Eye Gaze Tracking Research Articles

An easy iris center detection method for eye gaze tracking system

Iris center detection accuracy has great impact on eye gaze tracking system performance. This paper proposes an easy and efficient iris center detection method based on modeling the geometric relationship between the detected rough iris center and the two corners of the eye. The method fully considers four states of iris within the eye region, i.e. center, left, right, and upper. The proposed active edge detection algorithm is utilized to extract iris edge points for ellipse fitting. In addition, this paper also presents a predicted edge point algorithm to solve the decrease in ellipse fitting accuracy, when part of the iris becomes hidden from rolling into a nasal or temporal eye corner. The evaluated result of the method on our eye database shows the global average accuracy of 94.3%. Compared with existing methods, our method achieves the highest iris center detection accuracy. Additionally, in order to test the performance of the proposed method in gaze tracking, this paper presents the results of gaze estimation achieved by our eye gaze tracking system.

Comparing Ocular Parameters for Cognitive Load Measurement in Eye-Gaze-Controlled Interfaces for Automotive and Desktop Computing Environments

Eye-gaze tracking is traditionally used to analyze ocular parameters for investigating visual psychology, marketing study, behavior analysis, and so on. Currently, eye-gaze trackers are also being used to control electronic interfaces in assistive technology, automobile control, and even consumer electronic products like smartphones and tablets. However, there are not many attempts to combine these two streams of research on active and passive uses of eye-gaze trackers. This article compares a few ocular parameters to estimate users’ cognitive load in eye-gaze-controlled interfaces. It was found that average velocity of a particular type of microsaccadic eye movement called Saccadic Intrusion is most indicative of users’ cognitive load compared to pupil dilation and eye-blink-based parameters. Results from the study can be used to develop new metrics of cognitive load measurement, as well as to design intelligent gaze-controlled interfaces that respond to users’ cognitive load.

Towards demographic categorization using gaze analysis

Current use of gaze analysis, which is mostly restricted to eye gaze tracking for augmentative and alternative communication (AAC) medium, can benefit people afflicted with amyotrophic lateral sclerosis (ALS). This paper advances the use of gaze analysis for biometrics purposes related to gender and age demographics to benefit applications related to retail space for targeted advertising, behavioral biometrics to benefit health care, and surveillance applications. Towards that end, this paper expands on the recently introduced Gaze ANalysis Technique (GANT) for human identification to combine the length of time spent on observing patterns of interest and the scanning patterns for biometric representation with AdaBoost and super vector machines (SVM) subsequently used for biometric categorization. The experiments conducted show that while the initial results are promising further innovation and development is required to make gaze analysis a viable alternative for demographics categorization, on its own, or together with other biometrics. Further improvements on performance are expected from the derivation, extraction, and use of alternative and novel gaze driven features. This will include among others additional information that is already available about the arc features connecting the fixation points and the dynamics they encode about the roving gaze.

Eye Gaze Tracking With a Web Camera in a Desktop Environment

This paper addresses the eye gaze tracking problem using a low cost and more convenient web camera in a desktop environment, as opposed to gaze tracking techniques requiring specific hardware, e.g., infrared high-resolution camera and infrared light sources, as well as a cumbersome calibration process. In the proposed method, we first track the human face in a real-time video sequence to extract the eye regions. Then, we combine intensity energy and edge strength to obtain the iris center and utilize the piecewise eye corner detector to detect the eye corner. We adopt a sinusoidal head model to simulate the 3-D head shape, and propose an adaptive weighted facial features embedded in the pose from the orthography and scaling with iterations algorithm, whereby the head pose can be estimated. Finally, the eye gaze tracking is accomplished by integration of the eye vector and the head movement information. Experiments are performed to estimate the eye movement and head pose on the BioID dataset and pose dataset, respectively. In addition, experiments for gaze tracking are performed in real-time video sequences under a desktop environment. The proposed method is not sensitive to the light conditions. Experimental results show that our method achieves an average accuracy of around $1.28 ^\circ$ without head movement and $2.27 ^\circ$ with minor movement of the head.

A novel approach to the low cost real time eye mouse

The PCCR (Pupil Center Corneal Reflection) method became dominant for finding human's diverse eye gaze directions through the research on the eye tracking technology that has been done for a very long period of time. The initial studies on the eye tracking technology were related to the general human interface for operating equipment and devices, then it has been promoted to the field of various purposes such as a market research in a recent study analyzing customer's behaviors. In particular, a real time eye gaze tracking system is most important for many HCI applications including stereoscopic synthesis, intend extraction, behavior analysis and etc. In order to make an eye gaze tracking system to be real time, the system must have an efficient pupil detection algorithm and ambience-independent image processing as well as reduced complexity, small size and number of circuit components. This paper proposes a method for getting clean images compared to the previous systems to reduce image processing overhead. Because it also helps reducing the number of image frames to be dropped during the image processing, the proposed method can provide a sufficient performance even on a low cost hardware system by reducing the transmission traffic.

A novel single IR light based gaze estimation method using virtual glints

Among various infrared (IR) image based remote eye gaze tracking (REGT) methods, 2-D interpolation based methods, e.g., the cross ratio-based and homography normalization (HN)-based methods, have been widely researched owing to their highly accurate performance and simplicity with respect to hardware setup. These methods, however, can be employed only when user utilizes more than four IR light sources to obtain multiple corneal reflections projected on the image plane, i.e. glints. In this paper, a novel 2-D interpolation-based REGT method with a single IR light source is proposed, which attains both accuracy and headpose robustness. In the proposed method, the virtual glint (VG), which can substitute for the actual glint, is first estimated by utilizing the mathematical and geometrical principles established between the 3-D location of an IR light source and the corresponding glint in the image plane, and then the point of gaze (POG) is calculated by employing the HN method using the estimated VGs. The experimental results indicate that the proposed REGT method is highly competitive with conventional ones requiring multiple IR light sources, in terms of accuracy and robustness against head movements.

Corneal-Imaging Calibration for Optical See-Through Head-Mounted Displays.

In recent years optical see-through head-mounted displays (OST-HMDs) have moved from conceptual research to a market of mass-produced devices with new models and applications being released continuously. It remains challenging to deploy augmented reality (AR) applications that require consistent spatial visualization. Examples include maintenance, training and medical tasks, as the view of the attached scene camera is shifted from the user's view. A calibration step can compute the relationship between the HMD-screen and the user's eye to align the digital content. However, this alignment is only viable as long as the display does not move, an assumption that rarely holds for an extended period of time. As a consequence, continuous recalibration is necessary. Manual calibration methods are tedious and rarely support practical applications. Existing automated methods do not account for user-specific parameters and are error prone. We propose the combination of a pre-calibrated display with a per-frame estimation of the user's cornea position to estimate the individual eye center and continuously recalibrate the system. With this, we also obtain the gaze direction, which allows for instantaneous uncalibrated eye gaze tracking, without the need for additional hardware and complex illumination. Contrary to existing methods, we use simple image processing and do not rely on iris tracking, which is typically noisy and can be ambiguous. Evaluation with simulated and real data shows that our approach achieves a more accurate and stable eye pose estimation, which results in an improved and practical calibration with a largely improved distribution of projection error.

Eye gaze tracking reveals heightened attention to food in adults with binge eating when viewing images of real-world scenes

Individuals with eating disorders often exhibit food-related biases in attention tasks. To assess the engagement and maintenance of attention to food in adults with binge eating, in the present study, eye gaze tracking was used to compare fixations to food among non-clinical adults with versus without binge eating while they viewed images of real-world scenes. Fifty-seven participants' eye fixations were tracked and recorded throughout 8-second presentations of scenes containing high-calorie and/or low-caloriefood items in various settings (restaurants, social gatherings, etc.). Participants with binge eating fixated on both high-calorie and low-calorie food items significantly more than controls, and this was the case when the high- and low-calorie food items were presented in the same image and in different images. Participants with binge eating also fixated on food items significantly earlier in the presentations. A time course analysis that divided each 8-second presentation into 2-second intervals revealed that participants with binge eating attended to food items more than control participants throughout the 8-second presentation. These results have implications for theory regarding the initiation and maintenance of binge eating.

Perceived interest and overt visual attention in natural images

Region of interest (ROI) based image and video processing has attracted increased research efforts in recent years. The concept of perceptual ROI, however, is not always clearly defined leading to different interpretations between researchers related to bottom-up saliency (signal driven visual attention), top-down attention (subconscious, driven by higher cognitive factors, e.g. interest) or perceived interest. While all of these concepts are likely meaningful in the context of perceptual ROI based image and video processing, it is worth understanding how they are linked altogether. In this paper, the relationship between perceived interest and overt visual attention (which can cover both bottom-up and top-down attention) is studied. Towards this goal, a dedicated ROI selection experiment was performed and is analysed in detail, revealing deep insight into perceived interest in natural images. The outcomes are compared to an eye gaze tracking experiment representing overt visual attention in natural images. It is shown that there is indeed a strong relationship between perceived interest and overt visual attention for a wide range of natural scenes. We show that the relationship has a strong dependence on image content and presentation time during the eye gaze tracking experiment. Furthermore, eye gaze tracking data is revealed to have a high predictive value of primary ROI, particularly in case of the latter dominating over the remainder of the image. Both, the ROI and the eye gaze tracking databases are made publicly available to the research community.

A Probabilistic Approach to Online Eye Gaze Tracking Without Explicit Personal Calibration

Existing eye gaze tracking systems typically require an explicit personal calibration process in order to estimate certain person-specific eye parameters. For natural human computer interaction, such a personal calibration is often inconvenient and unnatural. In this paper, we propose a new probabilistic eye gaze tracking system without explicit personal calibration. Unlike the conventional eye gaze tracking methods, which estimate the eye parameter deterministically using known gaze points, our approach estimates the probability distributions of the eye parameter and eye gaze. Using an incremental learning framework, the subject does not need personal calibration before using the system. His/her eye parameter estimation and gaze estimation can be improved gradually when he/she is naturally interacting with the system. The experimental result shows that the proposed system can achieve <3° accuracy for different people without explicit personal calibration.

Multimodal Intelligent Eye-Gaze Tracking System

This article presents a series of user studies to develop a new eye-gaze tracking–based pointing system. We developed a new target prediction model that works for different input modalities and combined the eye-gaze tracking–based pointing with a joystick controller that can reduce pointing and selection times. The system finds important applications in cockpit of combat aircraft and for computer novice users. User studies confirmed that users can perform significantly faster using this new eye-gaze tracking–based system for both military and everyday computing tasks compared to existing input devices. As part of the study it was also found that the amplitude of maximum power component obtained through Fourier Transform of pupil signal significantly correlates with selection times and perceived cognitive load of users in terms of Task Load Index scores.

Eye Gaze Tracking Reveals Different Effects of a Sad Mood Induction on the Attention of Previously Depressed and Never Depressed Women

This study examined the effect of a sad mood induction (MI) on attention to emotional information and whether the effect varies as a function of depression vulnerability. Previously depressed (N = 42) and never depressed women (N = 58) were randomly assigned to a sad or a neutral MI and then viewed sets of depression-related, anxiety-related, positive, and neutral images. Attention was measured by tracking eye fixations to the images throughout an 8-s presentation. The sad MI had a substantial impact on the attention of never depressed participants: never depressed participants who experienced the sad MI increased their attention to positive images and decreased their attention to anxiety-related images relative to those who experienced the neutral MI. In contrast, previously depressed participants who experienced the sad MI did not attend to emotional images any differently than previously depressed participants who experienced the neutral MI. These results suggest that for never depressed individuals, a sad MI activates an emotion regulation strategy that changes the way that emotional information is attended to in order to counteract the sad mood; the absence of a difference for previously depressed individuals likely reflects a maladaptive emotion regulation response associated with depression vulnerability. Implications for cognitive theories of depression and depression-vulnerability are discussed.

Gaze Estimation Technique for Directing Assistive Robotics

Assistive robotics may extend capabilities for individuals with reduced mobility or dexterity. However, effective use of robotic agents typically requires the user to issue control commands in the form of speech, gesture, or text. Thus, for unskilled or impaired users, the need for a paradigm of intuitive Human-Robot Interaction (HRI) is prevalent. It can be inferred that the most productive interactions are those in which the assistive agent is able to ascertain the intention of the user. Also, to perform a task, the agent must know the user's area of attention in three-dimensional space. Eye gaze tracking can be used as a method to determine a specific Volume of Interest (VOI). However, gaze tracking has heretofore been under-utilized as a means of interaction and control in 3D space. This research aims to determine a practical volume of interest in which an individual's eyes are focused by combining past methods in order to achieve greater effectiveness. The proposed method makes use of eye vergence as a useful depth discriminant to generate a tool for improved robot path planning. This research investigates the accuracy of the Vector Intersection (VI) model when applied to a usably large workspace volume. A neural network is also used in tandem with the VI model to create a combined model. The output of the combined model is a VOI that can be used as an aid in a number of applications including robot path planning, entertainment, ubiquitous computing, and others.

視線追跡装置による衝動性眼球運動速度の計測

視線追跡装置による衝動性眼球運動速度の計測

An Eye Tracking Study of the Time Course of Attention to Positive and Negative Images in Dysphoric and Non-dysphoric Individuals

Researchers studying selective attention in depressed and dysphoric individuals have documented biases in the allocation of attention to emotional information (Gotlib &amp; Joormann, 2010; Yiend, 2010). Recent studies using eye gaze tracking have shown that when images are presented for extended durations (5–30 seconds), depressed and dysphoric individuals attend to depression-related images more than never depressed individuals and attend to positive images less (Armstrong &amp; Olatunji, 2012). The present study used eye gaze tracking and time course analyses to look for differences between dysphoric and non-dysphoric individuals in their attention to emotional images over time. Participants viewed sets of four images (a depression-related image, a threat-related image, a positive image, and a neutral image) while their eye fixations were tracked and recorded throughout a 10-second presentation. The time course analyses, which divided each 10-second presentation into 2-second intervals, revealed that group differences in attention to positive and depression-related images emerged only after 4 seconds had elapsed and then persisted for the remainder of the 10-second presentation. Dysphoric and non-dysphoric participants were further distinguished by the temporal profiles of their attention to positive and depression-related images. The implications for researchers' understanding of attention to emotion in dysphoria and depression are discussed.

A hybrid intelligence-aided approach to affect-sensitive e-learning

E-Learning has revolutionized the delivery of learning through the support of rapid advances in Internet technology. Compared with face-to-face traditional classroom education, e-learning lacks interpersonal and emotional interaction between students and teachers. In other words, although a vital factor in learning that influences a human's ability to solve problems, affect has been largely ignored in existing e-learning systems. In this study, we propose a hybrid intelligence-aided approach to affect-sensitive e-learning. A system has been developed that incorporates affect recognition and intervention to improve the learner's learning experience and help the learner become better engaged in the learning process. The system recognizes the learner's affective states using multimodal information via hybrid intelligent approaches, e.g., head pose, eye gaze tracking, facial expression recognition, physiological signal processing and learning progress tracking. The multimodal information gathered is fused based on the proposed affect learning model. The system provides online interventions and adapts the online learning material to the learner's current learning state based on pedagogical strategies. Experimental results show that interest and confusion are the most frequently occurring states when a learner interacts with a second language learning system and those states are highly related to learning levels (easy versus difficult) and outcomes. Interventions are effective when a learner is disengaged or bored and have been shown to help learners become more engaged in learning.

A Limbus-Based Approach for Eye Gaze Trackers

Eye gaze trackers have numerous applications in medicine, gaming, advertising, teaching and learning, intelligent transportation, etc. In this paper, we proposed a novel approach for video based eye gaze trackers. In this approach, we apply the circumcircle of triangle principle to the limbus part of human eyes. First, an image pre-processing step is used to find three triangle vertices located on limbus. Then, we use the coordinates of these points to determine the limbus center using the circumcircle of triangle principle. Furthermore, when the proposed system fails to find the three useful points on limbus of one eye, a mirror procedure is adopted to find its limbus center based on the information extracted from the other eye. The proposed method can solve the occlusion problem caused by the eyelids that cover part of limbus. The experimental results show that the average eye detection rate is 98.39% and the average error between estimated and actual centers of limbus is only 1.99 pixels. The proposed method is simple, fast, and effective.

Improving the usability of remote eye gaze tracking for human-device interaction

This paper presents a novel single-point calibration-based remote eye gaze tracking (REGT) method. The proposed method consists primarily of two steps. First, a user calibration database (UCDB) that contains user-specific data associated with multiple calibration points (CPs) is constructed for a certain number of users. Second, for new users, the candidate calibrated data are retrieved from the UCDB by simply requesting the users to look at a single CP on the screen center (SC). Experimental results show that the proposed REGT method with single-point calibration demonstrates a highly competitive accuracy compared with conventional methods employing multipoint calibration.

Tracking eye gaze during interpretation of endoluminal three-dimensional CT colonography: visual perception of experienced and inexperienced readers.

To identify and compare key stages of the visual process in experienced and inexperienced readers and to examine how these processes are used to search a moving three-dimensional ( 3D three-dimensional ) image and their relationship to false-negative errors. Institutional review board research ethics approval was granted to use anonymized computed tomographic (CT) colonographic data from previous studies and to obtain eye-tracking data from volunteers. Sixty-five radiologists (27 experienced, 38 inexperienced) interpreted 23 endoluminal 3D three-dimensional CT colonographic videos. Eye movements were recorded by using eye tracking with a desk-mounted tracker. Readers indicated when they saw a polyp by clicking a computer mouse. Polyp location and boundary on each video frame were quantified and gaze data were related to the polyp boundary for each individual reader and case. Predefined metrics were quantified and used to describe and compare visual search patterns between experienced and inexperienced readers by using multilevel modeling. Time to first pursuit was significantly shorter in experienced readers (hazard ratio, 1.22 [95% confidence interval: 1.04, 1.44]; P = .017) but other metrics were not significantly different. Regardless of expertise, metrics such as assessment, identification period, and pursuit times were extended in videos where polyps were visible on screen for longer periods of time. In 97% (760 of 787) of observations, readers correctly pursued polyps. Experienced readers had shorter time to first eye pursuit, but many other characteristics of eye tracking were similar between experienced and inexperienced readers. Readers pursued polyps in 97% of observations, which indicated that errors during interpretation of 3D three-dimensional CT colonography in this study occurred in either the discovery or the recognition phase, but rarely in the scanning phase of radiologic image inspection.

Trends in communicative access solutions for children with cerebral palsy.

Access solutions may facilitate communication in children with limited functional speech and motor control. This study reviews current trends in access solution development for children with cerebral palsy, with particular emphasis on the access technology that harnesses a control signal from the user (eg, movement or physiological change) and the output device (eg, augmentative and alternative communication system) whose behavior is modulated by the user's control signal. Access technologies have advanced from simple mechanical switches to machine vision (eg, eye-gaze trackers), inertial sensing, and emerging physiological interfaces that require minimal physical effort. Similarly, output devices have evolved from bulky, dedicated hardware with limited configurability, to platform-agnostic, highly personalized mobile applications. Emerging case studies encourage the consideration of access technology for all nonverbal children with cerebral palsy with at least nascent contingency awareness. However, establishing robust evidence of the effectiveness of the aforementioned advances will require more expansive studies.