The current push from the industry for Head-Mounted Display based wearable computers to the masses for everyday use suggests that academia's goals of a tight human and computer integration is achievable. Although promising, many interaction challenges remain to achieve a deep integration. Primarily that of active cognitive support in the form of focusing user attention. This thesis investigates to what degree a system can unobtrusively, perhaps even subliminally, guide attention of a user by directing their gaze from a current point to a selected point in a virtual environment. A subjective evaluation is made regarding the characteristics of visual sensory stimuli in order to possibly achieve an unobtrusive (or even subliminal) gaze guidance. The attention guidance system developed is deployed in a controlled experiment with 30 participants. Participants are asked to fire a longbow at targets in a virtual reality environment while their point of gaze is monitored with an eye-tracker. The experiment produced interesting results, but no conclusive evidence that the system was able actively guide a user's attention nor influence their choice could be observed. The conclusion of this thesis is that further development is needed towards a system that is capable of objectively calibrating the stimuli characteristics for each individual participant.

The main topic of this thesis are map skills, and the key point of interest are strategies used for map analysis. General reference map was found as a suitable map given its frequent use in the school atlases. The main goal of this study is evaluation of the general reference map analysis strategies in terms of their dimensions, i. e. their repertoire, distribution, efficiency, and adaptability. 20 upper secondary school students participated in an eye-tracking experiment that consisted of the test and the follow-up questionnaire. The eye-tracking data were analyzed qualitatively and quantitatively to obtain information about the strategy dimensions. Results showed that students used broad repertoire of strategies when analyzing the general reference map and they pointed to the most chosen strategies as well. In some cases, students used more than one strategy to solve the task and thus the most frequent strategy combinations were detected. The efficiency of strategies was evaluated based on the students' success rate and the length of the solving cycle which was affected by the type of elements, respectively map content, used for solving the task. The ability to adapt to specific task demand was proven by addition of elements needed into the strategy or using entirely different strategy type. The...

Eye tracking has a number of useful applications ranging from monitoring a vehicle driver for possible signs of fatigue, providing an interface to enable severely disabled people to communicate with others, to a number of medical applications. Most eye tracking applications require a non-intrusive way of tracking the eyes, making a camera-based approach a natural choice. However, although significant progress has been made in recent years, modern eye tracking systems still have not overcome a number of challenges including eye occlusions, variable ambient lighting conditions and inter-subject variability. This thesis describes the complete design and implementation of a real-time camera-based eye tracker, which was developed mainly for indoor applications. The developed eye tracker relies on the so-called bright/dark pupil effect for both the eye detection and eye tracking phases. The bright/dark pupil effect was realised by the development of specialised hardware and near-infrared illumination, which were interfaced with a machine vision camera. For the eye detection phase the performance of three different types of classifiers, namely neurals networks, SVMs and AdaBoost were directly compared with each other on a dataset consisting of 17 individual subjects from different ethnic backgrounds. For the actual tracking of the eyes, a Kalman filter was combined with the mean-shift tracking algorithm. A PC application with a graphical user interface (GUI) was also developed to integrate the various aspects of the eye tracking system, which allows the user to easily configure and use the system. Experimental results have shown the eye detection phase to be very robust, whereas the eye tracking phase was also able to accurately track the eyes from frame-to-frame in real-time, given a few constraints. AFRIKAANS : Oogvolging het ’n beduidende aantal toepassings wat wissel van die deteksie van bestuurderuitputting, die voorsiening van ’n rekenaarintervlak vir ernstige fisies gestremde mense, tot ’n groot aantal mediese toepassings. Die meeste toepassings van oogvolging vereis ’n nie-indringende manier om die oë te volg, wat ’n kamera-gebaseerde benadering ’n natuurlike keuse maak. Alhoewel daar alreeds aansienlike vordering gemaak is in die afgelope jare, het moderne oogvolgingstelsels egter nogsteeds verskeie uitdagings nie oorkom nie, insluitende oog okklusies, veranderlike beligtingsomstandighede en variansies tussen gebruikers. Die verhandeling beskryf die volledige ontwerp en implementering van ’n kamera-gebaseerde oogvolgingsstelsel wat in reële tyd werk. Die ontwikkeling van die oogvolgingsstelsel maak staat op die sogenaamde helder/donker pupil effek vir beide die oogdeteksie en oogvolging fases. Die helder/donker pupil effek was moontlik gemaak deur die ontwikkeling van gespesialiseerde hardeware en naby-infrarooi illuminasie. Vir die oogdeteksie fase was die akkuraatheid van drie verskillende tipes klassifiseerders getoets en direk vergelyk, insluitende neurale netwerke, SVMs en AdaBoost. Die datastel waarmee die klassifiseerders getoets was, het bestaan uit 17 individuele toetskandidate van verskillende etniese groepe. Vir die oogvolgings fase was ’n Kalman filter gekombineer met die gemiddelde-verskuiwings algoritme. ’n Rekenaar program met ’n grafiese gebruikersintervlak was ontwikkel vir ’n persoonlike rekenaar, sodat al die verskillende aspekte van die oogvolgingsstelsel met gemak opgestel kon word. Eksperimentele resultate het getoon dat die oogdeteksie fase uiters akkuraat en robuust was, terwyl die oogvolgings fase ook hoogs akuraat die oë gevolg het, binne sekere beperkinge. Copyright / Dissertation (MEng)--University of Pretoria, 2011. / Electrical, Electronic and Computer Engineering / unrestricted

In recent years, eye-tracking technology has gained considerable attention, facilitating analysis of gaze behavior and human visual attention. However, eye-tracking analysis often requires manual annotation on the objects being gazed upon, making quantitative data analysis a difficult and time-consuming process. This thesis explores the area of object detection and object tracking applied on scene camera footage from mobile eye-tracking glasses. We have evaluated the performance of state-of-the-art object detectors and trackers, resulting in an automated pipeline specialized at detecting and tracking objects in scene videos. Motion blur constitutes a significant challenge in moving cameras, complicating tasks such as object detection and tracking. To address this, we explored two approaches. The first involved retraining object detection models on datasets with augmented motion-blurred images, while the second one involved preprocessing the video frames with deblurring techniques. The findings of our research contributes with insights into efficient approaches to optimally detect and track objects in scene camera footage from eye-tracking glasses. Out of the technologies we tested, we found that motion deblurring using DeblurGAN-v2, along with a DINO object detector combined with the StrongSORT tracker, achieved the highest accuracies. Furthermore, we present an annotated dataset consisting of frames from recordings with eye-tracking glasses, that can be utilized for evaluating object detection and tracking performance.

No description available.

As a result of improved hardware, Virtual Reality (VR) has made a return to the digital entertainment market. The tools to create VR applications are now readily available and numerous developers are attempting to create engaging experiences. Concurrently, eye tracking technology is increasingly implemented in VR hardware, enabling better immersion and analytics. Due to its recent popularization, few tools for analyzing VR experiences exist. As such, this study aimed to find a method for collecting and visualizing eye tracking data to that end. A case study was conducted to answer these questions, wherein software for collecting, saving, and visualizing gaze data was constructed. A user test to assess the program's accuracy and viability followed. The study found a performance friendly way to get and save data using software provided by the hardware manufacturers, and resulted in a system for visualization in which the user's gaze is played back. The user test confirmed the system's accuracy, and identified possible behavioral patterns, suggesting the software can be used for analysis. The study provides a base for further research. / Som en följd av den senare tidens hårdvaruutveckling har Virtual Reality (VR) återvänt till den digitala underhållningsmarknaden. Verktygen för att skapa VRapplikationer är numera tillgängliga för alla, och många utvecklare har gett sig i kast med att skapa engagerande upplevelser för mediet. Samtidigt används ögonspårande teknologi inom VR i ökande utsträckning, vilket möjliggör bättre inlevelse samt analytiska möjligheter. I egenskap av sin nyvunna popularitet finns få verktyg och metoder för att analyzera VR-upplevelser. Därför ämnar denna studie samla och visualisera data från ögonspårande hårdvara i det syftet. En fallstudie genomfördes för att svara på hur detta kan göras, i vilken mjukvara för att samla, spara, och visa ögondata skapades. Ett användartest för att bedöma programmets träffsäkerhet och användbarhet följde. Studien hittade ett prestandavänligt sätt att samla och spara datan, och resulterade i ett visualiseringssystem som återspelar användarens blick. Användartestet bekräftade systemets precision, och identifierade möjliga beteendemönster, vilket antyder att mjukvaran kan användas för analys. Studien lägger en grund för vidare forskning.

No description available.

No description available.

No description available.

No description available.