Eye Gaze Tracking Research Articles

Improving Collaborative Filtering-Based Image Recommendation through Use of Eye Gaze Tracking

Due to the overwhelming variety of products and services currently available on electronic commerce sites, the consumer finds it difficult to encounter products of preference. It is common that product preference be influenced by the visual appearance of the image associated with the product. In this context, Recommendation Systems for products that are associated with Images (IRS) become vitally important in aiding consumers to find those products considered as pleasing or useful. In general, these IRS use the Collaborative Filtering technique that is based on the behaviour passed on by users. One of the principal challenges found with this technique is the need for the user to supply information concerning their preference. Therefore, methods for obtaining implicit information are desirable. In this work, the author proposes an investigation to discover to which extent information concerning user visual attention can aid in producing a more precise IRS. This work proposes therefore a new approach, which combines the preferences passed on from the user, by means of ratings and visual attention data. The experimental results show that our approach exceeds that of the state of the art.

A Low-Cost Pupil Center Localization Algorithm Based on Maximized Integral Voting of Circular Hollow Kernels

Abstract Pupil center localization is an essential requirement for robust eye gaze tracking systems. In this paper, a low-cost pupil center localization algorithm is presented. The aim is to propose a computationally inexpensive algorithm with high accuracy in terms of performance and processing speed. Hence, a computationally inexpensive pupil center localization algorithm based on maximized integral voting of candidate kernels is presented. As the kernel type, a novel circular hollow kernel (CHK) is used. Estimation of pupil center is employed by applying a rule-based schema for each pixel over the eye sockets. Additionally, several features of CHK are proposed for maximizing the probability of voting for each kernel. Experimental results show promising results with 96.94% overall accuracy with around 13.89 ms computational time (71.99 fps) for a single image as an average time by using a standard PC. An extensive benchmarking study indicates that this method outperforms the learning-free algorithms and it competes with the other methods having a learning phase while their processing speed is much higher. Furthermore, this proposed learning-free system is fast enough to run on an average PC and also applicable to work with even a low-resolution webcam on a real-time video stream.

Integration of BCI and Eye Gaze Tracker to Control Mouse

Integration of BCI and Eye Gaze Tracker to Control Mouse

Code-VEP vs. Eye Tracking: A Comparison Study.

Even with state-of-the-art techniques there are individuals whose paralysis prevents them from communicating with others. Brain–Computer-Interfaces (BCI) aim to utilize brain waves to construct a voice for those whose needs remain unmet. In this paper we compare the efficacy of a BCI input signal, code-VEP via Electroencephalography, against eye gaze tracking, among the most popular modalities used. These results, on healthy individuals without paralysis, suggest that while eye tracking works well for some, it does not work well or at all for others; the latter group includes individuals with corrected vision or those who squint their eyes unintentionally while focusing on a task. It is also evident that the performance of the interface is more sensitive to head/body movements when eye tracking is used as the input modality, compared to using c-VEP. Sensitivity to head/body movement could be better in eye tracking systems which are tracking the head or mounted on the face and are designed specifically as assistive devices. The sample interface developed for this assessment has the same reaction time when driven with c-VEP or with eye tracking; approximately 0.5–1 second is needed to make a selection among the four options simultaneously presented. Factors, such as system reaction time and robustness play a crucial role in participant preferences.

Free Head Movement Eye Gaze Contingent Ultrasound Interfaces for the da Vinci Surgical System

The current practice of intraoperative ultrasound requires an assistant because the surgeon's hands are occupied with surgical tools or console instruments. This process can be tedious and prone to error. Eye gaze is a promising control modality that can help address this issue. In previous work, a novel feature-based retro-fit eye gaze tracker has been designed for the da Vinci surgical system. In this letter, leveraging the da Vinci research kit, three interfaces incorporate eye gaze, and voice recognition into the da Vinci surgical system for ultrasound control in one common framework. This letter aims to improve autonomous use of ultrasound for surgeons. Since eye gaze tracking is sensitive to head movement, a novel calibration procedure is also proposed to accommodate head motion by decomposing pupil movement into eye rotation and head motion. This ensures that the eye gaze tracking can be reliably used as a control modality. A user study (N = 20) has shown that the designed eye gaze tracker has a mean binocular accuracy of 1.98° with mean -0.92 mm horizontal and 16.83-mm vertical head movement. A preliminary user study (N = 9) has shown that eye gaze tracking for ultrasound control has the potential to improve the way surgeons interact with their instrumentation and increase surgical autonomy.

상업시설 공간구성의 실시간 시선추적에 나타난 소비자 시지각 정보획득 특성 연구

상업시설 공간구성의 실시간 시선추적에 나타난 소비자 시지각 정보획득 특성 연구

Future trends in early diagnosis for cognition impairments in children based on eye measurements [Trends in Future I&M

There is a saying that the eyes are the gate to one's soul and the witnesses for various internal cognitive or emotional processes. Starting from this observation, a multitude of lesstraditional areas of research involving eye measures and gaze tracking were developed. As examples one can note the detection of deception as part of hostile intention perception, the estimation of pain intensity via facial expression analysis, interpersonal coordination of mother-infant, assistance in marketing, and also contributions to early detection of impairments such as the ones related to children affected by autism, dyslexia or anxiety disorders.

Assistive technology for disabled visual artists: exploring the impact of digital technologies on artistic practice

Disabled artists with physical impairments can experience significant barriers in producing creative work. Digital technologies offer alternative opportunities to support artistic practice, but there has been a lack of research investigating the impact of assistive digital tools in this context. This article explores the current practice of physically impaired visual artists and their experiences around the use of digital technologies. An online survey was conducted with professional disabled artists and followed up by face-to-face interviews with 10 invited artists. The findings illustrate the issues disabled artists experience in their practice and highlight how they are commonly using mainstream digital technologies as part of their practice. However, there is little awareness around novel forms of technology (e.g. eye gaze tracking) that present new creative opportunities. The importance of digital tools for supporting wider practice (i.e. administrative and business tasks) was also highlighted as a key area where further work is required.

30‐2: Implementation of a Real‐time Eye Gaze Tracking Solution for ASIC Based on VR Display

We implemented an ASIC‐oriented, real‐time eye gaze tracking solution without calling ARM, DSP, calculation IP cores and external memories. Prototype validation on Xilinx kintex‐7 platform showed that the sampling rate of the system can be above 380Hz and the accuracy is ≦1.5 degree at 200MHz frequency.

An Eye-gaze Tracking System for Teleoperation of a Mobile Robot

Most telerobotic applications rely on a Human-Robot Interface that requires the operator to continuously monitor the state of the robot through visual feedback while uses manual input devices to send commands to control the navigation of the robot. Although this setup is present in many examples of telerobotic applications, it may not be suitable in situations when it is not possible or desirable to have manual input devices, or when the operator has a motor disability that does not allow the use of that type of input devices. Since the operator already uses his/her eyes in the monitoring task, an interface based on the inputs from their gaze could be used to teleoperate the robot. This paper presents a telerobotic platform that uses a user interface based on eye-gaze tracking that enables a user to control the navigation of a teleoperated mobile robot using only his/her eyes as inputs to the system. Details of the operation of the eye-gaze tracking system and the results of a task-oriented evaluation of the developed system are also included.

Trading Accuracy for Speed in Selective Attention Tasks during Sleep Deprivation

Selective attention is a critical cognitive function in tasks that require careful monitoring of visual information. An increasing amount of night work on jobs that meet such requirements motivates the study of the effects of sleep deprivation (SD) on selective attention. Monitoring tasks in occupational settings can be operationalized for study in the laboratory by visual search tasks, in which the subject has to identify rare target items among distractor items. Visual search under SD leads to a decrease of overall response speed and accuracy. However, an increase of response speed per item with increasing number of items was also found under SD. This might indicate an unfavorable speed‐accuracy trade‐off: decision speed per item increases, while accuracy decreases in turn. Eye gaze tracking may provide additional indications for the duration of individual decisions during the search process.We recorded gaze behavior during two standard visual search tasks to explore if SD leads to faster and sloppier decisions per item (shorter fixation durations). Visual search performance (response time and sensitivity d′) in the conjunction (CST) and spatial configuration (SST) search task and the associated gaze behavior were tested in two groups of subjects. While sleep deprived participants (N=24, age: 25 ± 5 SD; 12 women) were kept awake during a 24 hour period, participants of a control group (N=24, age: 26 ± 4 SD; 10 women) were allowed to sleep (TIB: 8 hours).We found an increase of response time under SD compared to the control group (CST: p = 0.019, MSD= 128 ms ± 220 SD, MC= 1 ms ± 169 SD; SST: p < 0.001, MSD= 65 ms ± 755 SD, MC=− 45 ms ± 604 SD) and a decrease in sensitivity d′ (CST: p = 0.03, MSD= −0.14 ± 0.65 SD, MC= 0.01 ± 0.58 SD; SST: p < 0.001, MSD=−0.43 ± 0.82 SD, MC= 0.10 ± 0.64 SD). For gaze behavior, we found indications of a cognitive slowing in slower saccade velocities for the SD group compared to the control group (CST: p < 0.001, MSD= −38.8 °/s ± 42.4 SD, MC= −5.1 °/s ± 33.8 SD; SST: p < 0.001, MSD= −29.0 °/s ± 32.4 SD, MC= −2.8 °/s ± 23.7 SD) but not in terms of longer fixation durations. On the contrary, fixation durations decreased in the SD group relative to the control group (CST: p = 0.018, MSD= −16.1 ms ± 30.3 SD, MC= −6.2 ms ± 25.1 SD; SST: p = 0.008, MSD= −11.0 ms ± 23.4 SD, MC= −2.2 ms ± 19.7 SD). Moreover, the change in fixation duration was positively correlated with the change in task accuracy (CST: ρ = 0.29, p = 0.048; SST: ρ = 0.33, p = 0.022), suggesting that subjects that showed the strongest decrease in fixation duration exhibited also the strongest decrease in search accuracy. Further analysis showed that the general decrease of fixation duration was mainly associated with a steep increase of the frequency of very brief fixation durations, so called ‘express fixations' with durations shorter than 120 ms.The decrease in fixation duration under SD is further evidence for a shifted speed‐accuracy trade‐off as indicated by earlier search studies. SD seemingly leads to an increase of decision speed at the cost of reduced accuracy. Consequently, SD not only results in overall cognitive slowing but also in an impairment of adequate resource allocation in selective attention, potentially due to the absence of prefrontal inhibitory control.This abstract is from the Experimental Biology 2018 Meeting. There is no full text article associated with this abstract published in The FASEB Journal.

Attention to fat- and thin-related words in body-satisfied and body-dissatisfied women before and after thin model priming.

Understanding the cognitive processes underlying body dissatisfaction provides important information on the development and perpetuation of eating pathology. Previous research suggests that body-dissatisfied women process weight-related information differently than body-satisfied women, but the precise nature of these processing differences is not yet understood. In this study, eye-gaze tracking was used to measure attention to weight-related words in body-dissatisfied (n = 40) and body-satisfied (n = 38) women, before and after exposure to images of thin fashion models. Participants viewed 8-second displays containing fat-related, thin-related, and neutral words while their eye fixations were tracked and recorded. Based on previous research and theory, we predicted that body-dissatisfied women would attend to fat-related words more than body-satisfied women and would attend to thin-related words less. It was also predicted that exposure to thin model images would increase self-rated body dissatisfaction and heighten group differences in attention. The results indicated that body-dissatisfied women attended to both fat- and thin-related words more than body-satisfied women and that exposure to thin models did not increase this effect. Implications for cognitive models of eating disorders are discussed.

Detecting drivers’ cognitive load from saccadic intrusion

In this paper, we have explored use of Saccadic Intrusion to detect drivers’ cognitive load and instantaneous perception of developing road hazards. Saccadic Intrusion is a type of eye gaze movement which was earlier found to be related to change in cognitive load. We have developed an algorithm to detect saccadic intrusion from a commercially available low-cost eye gaze tracker and conducted four user studies involving a driving simulator and cognitive and hazard perception tests. Our results show that average velocities of saccadic intrusion increases with increase in cognitive load and recording saccadic intrusion and eye blinks for 6 s duration can predict drivers’ instantaneous perception of developing road hazards.

3D gaze estimation without explicit personal calibration

Model-based 3D gaze estimation represents a dominant technique for eye gaze estimation. It allows free head movement and gives good estimation accuracy. But it requires a personal calibration, which may significantly limit its practical utility. Various techniques have been proposed to replace intrusive and subject-unfriendly calibration methods. In this paper, we introduce a new implicit calibration method that takes advantage of four natural constraints during eye gaze tracking. The first constraint is based on two complementary gaze estimation methods. The underlying assumption is that different gaze estimation methods, though based on different principles and mechanisms, ideally predict exactly the same gaze point at the same time. The second constraint is inspired by the well-known center prior principle, it is assumed that most fixations are concentrated on the center of the screen with natural viewing scenarios. The third constraint arises from the fact that for console based eye tracking, human’s attention/gaze are always within the screen region. The final constraint comes from eye anatomy, where the value of eye parameters must be within certain regions. The four constraints are integrated jointly and help formulate the implicit calibration as a constrained unsupervised regression problem, which can be effectively solved through the proposed iterative hard EM algorithm. Experiments on two everyday interactions Web-browsing and Video-watching demonstrate the effectiveness of the proposed implicit calibration method.

The specificity of attentional biases by type of gambling: An eye-tracking study.

A growing body of research indicates that gamblers develop an attentional bias for gambling-related stimuli. Compared to research on substance use, however, few studies have examined attentional biases in gamblers using eye-gaze tracking, which has many advantages over other measures of attention. In addition, previous studies of attentional biases in gamblers have not directly matched type of gambler with personally-relevant gambling cues. The present study investigated the specificity of attentional biases for individual types of gambling using an eye-gaze tracking paradigm. Three groups of participants (poker players, video lottery terminal/slot machine players, and non-gambling controls) took part in one test session in which they viewed 25 sets of four images (poker, VLTs/slot machines, bingo, and board games). Participants' eye fixations were recorded throughout each 8-second presentation of the four images. The results indicated that, as predicted, the two gambling groups preferentially attended to their primary form of gambling, whereas control participants attended to board games more than gambling images. The findings have clinical implications for the treatment of individuals with gambling disorder. Understanding the importance of personally-salient gambling cues will inform the development of effective attentional bias modification treatments for problem gamblers.

HEYEbrid

We introduce hEYEbrid, a calibration-free method for spontaneous and long-term eye gaze tracking, with competitive gaze estimation. It is based on a hybrid concept that combines infrared eye images with corneal imaging. For this, two eye cameras are mounted on a glasses frame. In this way, the pupil can be tracked quickly with high precision. This information is translated into the corneal image, which is used to create a connection to the environment, acting like a scene camera. In a user study with 20 participants, we evaluated our approach against an extended version of the system, called 3C-hEYEbrid, and a state-of-the-art head-mounted Pupil Labs eye tracker. We show that hEYEbrid provides accurate gaze estimation in unconstrained environments and is robust against calibration drift (e.g. caused by taking off and putting on the device). In addition, we present a mobile and wearable implementation of hEYEbrid and 3C-hEYEbrid, that is also usable with a monocular Pupil Labs eye tracker. It connects the head-mounted device to a mobile phone, enabling gaze estimation in real time. hEYEbrid represents a significant step towards pervasive gaze-based interfaces.

Head-mounted eye gaze tracking devices: An overview of modern devices and recent advances.

An increasing number of wearable devices performing eye gaze tracking have been released in recent years. Such devices can lead to unprecedented opportunities in many applications. However, staying updated regarding the continuous advances and gathering the technical features that allow to choose the best device for a specific application is not trivial. The last eye gaze tracker overview was written more than 10 years ago, while more recent devices are substantially improved both in hardware and software. Thus, an overview of current eye gaze trackers is needed. This review fills the gap by providing an overview of the current level of advancement for both techniques and devices, leading finally to the analysis of 20 essential features in six head-mounted eye gaze trackers commercially available. The analyzed characteristics represent a useful selection providing an overview of the technology currently implemented. The results show that many technical advances were made in this field since the last survey. Current wearable devices allow to capture and exploit visual information unobtrusively and in real time, leading to new applications in wearable technologies that can also be used to improve rehabilitation and enable a more active living for impaired persons.

Security Systems Based On Eye Movement Tracking Methods

This survey presents an overview of eye-tracking techniques for various security systems, provides insights into using eye-tracking techniques in security systems. This paper classifies the techniques using some researches. Researches depend on characteristics of eye tracking data, which includes viewer and stimuli aspects, also it does depend on characteristics related to visualization methods. This work contributed in explain some of the security systems that depend on eye gaze tracking, the consequences, the positive and negative aspects resulting from the use of eye gaze tracking in the security system, presents the strengths and weaknesses to keep in mind in future.

Validation of eye-tracking measures of social attention as a potential biomarker for autism clinical trials.

Eye-gaze tracking (EGT), an automated tool that tracks eye-gaze patterns, might help measure outcomes in clinical trials investigating interventions to treat autism spectrum disorders. In this study, an EGT task was evaluated in children with ASD, who watched a video with an actor talking directly to them. Patterns of eye-gaze were associated with caregiver-reported measures of social communication that are used in clinical trials. We show EGT may be a promising objective tool measuring outcomes.

高齢者の身体的特徴を考慮した視線追跡用Face-Mounted Displayの開発

高齢者の身体的特徴を考慮した視線追跡用Face-Mounted Displayの開発