Made available in DSpace on 2016-12-12T20:22:52Z (GMT). No. of bitstreams: 1 Eduardo B Viecilli.pdf: 12003318 bytes, checksum: 049902e80d65ca85726715d69e30469a (MD5) Previous issue date: 2014-03-17 / Conselho Nacional de Desenvolvimento Científico e Tecnológico / Mobile robots should be able to seek (explore the environment and recognize the objects) autonomously and efficiently. This work developed a mobile robot capable of performing the search for a 3D object in an unknown environment, using only one depth camera (RGB + Depth) as sensor and executing a strategy of active vision. The Microsoft Kinect was adopted as sensor. Also a mobile robot (XKBO) was build using the Robot Operating System (ROS), and with its architecture adapted from the norm STANAG 4586. A new active exploration strategy was developed in which considers the effort of the robot to move to the frontier regions (occult areas), and the presence of traces of the object. The metrics used demonstrated that the use of depth cameras for visual search tasks have a potential for deployment because associates visual and depth information, allowing the robot to better understand the environment and the target object of the search. / Robôs móveis devem ter a capacidade de buscar (explorar o ambiente e reconhecer objetos) de forma autônoma e eficiente. Este trabalho desenvolveu um robô móvel capaz de executar a busca a um objeto (3D) em ambiente desconhecido, utilizando somente uma câmera de profundidade (RGB + distancia) como sensor e executando uma estratégia de visão ativa. A Microsoft Kinect foi a câmera adotada. Também construiu-se um robô móvel (XKBO) que utiliza o Sistema Operacional Robótico (ROS), e com a arquitetura adaptada da norma STANAG 4586. Foi possível usar algoritmos existentes para reconhecer objetos 3D usando o Kinect graças as ferramentas presentes no ROS. E o uso do Kinect facilitou a geração de mapas do ambiente. Desenvolveu-se uma nova estratégia de exploração ativa que considera o esforço de movimentação para as regiões de fronteiras (áreas ocultas), e a existência de indícios da presença do objeto. As métricas utilizadas demonstram que o uso de câmeras de profundidade para tarefas de busca tem potencial para evolução por associar informação visuais com as de profundidade, permitindo que o robô possa entender o ambiente e o objeto alvo da busca. Palavras-chave: Robô Móvel. Exploração. Busca Visual. Câmera RGB-D.

O aumento da população senescente no Brasil e no mundo implica ações específicas para satisfazer às necessidades e preferências do público idoso. Diversas áreas do conhecimento dedicam-se aos estudos relacionados ao envelhecimento humano com a finalidade de garantir a autonomia, independência, qualidade de vida e expectativa de vida saudável das pessoas com mais de 60 anos. Nesse contexto, novas tecnologias de intervenção baseadas nos jogos digitais têm sido utilizadas para promover a prá-tica de atividade física com o propósito de prevenir o declínio funcional em indivíduos idosos. Sendo assim, o objetivo desta pesquisa consiste em estabelecer um conjunto de requisitos de projeto para apoiar o desenvolvimento de jogos digitais que utilizam a interface natural, a partir da perspectiva dos usuários idosos caidores, a fim de contribuir para a melhora na qualidade de vida. Para tanto, realizou-se uma intervenção no projeto de extensão do Centro de Estudos de Lazer e Atividade Física do Idoso (Celari) da Escola de Educação Física (ESEF) da Universidade Federal do Rio Grande do Sul (UFRGS), em um período de oito semanas, com duas sessões semanais. Os instrumentos de avaliação aplicados na pesquisa foram dois questionários, incluindo questões fechadas, com delineamento pré e pós-intervenção. Além disso, utilizou-se a observação direta com o intuito de recolher informações acerca da amostra. O instrumento de intervenção adotado na pesquisa foi o console Xbox One® com o sensor de movimento Kinect 2.0® e sete jogos digitais. Estabeleceram-se, então, os requisitos de usuá-rios com base nas necessidades e preferências exigidos pelos participantes da pesquisa durante a inter-venção. Em uma etapa posterior, empregou-se o método do Desdobramento da Função Qualidade (QFD) para converter os requisitos de usuários em um conjunto de requisitos de projeto sistematizados de acordo com grau de importância atribuído pelos usuários. Com isso, pretendeu-se oferecer um con-junto de requisitos de projeto para, eventualmente, orientar o desenvolvimento de um jogo digital uti-lizando a interface natural, com vistas a melhorar a qualidade de vida, o equilíbrio e reduzir o risco de quedas das pessoas idosas. / The increase in the elderly population in Brazil and in the world implies specific actions to meet the needs and preferences of the elderly. Several areas of knowledge are involved with studies related to human aging in order to ensure autonomy, independence, life quality and healthy life expectancy of people over 60 years of age. In this context, new digital game-based intervention technologies have been used to promote the practice of physical activity aiming at preventing functional decline in the elderly. Thus, this research aims to establish a set of project requirements to support the development of digital games using the natural user interface from the perspective of elderly faller users in order to contribute for the improvement in life quality. Therefore, an intervention was accomplished in the extension project of the Center of Studies of Leisure and Physical Activity for the Elderly (Celari) from the School of Physical Education (ESEF), Federal University of Rio Grande do Sul (UFRGS), during a period of eight weeks, two sessions/week. The assessment tools used in the research were two questionnaires, with closed questions, pre- and post- test design. In addition, it was also used the direct observation in order to gather information about the sample. The intervention tool adopted in the research was the Xbox One® console with Kinect 2.0® motion sensor and seven digital games. Then, it was established the user’s requirements based on the needs and preferences required by the participants of the research during the intervention. At a later stage, it was used the Quality Function Deployment (QFD) method to convert the user requirements into a set of project requirements system-atized according to the degree of importance assigned by the users. Thus, it was intended to offer a set of requirements for the project in order to, possibly, orientate the development of a digital game using the natural user interface, aiming to improve the elderly’s life quality, balance as well as decrease their risk of falls.

O aumento da população senescente no Brasil e no mundo implica ações específicas para satisfazer às necessidades e preferências do público idoso. Diversas áreas do conhecimento dedicam-se aos estudos relacionados ao envelhecimento humano com a finalidade de garantir a autonomia, independência, qualidade de vida e expectativa de vida saudável das pessoas com mais de 60 anos. Nesse contexto, novas tecnologias de intervenção baseadas nos jogos digitais têm sido utilizadas para promover a prá-tica de atividade física com o propósito de prevenir o declínio funcional em indivíduos idosos. Sendo assim, o objetivo desta pesquisa consiste em estabelecer um conjunto de requisitos de projeto para apoiar o desenvolvimento de jogos digitais que utilizam a interface natural, a partir da perspectiva dos usuários idosos caidores, a fim de contribuir para a melhora na qualidade de vida. Para tanto, realizou-se uma intervenção no projeto de extensão do Centro de Estudos de Lazer e Atividade Física do Idoso (Celari) da Escola de Educação Física (ESEF) da Universidade Federal do Rio Grande do Sul (UFRGS), em um período de oito semanas, com duas sessões semanais. Os instrumentos de avaliação aplicados na pesquisa foram dois questionários, incluindo questões fechadas, com delineamento pré e pós-intervenção. Além disso, utilizou-se a observação direta com o intuito de recolher informações acerca da amostra. O instrumento de intervenção adotado na pesquisa foi o console Xbox One® com o sensor de movimento Kinect 2.0® e sete jogos digitais. Estabeleceram-se, então, os requisitos de usuá-rios com base nas necessidades e preferências exigidos pelos participantes da pesquisa durante a inter-venção. Em uma etapa posterior, empregou-se o método do Desdobramento da Função Qualidade (QFD) para converter os requisitos de usuários em um conjunto de requisitos de projeto sistematizados de acordo com grau de importância atribuído pelos usuários. Com isso, pretendeu-se oferecer um con-junto de requisitos de projeto para, eventualmente, orientar o desenvolvimento de um jogo digital uti-lizando a interface natural, com vistas a melhorar a qualidade de vida, o equilíbrio e reduzir o risco de quedas das pessoas idosas. / The increase in the elderly population in Brazil and in the world implies specific actions to meet the needs and preferences of the elderly. Several areas of knowledge are involved with studies related to human aging in order to ensure autonomy, independence, life quality and healthy life expectancy of people over 60 years of age. In this context, new digital game-based intervention technologies have been used to promote the practice of physical activity aiming at preventing functional decline in the elderly. Thus, this research aims to establish a set of project requirements to support the development of digital games using the natural user interface from the perspective of elderly faller users in order to contribute for the improvement in life quality. Therefore, an intervention was accomplished in the extension project of the Center of Studies of Leisure and Physical Activity for the Elderly (Celari) from the School of Physical Education (ESEF), Federal University of Rio Grande do Sul (UFRGS), during a period of eight weeks, two sessions/week. The assessment tools used in the research were two questionnaires, with closed questions, pre- and post- test design. In addition, it was also used the direct observation in order to gather information about the sample. The intervention tool adopted in the research was the Xbox One® console with Kinect 2.0® motion sensor and seven digital games. Then, it was established the user’s requirements based on the needs and preferences required by the participants of the research during the intervention. At a later stage, it was used the Quality Function Deployment (QFD) method to convert the user requirements into a set of project requirements system-atized according to the degree of importance assigned by the users. Thus, it was intended to offer a set of requirements for the project in order to, possibly, orientate the development of a digital game using the natural user interface, aiming to improve the elderly’s life quality, balance as well as decrease their risk of falls.

Submitted by VANIA CRISTINA DOS REIS MIRANDA null (vcrmiranda@yahoo.com.br) on 2016-09-05T15:39:47Z No. of bitstreams: 1 Tese Vania C R Miranda final.pdf: 2140103 bytes, checksum: 48748fd5e35442843be98efc330ce9ac (MD5) / Approved for entry into archive by Juliano Benedito Ferreira (julianoferreira@reitoria.unesp.br) on 2016-09-08T19:34:16Z (GMT) No. of bitstreams: 1 miranda_vcr_dr_guara.pdf: 2140103 bytes, checksum: 48748fd5e35442843be98efc330ce9ac (MD5) / Made available in DSpace on 2016-09-08T19:34:16Z (GMT). No. of bitstreams: 1 miranda_vcr_dr_guara.pdf: 2140103 bytes, checksum: 48748fd5e35442843be98efc330ce9ac (MD5) Previous issue date: 2016-07-12 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / A avaliação do controle postural é importante para o diagnóstico e monitoramento dos distúrbios de equilíbrio observados em várias situações e grupos populacionais, como os idosos, pelas consequentes quedas, que causam grande impacto na vida social desta população. Embora existam inúmeras ferramentas qualitativas e quantitativas para esta avaliação, é possível observar algumas limitações como a subjetividade de alguns testes, a complexidade dos equipamentos e divergência no uso de alguns instrumentos, tais como a espuma. Dentro deste contexto, os objetivos deste estudo foram desenvolver uma plataforma de força com molas para a avaliação do controle postural e verificar se as molas propostas são capazes de gerar instabilidade suficiente para esta avaliação em dois grupos, de adultos jovens e idosos, ambos saudáveis, a partir dos parâmetros do centro de pressão, e também verificar se o Kinect da Microsoft® é capaz de captar as oscilações do centro de massa de jovens adultos sobre a plataforma instável. Essa plataforma de força instável com molas foi elaborada para avaliar os parâmetros relacionados ao centro de pressão (CoP) e posteriormente 12 adultos jovens e 12 idosos saudáveis foram avaliados sob as condições com olhos abertos (OA) e olhos fechados (OF) sobre plataforma de força estável e instável. Uma outra plataforma com molas foi construída no Laboratório GSCOP (INP Grenoble – França) com o intuito de avaliar o controle postural de 20 adultos jovens saudáveis, associado aos dados provenientes do Kinect. Foi observado que no grupo de adultos jovens houve uma maior oscilação média na direção antero-posterior (AP) do CoP na plataforma instável, principalmente com olhos abertos, assim como um aumento na área de oscilação total do CoP. Para os idosos esse aumento ocorreu nos parâmetros de oscilação média na direção AP e médio lateral (ML) nas condições de olhos abertos e fechados, e a área de oscilação também aumentou na condição com olhos fechados. Os resultados com o Kinect ressaltaram um aumento significativo somente da oscilação AP do centro de massa (CM) sobre a plataforma instável com olhos fechados. A plataforma com molas foi capaz de gerar instabilidade suficiente para avaliar o controle postural e pode ser útil para identificar risco de quedas. O Kinect foi capaz de detectar maior oscilação do CM em situações mais desafiadoras. Porém são necessários mais estudos para investigar o efeito de mola no controle postural. / The assessment of postural control is important for the diagnosis and monitoring of balance disorders observed in several situations and population groups such as the elderly, by the consequent falls which cause great impact on the social life of this population. Although there are numerous qualitative and quantitative tools for this evaluation, it is possible to observe some limitations as the subjectivity of some tests, the complexity of the equipment and divergence in the use of some instruments, such as the foam. Within this context, the objectives of this study were to develop a force platform with springs for assessment of postural control and verify if the proposed springs are able to generate sufficient instability for this evaluation in two groups, young adults and older, both healthy, from the center of pressure parameters, and also to check if the Microsoft Kinect is able to capture the center of mass movements of young adults on the unstable platform. This unstable force plate with springs was developed to evaluate the parameters of center of pressure (CoP) and 12 healthy young adults and 12 healthy elderly were evaluated under the conditions with opened eyes (OE) and closed eyes (CE) on stable and unstable force platform. Another platform with springs was built in Laboratory GSCOP (INP Grenoble - France) to assess postural control of 20 younger adults, with data center of mass from the Kinect. It was observed that in young adults group had a average oscilation of anteroposterior (AP) displacement significant increase on the platform unstable, especially with opened eyes and an increase in the oscillation area. For elderly this significant increase occurred in the parameters oscillation’s CoP AP and medial-lateral (ML) CoP displacement in the conditions of opened and closed eyes, the oscillation’s area also increased with closed eyes. The results with Kinect highlighted a significant increase only oscillation’s AP of the center of mass (CM) over unstable force platform with closed eyes. The platform with springs was able to generate enough instability to assess postural control and can be useful for identifying falls risk. Kinect was able to detect greater CM sway in more challenging situations. But more studies are required to investigate the spring effect on postural control.

O aumento da população senescente no Brasil e no mundo implica ações específicas para satisfazer às necessidades e preferências do público idoso. Diversas áreas do conhecimento dedicam-se aos estudos relacionados ao envelhecimento humano com a finalidade de garantir a autonomia, independência, qualidade de vida e expectativa de vida saudável das pessoas com mais de 60 anos. Nesse contexto, novas tecnologias de intervenção baseadas nos jogos digitais têm sido utilizadas para promover a prá-tica de atividade física com o propósito de prevenir o declínio funcional em indivíduos idosos. Sendo assim, o objetivo desta pesquisa consiste em estabelecer um conjunto de requisitos de projeto para apoiar o desenvolvimento de jogos digitais que utilizam a interface natural, a partir da perspectiva dos usuários idosos caidores, a fim de contribuir para a melhora na qualidade de vida. Para tanto, realizou-se uma intervenção no projeto de extensão do Centro de Estudos de Lazer e Atividade Física do Idoso (Celari) da Escola de Educação Física (ESEF) da Universidade Federal do Rio Grande do Sul (UFRGS), em um período de oito semanas, com duas sessões semanais. Os instrumentos de avaliação aplicados na pesquisa foram dois questionários, incluindo questões fechadas, com delineamento pré e pós-intervenção. Além disso, utilizou-se a observação direta com o intuito de recolher informações acerca da amostra. O instrumento de intervenção adotado na pesquisa foi o console Xbox One® com o sensor de movimento Kinect 2.0® e sete jogos digitais. Estabeleceram-se, então, os requisitos de usuá-rios com base nas necessidades e preferências exigidos pelos participantes da pesquisa durante a inter-venção. Em uma etapa posterior, empregou-se o método do Desdobramento da Função Qualidade (QFD) para converter os requisitos de usuários em um conjunto de requisitos de projeto sistematizados de acordo com grau de importância atribuído pelos usuários. Com isso, pretendeu-se oferecer um con-junto de requisitos de projeto para, eventualmente, orientar o desenvolvimento de um jogo digital uti-lizando a interface natural, com vistas a melhorar a qualidade de vida, o equilíbrio e reduzir o risco de quedas das pessoas idosas. / The increase in the elderly population in Brazil and in the world implies specific actions to meet the needs and preferences of the elderly. Several areas of knowledge are involved with studies related to human aging in order to ensure autonomy, independence, life quality and healthy life expectancy of people over 60 years of age. In this context, new digital game-based intervention technologies have been used to promote the practice of physical activity aiming at preventing functional decline in the elderly. Thus, this research aims to establish a set of project requirements to support the development of digital games using the natural user interface from the perspective of elderly faller users in order to contribute for the improvement in life quality. Therefore, an intervention was accomplished in the extension project of the Center of Studies of Leisure and Physical Activity for the Elderly (Celari) from the School of Physical Education (ESEF), Federal University of Rio Grande do Sul (UFRGS), during a period of eight weeks, two sessions/week. The assessment tools used in the research were two questionnaires, with closed questions, pre- and post- test design. In addition, it was also used the direct observation in order to gather information about the sample. The intervention tool adopted in the research was the Xbox One® console with Kinect 2.0® motion sensor and seven digital games. Then, it was established the user’s requirements based on the needs and preferences required by the participants of the research during the intervention. At a later stage, it was used the Quality Function Deployment (QFD) method to convert the user requirements into a set of project requirements system-atized according to the degree of importance assigned by the users. Thus, it was intended to offer a set of requirements for the project in order to, possibly, orientate the development of a digital game using the natural user interface, aiming to improve the elderly’s life quality, balance as well as decrease their risk of falls.

The success of recognizing periodic actions in single-person-simple-background datasets, such as Weizmann and KTH, has created a need for more complex datasets to push the performance of action recognition systems. In this work, we create a new synthetic action dataset and use it to highlight weaknesses in current recognition systems. Experiments show that introducing background complexity to action video sequences causes a significant degradation in recognition performance. Moreover, this degradation cannot be fixed by fine-tuning system parameters or by selecting better feature points. Instead, we show that the problem lies in the spatio-temporal cuboid volume extracted from the interest point locations. Having identified the problem, we show how improved results can be achieved by simple modifications to the cuboids. For the above method however, one requires near-perfect localization of the action within a video sequence. To achieve this objective, we present a two stage weakly supervised probabilistic model for simultaneous localization and recognition of actions in videos. Different from previous approaches, our method is novel in that it (1) eliminates the need for manual annotations for the training procedure and (2) does not require any human detection or tracking in the classification stage. The first stage of our framework is a probabilistic action localization model which extracts the most promising sub-windows in a video sequence where an action can take place. We use a non-linear classifier in the second stage of our framework for the final classification task. We show the effectiveness of our proposed model on two well known real-world datasets: UCF Sports and UCF11 datasets. iii Another application of the weakly supervised probablistic model proposed above is in the gaming environment. An important aspect in designing interactive, action-based interfaces is reliably recognizing actions with minimal latency. High latency causes the system’s feedback to lag behind and thus significantly degrade the interactivity of the user experience. With slight modification to the weakly supervised probablistic model we proposed for action localization, we show how it can be used for reducing latency when recognizing actions in Human Computer Interaction (HCI) environments. This latency-aware learning formulation trains a logistic regression-based classifier that automatically determines distinctive canonical poses from the data and uses these to robustly recognize actions in the presence of ambiguous poses. We introduce a novel (publicly released) dataset for the purpose of our experiments. Comparisons of our method against both a Bag of Words and a Conditional Random Field (CRF) classifier show improved recognition performance for both pre-segmented and online classification tasks.

Face recognition and lip localization are two main building blocks in the development of audio visual automatic speech recognition systems (AV-ASR). In many earlier works, face recognition and lip localization were conducted in uniform lighting conditions with simple backgrounds. However, such conditions are seldom the case in real world applications. In this paper, we present an approach to face recognition and lip localization that is invariant to lighting conditions. This is done by employing infrared and depth images captured by the Kinect V2 device. First we present the use of infrared images for face detection. Second, we use the face’s inherent depth information to reduce the search area for the lips by developing a nose point detection. Third, we further reduce the search area by using a depth segmentation algorithm to separate the face from its background. Finally, with the reduced search range, we present a method for lip localization based on depth gradients. Experimental results demonstrated an accuracy of 100% for face detection, and 96% for lip localization.

This master thesis is engaged in development of software tool intended for measuring of status of lower limb bones. It analyzes status of the feet and lower limb and defines significantpointsonthem.Alsoanalyzesdesignoptionsofmeasuringsceneandmarkers and describe the one selected. In another part is described automated point recognition algorithm. The last part describes graphical user interface, where are these algorithms implemented.

Today, movement measurements are made manually in healthcare using a goniometer. The measurements are often time-consuming and specially trained practitioners are needed, furthermore the readings are dependent on the practitioner's eye measurements. New technology has been introduced to make the same measurements using external sensors which have the disadvantage that they can be costly and space consuming. Recently, depth camera technology has introduced an alternative solution to make it more efficient for both patients and practitioners. The purpose of this study is to investigate whether Apple depth camera technology can replace current technology by being able to perform motion measurements with only one Ipad/Iphone with a built-in depth camera. For this, a prototype has been developed to be able to automatically calculate medically relevant angles by filming a person. Various motion measurements have been performed and the measurement results have been analysed. Apple depth camera has high precision in the measured values. However, a larger study needs to be performed in order to be able to determine whether Apple's depth camera could replace current technology. / Idag görs rörelsemätningar manuellt i vården med hjälp av en goniometer. Mätningarna är ofta tidskrävande och kräver utbildade utövare samt är beroende av utövarens ögonmått. Det har introducerats ny teknik för att göra samma mätningar med hjälp av externa sensorer, vilket har nackdelen att de kan vara kostsamma och utrymmeskrävande. På senare tid har djupkameratekniken introducerats som en alternativ lösning för att effektivisera för både patienter och vårdpersonal. Syftet med den här studien är att undersöka om Apples djupkamerateknik kan ersätta nuvarande teknik genom att kunna utföra rörelsemätningar med endast en Ipad/Iphone med inbyggd djupkamera. För detta har en prototyp utvecklats för att automatiskt kunna beräkna medicinskt relevanta vinklar genom att filma en person. Olika rörelsemätningar har sedan utförts och mätresultaten har analyserats. Resultaten av analysen visar att Apples djupkamera har hög precision i mätvärdena. Dock behöver en större undersökning utföras för att kunna konstatera om Apples djupkamera helt skulle kunna ersätta nuvarande teknik.

Idag görs rörelsemätningar manuellt i vården med hjälp av en goniometer. Mätningarna är ofta tidskrävande och kräver utbildade utövare samt är beroende av utövarens ögonmått. Det har introducerats ny teknik för att göra samma mätningar med hjälp av externa sensorer, vilket har nackdelen att de kan vara kostsamma och utrymmeskrävande. På senare tid har djupkameratekniken introducerats som en alternativ lösning för att effektivisera för både patienter och vårdpersonal. Syftet med den här studien är att undersöka om Apples djupkamerateknik kan ersätta nuvarande teknik genom att kunna utföra rörelsemätningar med endast en Ipad/Iphone med inbyggd djupkamera. För detta har en prototyp utvecklats för att automatiskt kunna beräkna medicinskt relevanta vinklar genom att filma en person. Olika rörelsemätningar har sedan utförts och mätresultaten har analyserats. Resultaten av analysen visar att Apples djupkamera har hög precision i mätvärdena. Dock behöver en större undersökning utföras för att kunna konstatera om Apples djupkamera helt skulle kunna ersätta nuvarande teknik. / Today, movement measurements are made manually in healthcare using a goniometer. The measurements are often time-consuming and specially trained practitioners are needed, furthermore the readings are dependent on the practitioner's eye measurements. New technology has been introduced to make the same measurements using external sensors which have the disadvantage that they can be costly and space consuming. Recently, depth camera technology has introduced an alternative solution to make it more efficient for both patients and practitioners. The purpose of this study is to investigate whether Apple depth camera technology can replace current technology by being able to perform motion measurements with only one Ipad/Iphone with a built-in depth camera. For this, a prototype has been developed to be able to automatically calculate medically relevant angles by filming a person. Various motion measurements have been performed and the measurement results have been analysed. Apple depth camera has high precision in the measured values. However, a larger study needs to be performed in order to be able to determine whether Apple's depth camera could replace current technology.