P and CR images in the eye camera. By recording with artificial eyes, we can also show that the pupil size artefact has no major role in increasing and colouring noise. Our findings add to and replicate the observation by Niehorster et al., (2021) that lowpass filters in video-based P–CR eye trackers colour the data. Irrespective of source, filters or head movements, coloured noise can be confused for oculomotor drift. We also find that usage of the default head restriction in the EyeLink 1000+, the EyeLink II and the HiSpeed240 result in noisier data compared to less head restriction. Researchers investigating data quality in eye trackers should consider not using the Gen 2 artificial eye from SR Research / EyeLink. Data recorded with this artificial eye are much noisier than data recorded with other artificial eyes, on average 2.2–14.5 times worse for the five eye trackers.

show abstract

Section: Results 3: Positions Of P and Cr Images On The Eye Camera Sensormentioning

confidence: 99%

Small head movements increase and colour noise in data from five video-based P–CR eye trackers

Holmqvist

Örbom

Zemblys³

2021

Behav Res

View full text Add to dashboard Cite

show abstract

“…In this section we compare our differentiable rendering optimization approach to state-of-the-art glint tracking gaze estimation techniques. Particularly, we follow the representative method by Mestre et al [25], which uses an interpolation based technique that utilizes the pupil center and a ring of 12 glint illumination sources. We use our simulation pipeline to generate images of our CG eye model with corneal glint reflections (see Fig.…”

Section: Comparison Of Our Proposed Approaches To Glint-based Eye Tra...mentioning

confidence: 99%

“…These changes in position are used in conjunction with other eye features, such as the pupil position and geometry, to evaluate the gaze direction. Over the years, the point light source arrangements have evolved from single point lights (or "glints") with one camera [7], to multi-view [3,10], and multi-point-source [11,25] setups, with more sampled surface points generally leading to higher accuracy in gaze evaluation [25]. However, although the number of reflection points that sample the eye surface has increased, state-of-the-art methods still use only roughly ∼12 reflection points.…”

Section: Introductionmentioning

confidence: 99%

“…We demonstrate real-world experiments with evaluated precisions in gaze estimation between 0.11 • and only 0.02 • and relative gaze estimation errors between 0.45 • and only 0.27 • . Moreover, perform a quantitative comparison of our different flavors with a representative state-of-the-art method [25] and show that our method performs up to 6X better in both mean and standard deviation of the gaze error.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Optimization-Based Eye Tracking using Deflectometric Information

Wang¹,

Wang²,

Cossairt³

et al. 2023

Preprint

View full text Add to dashboard Cite

Eye tracking is an important tool with a wide range of applications in Virtual, Augmented, and Mixed Reality (VR/AR/MR) technologies. State-of-the-art eye tracking methods are either reflection-based and track reflections of sparse point light sources, or image-based and exploit 2D features of the acquired eye image. In this work, we attempt to significantly improve reflection-based methods by utilizing pixel-dense deflectometric surface measurements in combination with optimization-based inverse rendering algorithms. Utilizing the known geometry of our deflectometric setup, we develop a differentiable rendering pipeline based on PyTorch3D that simulates a virtual eye under screen illumination. Eventually, we exploit the imagescreen-correspondence information from the captured measurements to find the eye's rotation, translation, and shape parameters with our renderer via gradient descent. In general, our method does not require a specific pattern and can work with ordinary video frames of the main VR/AR/MR screen itself. We demonstrate real-world experiments with evaluated mean relative gaze errors below 0.45 • at a precision better than 0.11 • . Moreover, we show an improvement of 6X over a representative reflection-based state-of-the-art method in simulation.

show abstract

“…They use the visual features, such as pupil, iris, and glints, to estimate the 2D POR using the 2D mapping model obtained by user calibration or to estimate the 3D line-of-sight using the geometric imaging model. Model-based methods can effectively deal with the influence of individual differences and head movements, and the gaze accuracy is often between 0.5 • and 2 • [5]. VOLUME 10, 2022 Model-based gaze estimation methods are generally divided into 2D mapping-based methods and 3D model-based methods.…”

Section: Introductionmentioning

confidence: 99%

An Improved Cross-Ratio Based Gaze Estimation Method Using Weighted Average and Polynomial Compensation

Liu

Yang

et al. 2023

IEEE Access

View full text Add to dashboard Cite

The cross-ratio (CR)-based method exploits the invariance property of CRs in projective transformation to determine a screen point corresponding to the pupil center. However, this point is essentially the intersection of the eyeball optical axis (OA) and the screen, rather than the actual pointof-regard (POR). In addition, the premise of CR calculation is that the corneal reflection points of four on-screen light sources are coplanar with the 3D pupil center, but they are only assumed to be coplanar. To solve these issues, this paper proposes an improved CR-based gaze estimation method using weighted average and polynomial compensation. Under the configuration of a single camera and two light sources, the 3D corneal center and the normal vector of virtual pupil plane are first estimated using the eyeball imaging model, and then four reference planes parallel to the virtual pupil plane are determined based on the geometric model of pupil and screen corner points. The screen point corresponding to the intersection of each reference plane and the line connecting the camera optical center and the imaging pupil center is calculated using the conventional CR-based method. Thus, the point where the OA intersects the screen is determined by the weighted average of these four points. Finally, a polynomial is learned to compensate it to the POR. On the basis of simplifying the system configuration of CR-based methods, the proposed method avoids the non-coplanarity of 3D pupil center and corneal reflection plane, and considers the difference between the OA and the visual axis (VA) through polynomial compensation. The experimental results show that the gaze accuracy can reach 1.33 • , which is competitive with the state-of-the-art methods using more complex systems.INDEX TERMS Gaze estimation, cross-ratio, corneal reflection, virtual pupil, polynomial compensation.

show abstract

Robust eye tracking based on multiple corneal reflections for clinical applications

Cited by 16 publications

References 39 publications

Small head movements increase and colour noise in data from five video-based P–CR eye trackers

Small head movements increase and colour noise in data from five video-based P–CR eye trackers

Optimization-Based Eye Tracking using Deflectometric Information

An Improved Cross-Ratio Based Gaze Estimation Method Using Weighted Average and Polynomial Compensation

Contact Info

Product

Resources

About