The Perspective Geometry of the Eye: Toward Image-Based Eye-Tracking

Canessa, Andrea; Gibaldi, Agostino; Chessa, Manuela; Sabatini, Silvio P.; Solari, Fabio

doi:10.5772/45941

Cited by 9 publications

(8 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A diverse range of approaches has been proposed, such as algorithms using support vector machines (Crisafulli et al, 2009 ) or neural networks (Torricelli et al, 2008 ). The accuracy of most of these algorithms, however, is still around 1° of visual angle (Canessa et al, 2012 ). We used a dark-pupil technique and achieved accuracy close to 1° visual angle.…”

Section: Discussionmentioning

confidence: 99%

SET: a pupil detection method using sinusoidal approximation

et al. 2015

View full text Add to dashboard Cite

Mobile eye-tracking in external environments remains challenging, despite recent advances in eye-tracking software and hardware engineering. Many current methods fail to deal with the vast range of outdoor lighting conditions and the speed at which these can change. This confines experiments to artificial environments where conditions must be tightly controlled. Additionally, the emergence of low-cost eye tracking devices calls for the development of analysis tools that enable non-technical researchers to process the output of their images. We have developed a fast and accurate method (known as “SET”) that is suitable even for natural environments with uncontrolled, dynamic and even extreme lighting conditions. We compared the performance of SET with that of two open-source alternatives by processing two collections of eye images: images of natural outdoor scenes with extreme lighting variations (“Natural”); and images of less challenging indoor scenes (“CASIA-Iris-Thousand”). We show that SET excelled in outdoor conditions and was faster, without significant loss of accuracy, indoors. SET offers a low cost eye-tracking solution, delivering high performance even in challenging outdoor environments. It is offered through an open-source MATLAB toolkit as well as a dynamic-link library (“DLL”), which can be imported into many programming languages including C# and Visual Basic in Windows OS (www.eyegoeyetracker.co.uk).

show abstract

Section: Discussionmentioning

confidence: 99%

SET: a pupil detection method using sinusoidal approximation

et al. 2015

View full text Add to dashboard Cite

show abstract

“…Both the pupils and the limbus closely approximate perfect circles. [ 25 ] The projections of a circle from eccentric perspectives as captured by images are ellipses. The ellipses originating from pupil and the limbus of an eye for practical purposes can be considered as scaled version of the other sharing parallel major and minor axes.…”

Section: Discussionmentioning

confidence: 99%

“…The ellipses originating from pupil and the limbus of an eye for practical purposes can be considered as scaled version of the other sharing parallel major and minor axes. [ 25 ] It is important to note that the major and minor axes are parallel but may not be in the same line [ Figure 4 ]. This is because although the pupil and the limbus appear to share the same orientation the pupil is slightly eccentric with respect to the limbus[ 25 ] and this eccentricity changes with pupillary size under various conditions of illumination.…”

Section: Discussionmentioning

confidence: 99%

“…[ 25 ] It is important to note that the major and minor axes are parallel but may not be in the same line [ Figure 4 ]. This is because although the pupil and the limbus appear to share the same orientation the pupil is slightly eccentric with respect to the limbus[ 25 ] and this eccentricity changes with pupillary size under various conditions of illumination. [ 26 ] Thus measuring the pupilary diameter in the same axis as the limbus will give an erroneous result as illustrated in Figure 4 .…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Pupil to limbus ratio: Introducing a simple objective measure using two-box method for measuring early nisocoria and progress of pupillary change in the ICU

Mojumder

Patel

Nugent

et al. 2015

Journal of Neurosciences in Rural Practice

View full text Add to dashboard Cite

Introduction:Measurement of static pupillary size in the ICU is of importance in cases of acutely expanding intracranial mass lesions. The inaccuracies with subjective assessment of pupillary size by medical personnel preclude its use in emergent neurological situations.Objective:To determine if the ratio of pupil to limbus diameter (PLD ratio) measured by a two-box method is a reliable measure of pupil size for detecting early anisocoria and measuring pupillary changes.Materials and Methods:The PLD ratio was defined as the ratio of the pupillary diameter measured at a para-horizontal axial plane with the limbus diameter measured at the same or parallel axial plane. A two-box method was used to estimate the diameters of imaged pupils. Eyes were imaged using an iPhone 4S cellphone camera. Background illumination was measured and kept constant. The pupils of a 78-year-old woman, who presented with a large intra-axial parenchymal hemorrhage, were imaged. The patient had left pupillary miosis in dark but not in bright light. After presenting this case along with the images of the pupillary examination, a group of 21 medical staff were asked several questions on the pupillary examination. Reliability of PLD ratio were assessed via standard error of mean (S.E.M) of PLD ratios for 3 different subjects each imaged under constant illumination and fixation but from different angles to the optical axis.Results:Analysis of questionnaire data together with PLD ratios revealed that ~ 14% and 10% of participants could estimate the pupillary size in darkness and bright light respectively but none were simultaneously accurate indicating that subjective assessment of pupillary size was unreliable. The approach towards a systematic pupillary examination was inconsistent among the participants. The PLD ratio was found to be a reliable measure of pupillary size with standard error of mean below 0.1 mm for the three subjects tested.Conclusion:Static pupillary sizes can be objectively and consistently evaluated using PLD ratios using a two-box method. PLD ratios are resistant, within limits, to changes in imaging angle or choice of para-horizontal axes for measurement.

show abstract

“…Eye-tracking has found applications in fields such as neuro and cognitive sciences, psychology, human-computer interactions, consumer electronics, and assistive technologies [15]. Performance of eye trackers are judged based on their accuracy (in degrees of angular resolution) and it is affected by physiological limitations, tracker setup geometry, or due to type of calibration techniques used in them [16].…”

Section: Previous Work On Open-source Gaze Data Analysis Software Anmentioning

confidence: 99%

Development of Open-source Software and Gaze Data Repositories for Performance Evaluation of Eye Tracking Systems

Kar

Corcoran

2019

Vision

View full text Add to dashboard Cite

In this paper, a range of open-source tools, datasets, and software that have been developed for quantitative and in-depth evaluation of eye gaze data quality are presented. Eye tracking systems in contemporary vision research and applications face major challenges due to variable operating conditions such as user distance, head pose, and movements of the eye tracker platform. However, there is a lack of open-source tools and datasets that could be used for quantitatively evaluating an eye tracker’s data quality, comparing performance of multiple trackers, or studying the impact of various operating conditions on a tracker’s accuracy. To address these issues, an open-source code repository named GazeVisual-Lib is developed that contains a number of algorithms, visualizations, and software tools for detailed and quantitative analysis of an eye tracker’s performance and data quality. In addition, a new labelled eye gaze dataset that is collected from multiple user platforms and operating conditions is presented in an open data repository for benchmark comparison of gaze data from different eye tracking systems. The paper presents the concept, development, and organization of these two repositories that are envisioned to improve the performance analysis and reliability of eye tracking systems.

show abstract

The Perspective Geometry of the Eye: Toward Image-Based Eye-Tracking

Cited by 9 publications

References 58 publications

SET: a pupil detection method using sinusoidal approximation

SET: a pupil detection method using sinusoidal approximation

Pupil to limbus ratio: Introducing a simple objective measure using two-box method for measuring early nisocoria and progress of pupillary change in the ICU

Development of Open-source Software and Gaze Data Repositories for Performance Evaluation of Eye Tracking Systems

Contact Info

Product

Resources

About