Framework para o desenvolvimento e integração de aplicações de realidade virtual, realidade aumentada e multimédia

Os ambientes virtuais têm sido cada vez mais utilizados nas mais diferentes áreas, quer na medicina, engenharia civil ou até mesmo em áreas terapêuticas. Devido à sua emergente utilização foi estabelecido em parceria com o Museu da Baleia, através de várias reuniões, que seria viável a modelação de cenários virtuais, onde se desenvolvessem animações, com o intuito de que representassem o ciclo de vida das baleias cachalotes. Esta escolha foi efectuada de forma a envolver várias temáticas relacionadas com as baleias cachalotes, desde a migração, os problemas relacionados com o lixo no fundo do mar, etc. De seguida, foi construída uma Framework para incorporação destas animações (vídeos) e realização de actividades utilizando diferentes tipos de médias, Realidade Virtual e Realidade Aumentada, tornando desta forma as actividades mais interactivas, estimulantes e atractivas. Para a execução destas etapas do projecto foi decidido utilizar a ferramenta 3ds Max para a modelação dos objectos que iriam compor os cenários virtuais, bem como a sua animação. Para a implementação da Framework foi decidido utilizar o Adobe Flash visto ser uma ferramenta que permite a incorporação de diferentes tipos de médias, de Realidade Virtual, Realidade Aumentada e possibilita a construção de uma interface simples e atractiva. Esta Framework foi desenvolvida para que no futuro seja possível ser modificada, isto é, para que seja capaz de efectuar a incorporação de outros tipos de conteúdos, assim como a edição dos que já estão implementados.

Integrating eye tracking in virtual reality for stroke rehabilitation

This thesis reports on research done for the integration of eye tracking technology into virtual reality environments, with the goal of using it in rehabilitation of patients who suffered from stroke. For the last few years, eye tracking has been a focus on medical research, used as an assistive tool  to help people with disabilities interact with new technologies  and as an assessment tool  to track the eye gaze during computer interactions. However, tracking more complex gaze behaviors and relating them to motor deficits in people with disabilities is an area that has not been fully explored, therefore it became the focal point of this research. During the research, two exploratory studies were performed in which eye tracking technology was integrated in the context of a newly created virtual reality task to assess the impact of stroke. Using an eye tracking device and a custom virtual task, the system developed is able to monitor the eye gaze pattern changes over time in patients with stroke, as well as allowing their eye gaze to function as an input for the task. Based on neuroscientific hypotheses of upper limb motor control, the studies aimed at verifying the differences in gaze patterns during the observation and execution of the virtual goal-oriented task in stroke patients (N=10), and also to assess normal gaze behavior in healthy participants (N=20). Results were found consistent and supported the hypotheses formulated, showing that eye gaze could be used as a valid assessment tool on these patients. However, the findings of this first exploratory approach are limited in order to fully understand the effect of stroke on eye gaze behavior. Therefore, a novel model-driven paradigm is proposed to further understand the relation between the neuronal mechanisms underlying goal-oriented actions and eye gaze behavior.

3D reconstruction through photographs

Humans can perceive three dimension, our world is three dimensional and it is becoming increasingly digital too. We have the need to capture and preserve our existence in digital means perhaps due to our own mortality. We have also the need to reproduce objects or create small identical objects to prototype, test or study them. Some objects have been lost through time and are only accessible through old photographs. With robust model generation from photographs we can use one of the biggest human data sets and reproduce real world objects digitally and physically with printers. What is the current state of development in three dimensional reconstruction through photographs both in the commercial world and in the open source world? And what tools are available for a developer to build his own reconstruction software? To answer these questions several pieces of software were tested, from full commercial software packages to open source small projects, including libraries aimed at computer vision. To bring to the real world the 3D models a 3D printer was built, tested and analyzed, its problems and weaknesses evaluated. Lastly using a computer vision library a small software with limited capabilities was developed.