Publication Hub

Gaze behavior data in the vitrine of human movement science: considerations on eye-tracking technique

BACKGROUND: Eyes are the main gateway of visual information input. Moving the eyes is essential to extract visual information from scenes while performing motor actions. This helps to explain motor behavior, especially related to visual attention mechanisms, gaze training and learning, and the relevance of visual information in controlling actions. Thus, collecting data on gaze behavior is important for explaining motor behavior. AIM: We present the main video-based eye-tracking techniques, briefly describe the anatomy of the eyes, explain the operation of the eye-tracker (eye capture techniques, calibration, and data analysis), and propose interpretations of the main variables that were extracted by the technique. This way we develop considerations (limitations and advantages) on the eye-tracking technique that placed gaze behavior data under the view of human movement science. INTERPRETATION: Eye-tracking has become an excellent tool to assist in the analysis of human movement through gaze behavior. It is possible to make inferences, mainly from the combination of sensory information, such as visual information, with performance during motor tasks, about perception, cognition, and human behavior during the most diverse day-to-day activities. Eye-tracker systems have been employed in different majors related to motor behavior, such as medicine, commerce, and game development. KEYWORDS: Eye movement | Vision | Motor behavior

Eye Tracking Glasses

Software

4 versions available

Hand-Eye Behaviour Analytics for Children with Autism Spectrum Disorder

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition that typically manifests in early childhood. Early detection and diagnosis of the disease are vital for ensuring that children receive the necessary support and interventions, which can significantly improve their outcomes. However, the shortage of clinical professionals and the lengthy diagnostic process pose significant barriers to early screening and diagnosis. This highlights the pressing need to develop efficient and effective methods to enhance the early screening and diagnosis procedure. Human behaviour analytics has emerged as a promising solution to this challenge. This field leverages computer vision technology, providing valuable insights into behaviour patterns. Utilising Vision-based human behaviour analytics methods, the atypical hand and eye behaviour patterns in individuals with ASD can be objectively measured to provide valuable insights and objective behaviour measurement to aid in the diagnosis process. This thesis aims to utilise the methods of human behaviour analytics to conduct a study of the hand and eye-related atypical behavioural patterns in individuals with ASD, with the goal of ultimately enhancing the efficiency of ASD early screening and diagnosis. Firstly, action recognition has been incorporated into ASD research in recognising stereotyped behaviours. Compared to other modal data, skeletal data can better accommodate spatial-temporal information, which, together with the attention mechanism, is expected to model the temporal correlation better, thus improving recognition accuracy. Therefore, a self-attention network with a novel 2D skeleton joint position encoding is adopted for action/gesture recognition tasks; it obtained competitive results with reduced computational complexity. Furthermore, the action recognition performance of ASD stereotyped behaviour was significantly improved by applying transfer learning. Secondly, to facilitate manual behaviour observation in ASD diagnoses, two behaviour quantitative analysis strategies have been proposed. The first approach proposes a Sequential Bag of Convolutional Features (SBoCF) method based on the bag-of-words (BoW) model. This approach employs deep learning techniques to eliminate the need for manually human-observed behavioural coding (HOC), enabling efficient and objective behavioural analysis. The second approach draws inspiration from the action quality assessment (AQA) concept and develops corresponding deep learning models for scoring ASD behaviours. This approach achieves promising results, showing statistical correlations between model-predicted scores and truth scores on a large public ASD dataset. Finally, consider the atypical hand-eye behaviour in ASD to further explore joint hand-eye behaviour research and build an interpretative framework for assessing hand-eye coordination (HEC) abilities. This study designs a hand-drawing imitation protocol with a vision-based data acquisition system. A hand-eye coordination ability metric based on Cross-Recurrence Quantitative Analysis (C-RQA) is also proposed. In conclusion, this thesis comprehensively studies hand and joint hand-eye behaviour analytics for children with ASD. By incorporating machine learning and computer vision technologies, it attempts to develop new methods and techniques to assist in the diagnosis and intervention of ASD. The study focuses on both qualitative and quantitative analysis of behaviour patterns and demonstrates the potential of these techniques in diagnosing ASD.

Eye Tracking Glasses

Software

1 version available:

How do drivers allocate visual attention to vulnerable road users when turning at urban intersections?

Drivers turning at urban intersections pose a high risk to Vulnerable Road Users (VRUs), such as cyclists and pedestrians. In vehicle collisions with VRUs, driver attention misallocation is considered a leading contributor. While previous naturalistic studies have examined driver gaze behaviors at intersections, findings are limited to general gaze directions obtained through video analysis, meaning specific areas to which drivers attend cannot be determined. We present a secondary analysis of an on-road instrumented vehicle dataset collected in 2019 which offers eye-tracking and video data from 26 experienced drivers (13 cyclists and 13 non-cyclists). Three coders jointly examined eye-tracking footage from four right-signalized turns (n=96) to quantify drivers’ glance distributions to various areas of interest, including those most relevant to VRU safety when drivers turn. Individual temporal glance patterns and general attention allocation trends are presented and described. (1) Relevant pedestrians were the top objects of glance irrespective of signal status, and (2) at red light turns, driver attention was heavily skewed toward leftward traffic. This analysis provides a detailed report of driver glance distributions toward scene-specific areas (as opposed to general directions) at urban intersections and discusses how these patterns may influence VRU safety.

Eye Tracking Glasses

Simulator

5 versions available

Hypoxia impairs reaction time but not response accuracy in a visual choice reaction task

We investigated the effect of hypoxia on the reaction time (RT) and response accuracy of pilots performing a visual choice reaction task that corresponded to the scanning of helmet mounted display (HMD) symbology. Eighteen male military pilots performed the task in a hypobaric chamber at two simulated altitudes (92 m and 4572 m) in a single-blinded repeated measures and counter-balanced design. The visual stimuli were displayed in low and high contrast and at a 30- and 50-degree field of view (FoV). We measured the pilots' RT and response accuracy. Using an eye tracker, we measured the pilot's glance time at each stimulus location. Finally, we collected subjective ratings of alertness. The results show that hypoxia increased the RT and glance time. Lowering the stimulus contrast and increasing the FoV further increased the RT, independent of hypoxia. These findings provide no evidence for hypoxia-induced changes in visual contrast sensitivity or visual field. Instead, hypoxia seemed to affect RT and glance time by reducing alertness. Despite the increased RT, the pilots maintained their accuracy on the visual task, suggesting that visual scanning of HMD symbology may be resistant to the effects of acute hypoxia.

Eye Tracking Glasses

Simulator

5 versions available

Impact of Road Central Greening Configuration on Driver Eye Movements: A Study Based on Real Vehicle Experiments

Safe driving depends on drivers’ ability to rapidly and accurately process information in varying traffic conditions. The presence of central green landscapes on roads is a key factor in this context. However, there is a gap in current research, which tends to focus on qualitative aspects of landscape design while lacking quantitative data-driven analyses. In this study, we aim to address this gap by investigating the impact of road central greening configuration on the eye movements of young novice drivers, a population particularly sensitive to external environmental changes. Specifically, we explore the influence of central green landscapes on four visual parameters: driver gaze, saccade, blinking, and pupil behavior. Through real vehicle experiments conducted on different road sections, we collected visual feature data to comprehensively analyze the patterns of driver eye movements. Our findings reveal that the introduction of central green landscapes can exert cognitive pressure on drivers, leading to specific alterations in their visual parameters. These changes include dispersed gaze points, reduced effective gaze durations, increased gaze frequencies, extended saccade durations and angles, heightened blink durations and frequencies, and reduced pupil area. By shedding light on the intricate interplay between road central greenery and driver behavior, this study provides valuable insights for optimizing landscape design in transportation planning and enhancing road safety considerations.

Eye Tracking Glasses

Software

5 versions available

Improving Driving Automation Training Through Scaffolding of Roles and Responsibilities Information: A Comparison between Older and Younger Drivers

Adaptive Cruise Control (ACC) is an Advanced Driver Assistance System (ADAS) commonly found in new vehicles that shares the responsibilities of maintaining headway and speed. However, drivers often have a limited understanding of their roles and responsibilities and how they should modify their behaviors when driving with ACC. This study investigates the effect of scaffolding teaching technique by providing additional background knowledge about ACC and highlighting drivers’ new roles and responsibilities for both older and younger adults during text-based ACC training programs. The study also initiates a new approach to evaluate drivers’ learning outcomes at different stages of driving automation training (i.e., reading behavior during training, post-training knowledge test, gaze monitoring behavior, and driving performance during simulated driving). Thirty-nine participants (20 younger + 19 older) received one of the two ACC training protocols: basic (system functionality, operational procedures, and limitations) and comprehensive (basic training + ACC background information and driving roles and responsibilities). The results showed that the comprehensive training led to reduced reading page revisits and adjusted workload during training, better performance in post-training knowledge tests, and more ACC engagement during simulated driving. The findings also suggested the feasibilities and connections within the new training evaluation approach that can provide insights into understanding ACC training outcomes through different stages. Future research is needed to further explore the effect of scaffolding teaching method on trainees’ learning-behavioral translation and the application of the new training evaluation approach to support experimental design or other in-vehicle technologies.

Eye Tracking Glasses

Simulator

1 version available:

Linguistic Cognitive Load Analysis on Dialogues with an Intelligent Virtual Assistant

Virtual assistants have become fixtures in everyday settings, but most research focuses on their development rather than their use following deployment. To facilitate study of their use in office settings, we introduce OfficeDial, a multimodal dataset containing audio recordings, transcriptions, eye tracking data, and screen recordings from conversations between humans and virtual assistants in office environments. Conversations are paired with physical and behavioral measures of cognitive load. We study the associations between verbal behavior and noise level and reveal key relationships between verbal redundancy, disfluency, and noise level. We make our new dataset available to interested researchers to inspire further exploration.

Eye Tracking Glasses

Software

1 version available:

Look right! The influence of bicycle crossing design on drivers’ approaching behavior

One of the most frequent crashes between cyclists and motor vehicles is the so-called “turning into” accident, where a motor vehicle turns into the main road and collides with a cyclist riding on the main road and crossing the vehicle’s course. Previous studies mainly examined this type of crash and its causes with accident analyses or observational approaches. This study uses a driving simulator to examine the effect of possible countermeasures like the drivers’ expectancy towards crossing cyclists, the view into the junction, and various bicycle crossing designs. N = 66 participants passed T-junctions that differ in the mentioned measures. Gaze and driving data were collected to assess the criticality of each approach. Results indicate that drivers approach marked bicycle crossings at a lower speed than unmarked crossings. Furthermore, crossings with pronounced designs showed more uncritical approaches. However, an alarming percentage of all approaches were critical because drivers showed no appropriate gaze behavior. This was even increased when the view into the junction was limited. The findings suggest that especially the view at junctions must not be obstructed to provide sufficient fields of view. Pronounced bicycle crossing, however, can enhance drivers’ approaching behavior and might help to reduce the frequency of “turning into” accidents.

Simulator

Software

5 versions available

Machine learning based approach for exploring online shopping behavior and preferences with eye tracking

In light of advancements in information technology and the widespread impact of the COVID-19 pandemic, consumer behavior has undergone a significant transformation, shifting from traditional in-store shopping to the realm of online retailing. This shift has notably accelerated the growth of the online retail sector. An essential advantage offered by e-commerce lies in its ability to accumulate and analyze user data, encompassing browsing and purchase histories, through its recommendation systems. Nevertheless, prevailing methodologies predominantly rely on historical user data, which often lack the dynamism required to comprehend immediate user responses and emotional states during online interactions. Recognizing the substantial influence of visual stimuli on human perception, this study leverages eye-tracking technology to investigate online consumer behavior. The research captures the visual engagement of 60 healthy participants while they engage in online shopping, while also taking note of their preferred items for purchase. Subsequently, we apply statistical analysis and machine learning models to unravel the impact of visual complexity, consumer considerations, and preferred items, thereby providing valuable insights for the design of e-commerce platforms. Our findings indicate that the integration of eye-tracking data into e-commerce recommendation systems is conducive to enhancing their performance. Furthermore, machine learning algorithms exhibited remarkable classification capabilities when combined with eye-tracking data. Notably, during the purchase of hedonic products, participants primarily fixated on product images, whereas for utilitarian products, equal attention was dedicated to images, prices, reviews, and sales volume. These insights hold significant potential to augment the effectiveness of e-commerce marketing endeavors.

Eye Tracking Glasses

Software

2 versions available

Machine Learning in Driver Drowsiness Detection: A Focus on HRV, EDA, and Eye Tracking

Drowsy driving continues to be a significant cause of road traffic accidents, necessitating the development of robust drowsiness detection systems. This research enhances our understanding of driver drowsiness by analyzing physiological indicators – heart rate variability (HRV), the percentage of eyelid closure over the pupil over time (PERCLOS), blink rate, blink percentage, and electrodermal activity (EDA) signals. Data was collected from 40 participants in a controlled scenario, with half of the group driving in a non-monotonous scenario and the other half in a monotonous scenario. Participant fatigue was assessed twice using the Fatigue Assessment Scale (FAS).The research developed three machine learning models: HRV-Based Model, EDA-Based Model, and Eye-Based Model, achieving accuracy rates of 98.28%, 96.32%, and 90% respectively. These models were trained on the aforementioned physiological data, and their effectiveness was evaluated against a range of advanced machine learning models including GRU, Transformers, Mogrifier LSTM, Momentum LSTM, Difference Target Propagation, and Decoupled Neural Interfaces Using Synthetic Gradients. The HRV-Based Model and EDA-Based Model demonstrated robust performance in classifying driver drowsiness. However, the Eye-Based Model had some difficulty accurately identifying instances of drowsiness, likely due to the imbalanced dataset and underrepresentation of certain fatigue states. The study duration, which was confined to 45 minutes, could have contributed to this imbalance, suggesting that longer data collection periods might yield more balanced datasets. The average fatigue scores obtained from the FAS before and after the experiment showed a relatively consistent level of reported fatigue among participants, highlighting the potential impact of external factors on fatigue levels. By integrating the outcomes of these individual models, each demonstrating strong performance, this research establishes a comprehensive and robust drowsiness detection system. The HRV-Based Model displayed remarkable accuracy, while the EDA-Based Model and the Eye-Based Model contributed valuable insights despite some limitations. The research highlights the necessity of further optimization, including more balanced data collection and investigation of individual and external factors impacting drowsiness. Despite the challenges, this work significantly contributes to the ongoing efforts to improve road safety by laying the foundation for effective real-time drowsiness detection systems and intervention methods.

Eye Tracking Glasses

Software

1 version available:

Company

Publication Hub

Filter menu

Gaze behavior data in the vitrine of human movement science: considerations on eye-tracking technique

Hand-Eye Behaviour Analytics for Children with Autism Spectrum Disorder

How do drivers allocate visual attention to vulnerable road users when turning at urban intersections?

Hypoxia impairs reaction time but not response accuracy in a visual choice reaction task

Impact of Road Central Greening Configuration on Driver Eye Movements: A Study Based on Real Vehicle Experiments

Improving Driving Automation Training Through Scaffolding of Roles and Responsibilities Information: A Comparison between Older and Younger Drivers

Linguistic Cognitive Load Analysis on Dialogues with an Intelligent Virtual Assistant

Look right! The influence of bicycle crossing design on drivers’ approaching behavior

Machine learning based approach for exploring online shopping behavior and preferences with eye tracking

Machine Learning in Driver Drowsiness Detection: A Focus on HRV, EDA, and Eye Tracking

Explore Cutting-Edge Research in Human Factors and Ergonomics