Gaze Estimation

2012 ◽  
pp. 310-325
Author(s):  
Arantxa Villanueva ◽  
Rafael Cabeza ◽  
Javier San Agustin
Keyword(s):  
Eye Tracking ◽  
Accurate Estimate ◽  
Estimation Methods ◽  
Line Of Sight ◽  
Gaze Estimation ◽  
Advanced Mathematics ◽  
Estimation Techniques ◽  
Vector Calculus ◽  
3D Geometry ◽  
Matrix Manipulation

The main objective of gaze trackers is to provide an accurate estimate of the user’s gaze by using the eye tracking information. Gaze, in its most general form, can be considered to be the line of sight or line of gaze, as 3D (imaginary) lines with respect to the camera, or as the point of regard (also termed the point of gaze). This chapter introduces different gaze estimation techniques, including geometry-based methods and interpolation methods. Issues related to both remote and head mounted trackers are discussed. Different fixation estimation methods are also briefly introduced. It is assumed that the reader is familiar with basic 3D geometry concepts as well as advanced mathematics, such as matrix manipulation and vector calculus.

scholarly journals Accurate Model-Based Point of Gaze Estimation on Mobile Devices

Vision ◽  
2018 ◽  
Vol 2 (3) ◽  
pp. 35 ◽  
Author(s):  
Braiden Brousseau ◽  
Jonathan Rose ◽  
Moshe Eizenman
Keyword(s):  
Eye Tracking ◽  
Mobile Devices ◽  
Head Movements ◽  
Roll Angle ◽  
New Method ◽  
Estimation Methods ◽  
Infrared Light ◽  
Gaze Estimation ◽  
Tracking Systems ◽  
Estimation Models

The most accurate remote Point of Gaze (PoG) estimation methods that allow free head movements use infrared light sources and cameras together with gaze estimation models. Current gaze estimation models were developed for desktop eye-tracking systems and assume that the relative roll between the system and the subjects’ eyes (the ’R-Roll’) is roughly constant during use. This assumption is not true for hand-held mobile-device-based eye-tracking systems. We present an analysis that shows the accuracy of estimating the PoG on screens of hand-held mobile devices depends on the magnitude of the R-Roll angle and the angular offset between the visual and optical axes of the individual viewer. We also describe a new method to determine the PoG which compensates for the effects of R-Roll on the accuracy of the POG. Experimental results on a prototype infrared smartphone show that for an R-Roll angle of 90 ° , the new method achieves accuracy of approximately 1 ° , while a gaze estimation method that assumes that the R-Roll angle remains constant achieves an accuracy of 3.5 ° . The manner in which the experimental PoG estimation errors increase with the increase in the R-Roll angle was consistent with the analysis. The method presented in this paper can improve significantly the performance of eye-tracking systems on hand-held mobile-devices.

scholarly journals High-Accuracy Gaze Estimation for Interpolation-Based Eye-Tracking Methods

Vision ◽  
2021 ◽  
Vol 5 (3) ◽  
pp. 41
Author(s):  
Fabricio Batista Narcizo ◽  
Fernando Eustáquio Dantas dos Santos ◽  
Dan Witzner Hansen
Keyword(s):  
Eye Tracking ◽  
Optical Axis ◽  
High Accuracy ◽  
Estimation Methods ◽  
Geometric Transformation ◽  
Gaze Estimation ◽  
Eye Tracker ◽  
Simulated Environment ◽  
Camera Location ◽  
Transformation Methods

This study investigates the influence of the eye-camera location associated with the accuracy and precision of interpolation-based eye-tracking methods. Several factors can negatively influence gaze estimation methods when building a commercial or off-the-shelf eye tracker device, including the eye-camera location in uncalibrated setups. Our experiments show that the eye-camera location combined with the non-coplanarity of the eye plane deforms the eye feature distribution when the eye-camera is far from the eye’s optical axis. This paper proposes geometric transformation methods to reshape the eye feature distribution based on the virtual alignment of the eye-camera in the center of the eye’s optical axis. The data analysis uses eye-tracking data from a simulated environment and an experiment with 83 volunteer participants (55 males and 28 females). We evaluate the improvements achieved with the proposed methods using Gaussian analysis, which defines a range for high-accuracy gaze estimation between −0.5∘ and 0.5∘. Compared to traditional polynomial-based and homography-based gaze estimation methods, the proposed methods increase the number of gaze estimations in the high-accuracy range.

scholarly journals Low Cost Eye Tracking: The Current Panorama

2016 ◽  
Vol 2016 ◽  
pp. 1-14 ◽  
Author(s):  
Onur Ferhat ◽  
Fernando Vilariño
Keyword(s):  
Eye Tracking ◽  
Visible Light ◽  
Open Source ◽  
Low Cost ◽  
Gaze Estimation ◽  
Head Pose ◽  
Gaze Tracking ◽  
Estimation Techniques ◽  
Public Datasets ◽  
Interesting Alternative

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.

scholarly journals Comparative Analysis of Kinect-Based and Oculus-Based Gaze Region Estimation Methods in a Driving Simulator

Sensors ◽  
2020 ◽  
Vol 21 (1) ◽  
pp. 26
Author(s):  
David González-Ortega ◽  
Francisco Javier Díaz-Pernas ◽  
Mario Martínez-Zarzuela ◽  
Míriam Antón-Rodríguez
Keyword(s):  
Virtual Reality ◽  
Comparative Analysis ◽  
Driving Simulator ◽  
Estimation Method ◽  
Estimation Methods ◽  
Gaze Estimation ◽  
Driving Simulators ◽  
Oculus Rift ◽  
Gaze Patterns ◽  
And Performance

Driver’s gaze information can be crucial in driving research because of its relation to driver attention. Particularly, the inclusion of gaze data in driving simulators broadens the scope of research studies as they can relate drivers’ gaze patterns to their features and performance. In this paper, we present two gaze region estimation modules integrated in a driving simulator. One uses the 3D Kinect device and another uses the virtual reality Oculus Rift device. The modules are able to detect the region, out of seven in which the driving scene was divided, where a driver is gazing at in every route processed frame. Four methods were implemented and compared for gaze estimation, which learn the relation between gaze displacement and head movement. Two are simpler and based on points that try to capture this relation and two are based on classifiers such as MLP and SVM. Experiments were carried out with 12 users that drove on the same scenario twice, each one with a different visualization display, first with a big screen and later with Oculus Rift. On the whole, Oculus Rift outperformed Kinect as the best hardware for gaze estimation. The Oculus-based gaze region estimation method with the highest performance achieved an accuracy of 97.94%. The information provided by the Oculus Rift module enriches the driving simulator data and makes it possible a multimodal driving performance analysis apart from the immersion and realism obtained with the virtual reality experience provided by Oculus.

Integrating fuzzy case-based reasoning, parametric and feature-based cost estimation methods for machining process

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Fentahun Moges Kasie ◽  
Glen Bright
Keyword(s):  
Cost Estimation ◽  
Intelligent System ◽  
Machining Process ◽  
Estimation Methods ◽  
Case Based Reasoning ◽  
Cost Estimates ◽  
Content Type ◽  
Estimation Techniques ◽  
Feature Based ◽  
Case Based

Purpose This paper aims to propose an intelligent system that serves as a cost estimator when new part orders are received from customers. Design/methodology/approach The methodologies applied in this study were case-based reasoning (CBR), analytic hierarchy process, rule-based reasoning and fuzzy set theory for case retrieval. The retrieved cases were revised using parametric and feature-based cost estimation techniques. Cases were represented using an object-oriented (OO) approach to characterize them in n-dimensional Euclidean vector space. Findings The proposed cost estimator retrieves historical cases that have the most similar cost estimates to the current new orders. Further, it revises the retrieved cost estimates based on attribute differences between new and retrieved cases using parametric and feature-based cost estimation techniques. Research limitations/implications The proposed system was illustrated using a numerical example by considering different lathe machine operations in a computer-based laboratory environment; however, its applicability was not validated in industrial situations. Originality/value Different intelligent methods were proposed in the past; however, the combination of fuzzy CBR, parametric and feature-oriented methods was not addressed in product cost estimation problems.

Parameter estimation using relay feedback

2019 ◽  
Vol 35 (4) ◽  
pp. 505-529
Author(s):  
Kalpana Dharmalingam ◽  
Thyagarajan Thangavelu
Keyword(s):  
Parameter Estimation ◽  
Closed Loop ◽  
Parametric Estimation ◽  
Estimation Methods ◽  
Model Parameters ◽  
Relay Feedback ◽  
Research Activity ◽  
Process Industries ◽  
Single Input Single Output ◽  
Estimation Techniques

Abstract In process industries, closed-loop step and closed-loop relay feedback tests are popularly used for estimating model parameters. In this paper, different methods available in the literature for parameter estimation using conventional techniques and techniques based on relay feedback test are surveyed by reviewing around 152 research articles published during the past three decades. Through a comprehensive survey of available literature, the parameter estimation methods are classified into two broad groups, namely conventional techniques and relay-based parametric estimation techniques. These relay-based techniques are further classified into two subgroups, namely single-input-single-output (SISO) systems and multi-input-multi-output systems (both square and nonsquare), and are revealed in a lucid manner with the help of benchmark examples and case studies. For the above categorized methods, the procedural steps involved in relay-based parametric estimation methods are also presented. To facilitate the readers, comparison tables are included to comprehend the results of different parametric estimation techniques available in the literature. The incorporation of quantitative and qualitative analysis of papers published in various journals in the above area with the help of pie charts and graphs would enable the readers to grasp the overview of the research activity being carried out in the relay feedback domain. At the end, the challenging issues in relay-based parametric estimation methods and the directions for future investigations that can be explored are also highlighted.

Performance Analysis of Tacholess Rotation Speed Estimation Methods for Condition Monitoring of Gearboxes of Offshore Wind Farm

2021 ◽  
Author(s):  
Cédric Peeters ◽  
Jérôme Antoni ◽  
Quentin Leclère ◽  
Jan Helsen
Keyword(s):  
Wind Farm ◽  
Rotation Speed ◽  
Probabilistic Approach ◽  
Offshore Wind ◽  
Estimation Methods ◽  
Offshore Wind Turbine ◽  
Large Set ◽  
Speed Estimation ◽  
Estimation Techniques ◽  
Vibration Data

Abstract This paper investigates the efficacy and reliability of three different state-of-the-art rotation speed estimation techniques on a very large set of experimental vibration data originating from thirty offshore wind turbine gearboxes. The three methods include the multi-order probabilistic approach, the phase demodulation method based on the frequency-domain energy operator, and the multi-harmonic demodulation technique. The goal is twofold: to assess statistically the performance of present-day vibration-based rotation speed estimation techniques on challenging experimental data, and to establish indirect rotation speed estimation through vibration data as a viable alternate solution to the conventional solution involving a direct measurement with a physical device such as a tachometer or an angle encoder. The results show that while all three techniques attain satisfying results, the multi-harmonic demodulation technique produces the most accurate speed estimate for the majority of all measurements whilst also being flexible in its usage.

Sign in / Sign up

Export Citation Format

Share Document