No description available.

Interactive collaborative enviroments are solved by many companies and research teams. This thesis is focused on design and development of own system for gesture recognition based on Microsoft Kinect controller. The system is focused on collaboration of multiple users. Therefore, proposed solution can distinguish interactions of different users. The result allows to create an interactive area from a common wall using a computer, projector and Kinect controller.

Health is one of the most important elements in every individual’s life. Even though there is much advancement in science, the quality of healthcare has never been up to the mark. This appears to be true especially in the field of Physiotherapy. Physiotherapy is the analysis of human joints and bodies and providing remedies for any pains or injuries that might have affected the physiology of a body. To give patients a top notch quality health analysis and treatment, either the number of doctors should increase, or there should be an alternative replacement for a doctor. Our Master Thesis is aimed at developing a prototype which can aid in providing healthcare of high standards to the millions.  Methods: Microsoft Kinect SDK 2.0 is used to develop the prototype. The study shows that Kinect can be used both as Marker-based and Marker less systems for tracking human motion. The degree angles formed from the motion of five joints namely shoulder, elbow, hip, knee and ankle were calculated. The device has infrared, depth and colour sensors in it. Depth data is used to identify the parts of the human body using pixel intensity information and the located parts are mapped onto RGB colour frame.  The image resulting from the Kinect skeleton mode was considered as the images resulting from the markerless system and used to calculate the angle of the same joints. In this project, data generated from the movement tracking algorithm for Posture Side and Deep Squat Side movements are collected and stored for further evaluation.  Results: Based on the data collected, our system automatically evaluates the quality of movement performed by the user. The system detected problems in static posture and Deep squat based on the feedback on our system by Physiotherapist.

This master thesis deals with the design and implementation of an application used for spatial data processing. The first part provides an overview of different augmented reality projects focused on manipulation with spatial data. It also contains review of computer vision libraries. In the methodology, description of all project components is provided. The following part describes in detail the design and implementation of mentioned application for spatial data processing. The proposed implementation is verified on scenario of spatial turn-based game

In pursuit of creating a fully automated navigation system that is capable of operating in dynamic environments, a large amount of research is being devoted to systems that use visual odometry assisted methods to estimate the position of a platform with regards to the environment surrounding it. This includes systems that do and do not know the environment a priori, as both rely on the same methods for localisation. For the combined problem of localisation and mapping, Simultaneous Localisation and Mapping (SLAM) is the de facto choice, and in recent years with the advent of color and depth (RGB-D) sensors, RGB-D SLAM has become a hot topic for research. Most research being performed is on improving the overall system accuracy or more specifically the performance with regards to the overall trajectory error. While this approach quantifies the performance of the system as a whole, the individual frame-to-frame performance is often not mentioned or explored properly. While this will directly tie in to the overall performance, the level of scene cohesion experienced between two successive observations can vary greatly over a single dataset of observations. The focus of this dissertation will be the relevant levels of translational and rotational velocities experienced by the sensor between two successive observations and the effect on the final accuracy of the SLAM implementation. The frame rate will specifically be used to alter and evaluate the different spatial velocities experienced over multiple datasets of RGB-D data. Two systems were developed to illustrate and evaluate the potential of various approaches to RGB-D SLAM. The first system is a real-world implementation where SLAM is used to localise and map the environment surrounding a quadcopter platform. A Microsoft Kinect is directly mounted to the quadcopter and is used to provide a RGB-D datastream to a remote processing terminal. This terminal runs a SLAM implementation that can alternate between different visual odometry methods. The remote terminal acts as the position controller for the quadcopter, replacing the need for a direct human operator. A semi-automated system is implemented, that allows a human operator to designate waypoints within the environment that the quadcopter moves to. The second system uses a series of publicly available RGB-D datasets with their accompanying ground-truth readings to simulate a real RGB-D datasteam. This is used to evaluate the performance of the various RGB-D SLAM approaches to visual odometry. For each of the datasets, the accompanying translational and angular velocity on a frame-to-frame basis can be calculated. This can, in turn, be used to evaluate the frame-to-frame accuracy of the SLAM implementation, where the spatial velocity can be manually altered by occluding frames within the sequence. Thus, an accurate relationship can be calculated between the frame rate, the spatial velocity and the performance of the SLAM implementation. Three image processing techniques were used to implement the visual odometry for RGB-D SLAM. SIFT, SURF and ORB were compared across eight of the TUM database datasets. SIFT had the best performance, with a 30% increase over SURF and doubling the performance of ORB. By implementing SIFT using CUDA, the feature detection and description process only takes 18ms, negating the disadvantage that SIFT has compared to SURF and ORB. The RGB-D SLAM implementation was compared to four prominent research papers, and showed comparable results. The effect of rotation and translation was evaluated, based on the effect of each rotation and translation axis. It was found that the z-axis (scale) and the roll-axis (scene orientation) have a lower effect on the average RPE error in a frame-to-frame basis. It was found that rotation has a much greater impact on the performance, when evaluating rotation and translation separately. On average, a rotation of 1deg resulted in a 4mm translation error and a 20% rotation error , where a translation of 10mm resulted in a rotation error of 0.2deg and a translation error of 45%. The combined effect of rotation and translation had a multiplicative effect on the error metric. The quadcopter platform designed to work with the SLAM implementation did not function ideally, but it was sufficient for the purpose. The quadcopter is able to self stabilise within the environment, given a spacious area. For smaller, enclosed areas the backdraft generated by the quadcopter motors lead to some instability in the system. A frame-to-frame error of 40.34mm and 1.93deg was estimated for the quadcopter system. / Dissertation (MEng)--University of Pretoria, 2017. / Electrical, Electronic and Computer Engineering / MEng / Unrestricted

This master thesis is focused on visualization of virtual objects in the real space. The introductory section provides a brief description of Kinect and Unity technologies. Moreover, similar state-of-the-art projects are outlined with regard to the used methodics of interaction. Subsequently, a review of useful libraries is provided. On the basis of these information, the methodics of my project is formu-lated. The subsequent part of the thesis deals with the implementation of experi-mental application in the C# programming language. Finally, the application is evaluated and there is a discussion of its pros and cons.

This Bachelor’s Thesis in Computer Science investigates the use of the parameterised facial animation model named CANDIDE-3 (J. Ahlberg, 2001) in Telepresence communication with relatively cheap hardware. An experimental study was conducted to evaluate how well an implementation using the Microsoft Kinect Face Tracking device could capture and animate the 6 classical emotional states: joy, sadness, surprise, anger, fear and disgust. A total of 80 test candidates took part in a survey where they were to try and classify the emotional states of images of photographed and animated faces. The animated faces were created using the prototype system built for the purpose of the survey and rendered onto the robotic Furhat face (Al Moubayed, S., Skantze, G., Beskow, J., Stefanov, K., & Gustafson, J, 2012). Results showed that a person’s emotional state is preserved very well through the animation technique used, and for some basic emotions, like joy or sadness, the animation could even amplify the emotional state for the viewer. However, the 6 Action Units captured from the Kinect device were not enough to sufficiently distinguish between even some of most the basic emotional states (e.g. disgust, anger). / Denna kandidatuppsats inom Datateknik undersöker hur väl den parametriserade animationsmodellen CANDIDE-3 (J.Ahlberg, 2001) kan användas för att visa ansiktsuttryck inom Telepresence-sammanhang med hjälp av relativt billig hårdvara. En experimentell studie utfördes för att undersöka hur väl en implementation som använder Microsoft Kinects ansiktsigenkänning kunde fånga och animera de 6 klassiska ansiktsuttrycken: glädje, sorg, förvåning, ilska, rädsla och avsky. Totalt deltog 80 personer i undersökningen där deras uppgift var att klassificera känslomässiga tillstånd från fotograferade och animerade ansikten. De animerade ansiktena skapades med hjälp av det prototypsystem som byggdes i undersökningens syfte och renderades på det robotiserade Furhat-ansiktet (Al Moubayed, S., Skantze, G., Beskow, J., Stefanov, K., & Gustafson, J, 2012). Resultat visade att en persons känslomässiga tillstånd väldigt väl bevaras genom animationstekniken som används, och för några grundläggande känslor, såsom glädje och sorg, kunde animationen till och med förstärka det känslomässiga tillståndet för åskådaren. De 6 AU-enheterna som fångas av Kinect-enheten var dock inte tillräckliga för att särskilja till och med några av de mest grundläggande känslomässiga tillstånden (såsom avsky, ilska).

Submitted by Cláudia Bueno (claudiamoura18@gmail.com) on 2016-03-03T20:59:22Z No. of bitstreams: 2 Dissertação - Rafael Tomaz Parreira - 2015.pdf: 4890640 bytes, checksum: 77343ad4266b8d39c9b9e142b0c167c3 (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) / Approved for entry into archive by Luciana Ferreira (lucgeral@gmail.com) on 2016-03-04T11:31:51Z (GMT) No. of bitstreams: 2 Dissertação - Rafael Tomaz Parreira - 2015.pdf: 4890640 bytes, checksum: 77343ad4266b8d39c9b9e142b0c167c3 (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) / Made available in DSpace on 2016-03-04T11:31:51Z (GMT). No. of bitstreams: 2 Dissertação - Rafael Tomaz Parreira - 2015.pdf: 4890640 bytes, checksum: 77343ad4266b8d39c9b9e142b0c167c3 (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) Previous issue date: 2015-10-29 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPES / Forest Inventory is a se to fimportanttechniquesthatprovidesessentialinformationsfor rationalandsustainableresourcesdrivinginforests. The selectedareacanbecharacteri- zedaboutspeciesquantityandquality.Forest inventories areusedinmanykindofstudies inorderofknowing,forecastingandevaluationinfields.Furthermore,theforestinven- toryalsoallowstoevaluatethetimberstockanditsviability,planningandpreparation ofexplorationtreestandsandpostexploratory.Anessentialinformationisthediameters alongoftreetrunkanditisindispensablefortimbervolume calculation.Currently,fordi- ametermeasuringahugetimeisrequiredandmanymistakesare possibledueinstruments defectsandhumanfailures.Somestudieshaveuseddifferent techniquesforreplacingtra- ditionaldiametermeasuringinstruments,amongthemstands outdeviceswithcapability ofgetdepthdatainthefield.Amongthesedevicesarethedepth camerasthatduethe recentdecreaseofpricehavebecomeverypopularincomputer visionapplications.Inor- dertoassistvolumeestimation,thisworksproposesusingdepthcamerastoconductdata acquisitionandanalisysofEucalyptustreediameters.The modeldevelopediscapable toacquirediametersindifferenttreeheights,howeverthe focusismorespecificallyin getdiametersat0.3,0.7and1.3metersfromtheground.Experimentswereconducted inordertocomparetheproposedmodeltotraditionaltechniquesandtheresultsarevery satisfactory. / O inventário florestal é um conjunto de técnicas importantes que fornece informações essenciais para direcionamento racional e sustentável dos recursos disponíveis nas florestas. Por meio dele é possível a caracterização de uma determinada área e do conhecimento quantitativo e qualitativo das espécies que a compõe. Inventários florestais são utilizado sem vários tipos de levantamentos com a finalidade de reconhecimento,diagnóstico e avaliações no campo florestal. A avaliação de estoque de madeira em estudos de viabilidade, planejamento e preparação de talhões de exploração, bem como, diagnóstico pós-exploratório, exigem inventários específicos. Uma das informações essenciais é o diâmetro ao longo do tronco das árvores, que é imprescindível para o cálculo de volume de madeira. Atualmente, para medir esses diâmetros é demandado um período elevado de tempo, sendo passível de erros gerados por defeitos em instrumentos e/ou falhas dos operadores. Alguns estudos têm utilizado técnicas diferentes para substituir o uso de instrumentos tradicionais na tomada das medidas dos diâmetros, entre elas se destaca o uso de dispositivos que podem obter os padrões de profundidade em cenários que contém árvores. Entre os dispositivos capazes de obter profundidade, está as câmeras de profundidade, que vem se popularizando,tornando-se cada vez mais acessíveis,com isso diversas aplicações de visão computacional vêm sendo desenvolvidas, e são capazes de fazer a extração de informações bastante úteis. Este trabalho propõe a utilização de câmeras de profundidade para realizar análise e aquisição de dados que são usados para estimar diâmetros de árvores do gênero Eucalyptus. O modelo desenvolvido para calcular os diâmetros da base das árvores nas alturas de 0,3;0,7 e 1,3 metros em relação ao solo. O modelo proposto, tem por objetivo, o uso dos diâmetros estimados por câmera de profundidade para o cálculo do volume das árvores de eucalipto apartir método apresentado nos trabalhos relacionados. Foram realizados testes a fim de comparar o desempenho do modelo proposto aos métodos tradicionais.Os resultados obtidos foram considerados bastante satisfatórios.

Submitted by Marlene Santos (marlene.bc.ufg@gmail.com) on 2014-10-15T21:29:54Z No. of bitstreams: 2 Dissertacao - Fabrício Leonardo Leopoldino - 2013.pdf: 15282157 bytes, checksum: d2e674ff7b57f0a88c10f3ee9a9b248d (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) / Approved for entry into archive by Jaqueline Silva (jtas29@gmail.com) on 2014-10-16T17:22:45Z (GMT) No. of bitstreams: 2 Dissertacao - Fabrício Leonardo Leopoldino - 2013.pdf: 15282157 bytes, checksum: d2e674ff7b57f0a88c10f3ee9a9b248d (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) / Made available in DSpace on 2014-10-16T17:22:45Z (GMT). No. of bitstreams: 2 Dissertacao - Fabrício Leonardo Leopoldino - 2013.pdf: 15282157 bytes, checksum: d2e674ff7b57f0a88c10f3ee9a9b248d (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) Previous issue date: 2013-09-18 / This study proposes a Virtual Environment to support the functional rehabilitation of the upper limbs, using the Microsoft Kinect sensor motion capture. It is organized in five chapters: 1) Use of Virtual Environments in the process of functional rehabilitation of people affected by an Encephalic Vascular Accident; 2) Technologies used, 3) AVARFMS development; 4) Discussion; 5) Conclusions. Sequelae of Encephalic Vascular Accident impair the development of the Activities of Daily Living. Rehabilitation does not consist in a process that seeks only the adaptation of the patient, but in a real effort with the goal of promoting the development of people creative and inclusive functionality. With the emergence of Virtual Environments and greater integration between the areas of rehabilitation medicine and information systems as well as the appearance of low cost motion sensors (Microsoft Kinect, for example), a new paradigm begins to be postulated between researchers in these two areas: the study and development of virtual environments to assist in the rehabilitation process. With the goal of providing a fun tool to patients who have been affected by an encephalic vascular accident and offering therapists ways to measure (qualitatively and quantitatively) the evolution of the patient treatment, it is proposed a virtual environment that uses the motion sensor Kinect, created by Microsoft. The findings presented in this study show that the proposed objectives were achieved. / O presente trabalho propõe um ambiente virtual de apoio à reabilitação funcional de membros superiores, utilizando o sensor de captura de movimento da Microsoft, Kinect. Está dividido em cinco capítulos: 1) Utilização de Ambientes Virtuais no Processo de Reabilitação Funcional de Pessoas Acometidas por um Acidente Vascular Encefálico; 2) Tecnologias Utilizadas; 3) Desenvolvimento do AVARFMS; 4) Discussão e 5) Conclusões. O Acidente Vascular Encefálico (AVE) deixa sequelas que comprometem o desenvolvimento das Atividades de Vida Diária. A reabilitação não consiste em um processo que busca apenas a adaptação do paciente, mas em um esforço concreto, com o objetivo de promover o desenvolvimento máximo da funcionalidade criadora e inclusiva das pessoas. Com o surgimento dos Ambientes Virtuais (AVs) e a maior integração entre as áreas da medicina de reabilitação e sistemas de informação, bem como o aparecimento de Sensores de Movimento (Microsoft Kinect, por exemplo) de baixo custo, um novo paradigma começa a ser postulado entre pesquisadores destas duas áreas: o estudo e desenvolvimento de AVs para auxiliar no processo de reabilitação. Com o objetivo de fornecer uma ferramenta divertida aos pacientes que foram acometidos por um AVE e oferecer aos terapeutas maneiras de medir (qualitativamente e quantitativamente) a evolução do tratamento de um paciente, é proposto um Ambiente Virtual que utiliza o sensor de movimentos Kinect, criado pela Microsoft. As conclusões apresentadas neste trabalho mostram que os objetivos propostos pelo ambiente foram atingidos

Physiotherapy patients, victims of accidents, strokes and injuries are submitted for several months of repetitive exercise in rehabilitation sessions, depending almost entirely of aid and monitoring of the physical therapist. The performed exercises should be supervised and evaluated regularly in order to measure the patient's progress in treatment. The evolution of new interaction technologies with the patient, through low-cost motion detection sensors, enables the creation for physical therapy support software. Furthermore, the introduction of Exergames and BrainTraining games in the fields of medicine and physical therapy has shown that serious games can be used to assist the treatment of diseases and patients in special conditions. However, few studies demonstrate the importance or relevant results regarding the usability of solutions. This paper presents the development and evaluation of a gaming system to assist physiotherapists in quality analysis and workout efficiency. The evaluation through specific questionnaires showed the quality of the developed system on the usability and functionality of the games. Also from the final collected data, it is presented an ideal standard for players movement data, that can be used as a reference during treatment of patients. / Pacientes de fisioterapia, vítimas de acidentes, derrames e lesões são submetidos por vários meses a sessões repetitivas de exercícios para reabilitação, dependendo quase que totalmente do auxílio e acompanhamento do fisioterapeuta. Os exercícios realizados devem ser supervisionados e avaliados regularmente, com o intuito de medir o progresso do paciente no tratamento. A evolução de novas tecnologias de interação com o paciente, através de sensores de detecção de movimentos de baixo custo, possibilita a criação de softwares de apoio ao tratamento fisioterapêutico. Além disso, a introdução de Exergames e BrainTraining games nos campos da medicina e fisioterapia tem demonstrado que é possível utilizar jogos sérios para auxiliar nos tratamentos de doenças e condições especiais dos pacientes. Contudo, poucos estudos demonstram a importância ou resultados relevantes quanto à usabilidade das soluções. Este trabalho apresenta o desenvolvimento e avaliação de um sistema de jogos para auxiliar fisioterapeutas na análise da qualidade e eficiência da sessão de exercícios. A avaliação realizada através de questionários específicos demonstrou a qualidade do sistema desenvolvido quanto à usabilidade e funcionalidade dos jogos apresentados. Também a partir dos dados finais coletados, apresenta-se um padrão ideal de dados para os movimentos dos jogadores, que pode ser usado como referência durante o tratamento de pacientes.