Improvement of computational rehabilitation support systems based on virtual and augmented reality: clinical similarity and biomechanical movement recognition

Detalhes bibliográficos
Ano de defesa: 2015
Autor(a) principal: GAMA, Alana Elza Fontes da
Orientador(a): TEICHRIEB, Veronica
Banca de defesa: Não Informado pela instituição
Tipo de documento: Tese
Tipo de acesso: Acesso aberto
Idioma: eng
Instituição de defesa: Não Informado pela instituição
Programa de Pós-Graduação: Programa de Pos Graduacao em Ciencia da Computacao
Departamento: Não Informado pela instituição
País: Brasil
Palavras-chave em Português:
Link de acesso: https://repositorio.ufpe.br/handle/123456789/14228
Resumo: Traditionally, the rehabilitation process is a slow and repetitive process which leads to a high evasion rate. Due the growing of interactive technologies such as Virtual Reality (VR) and Augmented Reality (AR) diverse systems are being develop aiming to motivate patient in their exercise. Majority of them interacts using reaching, taking and putting movements for upper limbs in order to reach higher range of motion and equilibrium exercises for lower limbs and trunk. The aim of this work is to improve interactive system for motor rehabilitation applications making them more related to clinical practice. A meeting with physiotherapists was performed to help on the requirements definitions. Among the listed requirements, one of the principal was the possibility to interact with system through movements which are traditionally performed on clinical routine with the flexibility to allow therapist to choose between of them. This thesis proposes a new method of movement recognition which is capable to analyze movement according with biomechanical conventions. The checkpoints method was also developed in order to contemplate the functional movements, which are also used in clinical practice. At this method the movements can be registered by the therapist or patient and then used to control applications. The methods proposed were then integrated in a movement analysis library to allow their uses on different applications. This library provides information such as range of motion and movement quality. It was integrated to a motor rehabilitation system, which we named Ikapp, where the others requirements listed were included. This system made use of the movement recognition in an interactive application to motivate patient during exercise. It was also improved with a configuration file to provide therapist flexibility on choosing movement characteristics such as maximum range of motion and accuracy required during exercise in the application, and also provides a report for further evaluation by therapist. The possibility to guide and correct movement performance is another important requisite. It was allowed by using the movement analysis library which provides information about movement quality and its execution errors. These information could then be used to provide visual feedback. Integrating the movement recognition library with the Ikapp system it was developed two applications, one VR and one AR based system. The reAIRbilitation is a game where the biomechanical or functional movement can control an airplane. Visual and auditory warnings suggesting how to correct the movement are provided. The mirrARbilitation was the AR based application where objects are positioned on the screen to induce movement. They are positioned according to user position and the aimed range of motion. Images and messages demonstrating how to correct the movement are provided. Both systems were tested by patients, physiotherapists and developers from games and interaction area. The use of biomechanical and functional movements as interactive tool presented good response and acceptability by the users. Physiotherapists recognized the therapeutic values of these systems. Guidance benefits was demonstrated by the higher number of correct exercise performance while using the system. It was detected the necessity of improvements on fun aspects and system interface. It is proposed the use of the movement recognition here proposed for developments focusing on game aspects to work on the observed limitations.