Feasibility and acceptability of an exergame intervention for schizophrenia

Objectives To evaluate the feasibility and acceptability of an exergame intervention as a tool to promote physical activity in outpatients with schizophrenia. Design Feasibility/Acceptability Study and Quasi-Experimental Trial. Method Sixteen outpatients with schizophrenia received treatment as usual and they all completed an 8-week exergame intervention using Microsoft Kinect® (20 min sessions, biweekly). Participants completed pre and post treatment assessments regarding functional mobility (Timed Up and Go Test), functional fitness performance (Senior Fitness Test), motor neurological soft signs (Brief Motor Scale), hand grip strength (digital dynamometer), static balance (force plate), speed of processing (Trail Making Test), schizophrenia-related symptoms (Positive and Negative Syndrome Scale) and functioning (Personal and Social Performance Scale). The EG group completed an acceptability questionnaire after the intervention. Results Attrition rate was 18.75% and 69.23% of the participants completed the intervention within the proposed schedule. Baseline clinical traits were not related to game performance indicators. Over 90% of the participants rated the intervention as satisfactory and interactive. Most participants (76.9%) agreed that this intervention promotes healthier lifestyles and is an acceptable alternative to perform physical activity. Repeated-measures MANOVA analyses found no significant multivariate effects for combined outcomes. Conclusion This study established the feasibility and acceptability of an exergame intervention for outpatients with schizophrenia. The intervention proved to be an appealing alternative to physical activity. Future trials should include larger sample sizes, explore patients' adherence to home-based exergames and consider greater intervention dosage (length, session duration, and/or frequency) in order to achieve potential effects.

Video-based analysis of Gait pathologies

L’analyse de la marche a émergé comme l’un des domaines médicaux le plus im- portants récemment. Les systèmes à base de marqueurs sont les méthodes les plus fa- vorisées par l’évaluation du mouvement humain et l’analyse de la marche, cependant, ces systèmes nécessitent des équipements et de l’expertise spécifiques et sont lourds, coûteux et difficiles à utiliser. De nombreuses approches récentes basées sur la vision par ordinateur ont été développées pour réduire le coût des systèmes de capture de mou- vement tout en assurant un résultat de haute précision. Dans cette thèse, nous présentons notre nouveau système d’analyse de la démarche à faible coût, qui est composé de deux caméras vidéo monoculaire placées sur le côté gauche et droit d’un tapis roulant. Chaque modèle 2D de la moitié du squelette humain est reconstruit à partir de chaque vue sur la base de la segmentation dynamique de la couleur, l’analyse de la marche est alors effectuée sur ces deux modèles. La validation avec l’état de l’art basée sur la vision du système de capture de mouvement (en utilisant le Microsoft Kinect) et la réalité du ter- rain (avec des marqueurs) a été faite pour démontrer la robustesse et l’efficacité de notre système. L’erreur moyenne de l’estimation du modèle de squelette humain par rapport à la réalité du terrain entre notre méthode vs Kinect est très prometteur: les joints des angles de cuisses (6,29◦ contre 9,68◦), jambes (7,68◦ contre 11,47◦), pieds (6,14◦ contre 13,63◦), la longueur de la foulée (6.14cm rapport de 13.63cm) sont meilleurs et plus stables que ceux de la Kinect, alors que le système peut maintenir une précision assez proche de la Kinect pour les bras (7,29◦ contre 6,12◦), les bras inférieurs (8,33◦ contre 8,04◦), et le torse (8,69◦contre 6,47◦). Basé sur le modèle de squelette obtenu par chaque méthode, nous avons réalisé une étude de symétrie sur différentes articulations (coude, genou et cheville) en utilisant chaque méthode sur trois sujets différents pour voir quelle méthode permet de distinguer plus efficacement la caractéristique symétrie / asymétrie de la marche. Dans notre test, notre système a un angle de genou au maximum de 8,97◦ et 13,86◦ pour des promenades normale et asymétrique respectivement, tandis que la Kinect a donné 10,58◦et 11,94◦. Par rapport à la réalité de terrain, 7,64◦et 14,34◦, notre système a montré une plus grande précision et pouvoir discriminant entre les deux cas.

A survey of human motion analysis using depth imagery

Analysis of human behaviour through visual information has been a highly active research topic in the computer vision community. This was previously achieved via images from a conventional camera, but recently depth sensors have made a new type of data available. This survey starts by explaining the advantages of depth imagery, then describes the new sensors that are available to obtain it. In particular, the Microsoft Kinect has made high-resolution real-time depth cheaply available. The main published research on the use of depth imagery for analysing human activity is reviewed. Much of the existing work focuses on body part detection and pose estimation. A growing research area addresses the recognition of human actions. The publicly available datasets that include depth imagery are listed, as are the software libraries that can acquire it from a sensor. This survey concludes by summarising the current state of work on this topic, and pointing out promising future research directions.

ReadingAct RGB-D action dataset and human action recognition from local features

For general home monitoring, a system should automatically interpret people’s actions. The system should be non-intrusive, and able to deal with a cluttered background, and loose clothes. An approach based on spatio-temporal local features and a Bag-of-Words (BoW) model is proposed for single-person action recognition from combined intensity and depth images. To restore the temporal structure lost in the traditional BoW method, a dynamic time alignment technique with temporal binning is applied in this work, which has not been previously implemented in the literature for human action recognition on depth imagery. A novel human action dataset with depth data has been created using two Microsoft Kinect sensors. The ReadingAct dataset contains 20 subjects and 19 actions for a total of 2340 videos. To investigate the effect of using depth images and the proposed method, testing was conducted on three depth datasets, and the proposed method was compared to traditional Bag-of-Words methods. Results showed that the proposed method improves recognition accuracy when adding depth to the conventional intensity data, and has advantages when dealing with long actions.

Interação gestual em ambiente residencial: estudo, concepção e desenvolvimento

Control and automation of residential environments domotics is emerging area of computing application. The development of computational systems for domotics is complex, due to the diversity of potential users, and because it is immerse in a context of emotional relationships and familiar construction. Currently, the focus of the development of this kind of system is directed, mainly, to physical and technological aspects. Due to the fact, gestural interaction in the present research is investigated under the view of Human-Computer Interaction (HCI). First, we approach the subject through the construction of a conceptual framework for discussion of challenges from the area, integrated to the dimensions: people, interaction mode and domotics. A further analysis of the domain is accomplished using the theoretical-methodological referential of Organizational Semiotics. After, we define recommendations to the diversity that base/inspire the inclusive design, guided by physical, perceptual and cognitive abilities, which aim to better represent the concerned diversity. Although developers have the support of gestural recognition technologies that help a faster development, these professionals face another difficulty by not restricting the gestural commands of the application to the standard gestures provided by development frameworks. Therefore, an abstraction of the gestural interaction was idealized through a formalization, described syntactically by construction blocks that originates a grammar of the gestural interaction and, semantically, approached under the view of the residential system. So, we define a set of metrics grounded in the recommendations that are described with information from the preestablished grammar, and still, we conceive and implement in Java, under the foundation of this grammar, a residential system based on gestural interaction for usage with Microsoft Kinect. Lastly, we accomplish an experiment with potential end users of the system, aiming to better analyze the research results

Simplificação de malhas visando representações em multirresolução

The representation of real objects in virtual environments has applications in many areas, such as cartography, mixed reality and reverse engineering. The generation of these objects can be performed through two ways: manually, with CAD (Computer Aided Design) tools, or automatically, by means of surface reconstruction techniques. The simpler the 3D model, the easier it is to process and store it. However, this methods can generate very detailed virtual elements, that can result in some problems when processing the resulting mesh, because it has a lot of edges and polygons that have to be checked at visualization. Considering this context, it can be applied simplification algorithms to eliminate polygons from resulting mesh, without change its topology, generating a lighter mesh with less irrelevant details. The project aimed the study, implementation and comparative tests of simplification algorithms applied to meshes generated through a reconstruction pipeline based on point clouds. This work proposes the realization of the simplification step, like a complement to the pipeline developed by (ONO et al., 2012), that developed reconstruction through cloud points obtained by Microsoft Kinect, and then using Poisson algorithm

Um método para reconstrução de superfícies baseado em nuvem de pontos visando representações em multirresolução

The representation of real objects in virtual environments has applications in many areas, such as cartography, mixed reality and reverse engineering. The generation of these objects can be performed in two ways: manually, with CAD (Computer Aided Design) tools, or automatically, by means of surface reconstruction techniques. The simpler the 3D model, the easier it is to process and store it. Multiresolution reconstruction methods can generate polygonal meshes in different levels of detail and, to improve the response time of a computer program, distant objects can be represented with few details, while more detailed models are used in closer objects. This work presents a new approach to multiresolution surface reconstruction, particularly interesting to noisy and low definition data, for example, point clouds captured with Kinect sensor

Riabilitazione e valutazione di pazienti con deficit neurologici mediante l'utilizzo di realtà virtuale, feedback aumentati, sensori inerziali e tecnologie video a basso costo.

La neuroriabilitazione è un processo attraverso cui individui affetti da patologie neurologiche mirano al conseguimento di un recupero completo o alla realizzazione del loro potenziale ottimale benessere fisico, mentale e sociale. Elementi essenziali per una riabilitazione efficace sono: una valutazione clinica da parte di un team multidisciplinare, un programma riabilitativo mirato e la valutazione dei risultati conseguiti mediante misure scientifiche e clinicamente appropriate. Obiettivo principale di questa tesi è stato sviluppare metodi e strumenti quantitativi per il trattamento e la valutazione motoria di pazienti neurologici. I trattamenti riabilitativi convenzionali richiedono a pazienti neurologici l’esecuzione di esercizi ripetitivi, diminuendo la loro motivazione. La realtà virtuale e i feedback sono in grado di coinvolgerli nel trattamento, permettendo ripetibilità e standardizzazione dei protocolli. È stato sviluppato e valutato uno strumento basato su feedback aumentati per il controllo del tronco. Inoltre, la realtà virtuale permette l’individualizzare il trattamento in base alle esigenze del paziente. Un’applicazione virtuale per la riabilitazione del cammino è stata sviluppata e testata durante un training su pazienti di sclerosi multipla, valutandone fattibilità e accettazione e dimostrando l'efficacia del trattamento. La valutazione quantitativa delle capacità motorie dei pazienti viene effettuata utilizzando sistemi di motion capture. Essendo il loro uso nella pratica clinica limitato, una metodologia per valutare l’oscillazione delle braccia in soggetti parkinsoniani basata su sensori inerziali è stata proposta. Questi sono piccoli, accurati e flessibili ma accumulano errori durante lunghe misurazioni. È stato affrontato questo problema e i risultati suggeriscono che, se il sensore è sul piede e le accelerazioni sono integrate iniziando dalla fase di mid stance, l’errore e le sue conseguenze nella determinazione dei parametri spaziali sono contenuti. Infine, è stata presentata una validazione del Kinect per il tracking del cammino in ambiente virtuale. Risultati preliminari consentono di definire il campo di utilizzo del sensore in riabilitazione.

TECHNOLOGICAL ADVANCEMENT IN REMOTE SENSING AND INNOVATIVE APPLICATION TO VOLCANOLOGY

The integration of remote monitoring techniques at different scales is of crucial importance for monitoring of volcanoes and assessment of the associated hazard. In this optic, technological advancement and collaboration between research groups also play a key role. Vhub is a community cyberinfrastructure platform designed for collaboration in volcanology research. Within the Vhub framework, this dissertation focuses on two research themes, both representing novel applications of remotely sensed data in volcanology: advancement in the acquisition of topographic data via active techniques and application of passive multi-spectral satellite data to monitoring of vegetated volcanoes. Measuring surface deformation is a critical issue in analogue modelling of Earth science phenomena. I present a novel application of the Microsoft Kinect sensor to measurement of vertical and horizontal displacements in analogue models. Specifically, I quantified vertical displacement in a scaled analogue model of Nisyros volcano, Greece, simulating magmatic deflation and inflation and related surface deformation, and included the horizontal component to reconstruct 3D models of pit crater formation. The detection of active faults around volcanoes is of importance for seismic and volcanic hazard assessment, but not a simple task to be achieved using analogue models. I present new evidence of neotectonic deformation along a north-south trending fault from the Mt Shasta debris avalanche deposit (DAD), northern California. The fault was identified on an airborne LiDAR campaign of part of the region interested by the DAD and then confirmed in the field. High resolution LiDAR can be utilized also for geomorphological assessment of DADs, and I describe a size-distance analysis to document geomorphological aspects of hummock in the Shasta DAD. Relating the remote observations of volcanic passive degassing to conditions and impacts on the ground provides an increased understanding of volcanic degassing and how satellite-based monitoring can be used to inform hazard management strategies in nearreal time. Combining a variety of satellite-based spectral time series I aim to perform the first space-based assessment of the impacts of sulfur dioxide emissions from Turrialba volcano, Costa Rica, on vegetation in the surrounding environment, and establish whether vegetation indices could be used more broadly to detect volcanic unrest.

Hands-Free Navigation in Immersive Environments for the Evaluation of the Effectiveness of Indoor Navigation Systems

While navigation systems for cars are in widespread use, only recently, indoor navigation systems based on smartphone apps became technically feasible. Hence tools in order to plan and evaluate particular designs of information provision are needed. Since tests in real infrastructures are costly and environmental conditions cannot be held constant, one must resort to virtual infrastructures. This paper presents the development of an environment for the support of the design of indoor navigation systems whose center piece consists in a hands-free navigation method using the Microsoft Kinect in the four-sided Definitely Affordable Virtual Environment (DAVE). Navigation controls using the user's gestures and postures as the input to the controls are designed and implemented. The installation of expensive and bulky hardware like treadmills is avoided while still giving the user a good impression of the distance she has traveled in virtual space. An advantage in comparison to approaches using a head mounted display is that the DAVE allows the users to interact with their smartphone. Thus the effects of different indoor navigation systems can be evaluated already in the planning phase using the resulting system

Estimating Gesture Accuracy in Motion-Based Health Games

This manuscript details a technique for estimating gesture accuracy within the context of motion-based health video games using the MICROSOFT KINECT. We created a physical therapy game that requires players to imitate clinically significant reference gestures. Player performance is represented by the degree of similarity between the performed and reference gestures and is quantified by collecting the Euler angles of the player's gestures, converting them to a three-dimensional vector, and comparing the magnitude between the vectors. Lower difference values represent greater gestural correspondence and therefore greater player performance. A group of thirty-one subjects was tested. Subjects achieved gestural correspondence sufficient to complete the game's objectives while also improving their ability to perform reference gestures accurately.

Desarrollo de una Interfaz de sustitución sensorial para el estudio de la percepción del flujo vibrotáctil (retina táctil)

En el presente trabajo fin de máster se ha concebido, diseñado e utilizado una interfaz háptica, adecuada para ser utilizada como dispositivo de sustitución sensorial, la cual hemos llamado retina táctil. Por cuanto trata de proporcionar información propia del sentido de la vista a través del sentido del tacto. Durante este trabajo, que fue desarrollado en el grupo de robótica y cibernética CAR UPM-CSIC, se ha trabajado en estrecha colaboración con el departamento de la facultad de psicología de la universidad autónoma de Madrid, los cuales han definido las bases de la información de alto orden, como podrían ser, gradientes de intensidades de vibración, mediante las cuales el individuo llega a tener una mejor comprensión del ambiente. El proyecto maneja teorías psicológicas recientes, como las teorías ecológicas y dinámicas que entienden que la percepción se basa en variables informacionales de alto orden. Ejemplos de tales variables son el flujo óptico, gradientes de movimiento, gradientes de intensidades, cambios en gradientes, etc. Sorprendentemente, nuestra percepción visual es mucho más sensible a variables de alto orden que a variables de bajo orden, lo cual descarta que variables de alto orden se infieran o calculen en base a variables de bajo orden. La hipótesis que maneja la teoría ecológica es que las variables de alto orden se detectan como unidades básicas, sin descomponerlas en variables de bajo orden. Imaginemos el caso de un objeto acercándose, intuitivamente pensaríamos que calculamos la distancia y la velocidad del objeto para determinar el momento en el cual este nos impactaría, ¿pero es este realmente el modo en el que actúa nuestro cerebro?, ¿no seremos capaces en determinar directamente el tiempo de contacto como una variable de alto orden presente en el entorno?, por ejemplo, determinar directamente la relación entre el tamaño del objeto y la tasa de crecimiento. También cabe preguntarse si todas estas suposiciones son válidas para estimulaciónes a través de los receptores táctiles en la piel. El dispositivo desarrollado está conformado por 13 módulos cada uno de los cuales maneja 6 tactores o vibradores, para hacer un total de 78 vibradores (ampliables al agregar módulos adicionales), cada uno de los tactores tiene 8mm de diámetro y proporciona información del flujo óptico asociado al entorno que rodea al usuario a través de información táctil, él mismo puede ser utilizado inalámbricamente a pesar de que el procesamiento de los datos se este realizando en una computadora de mesa, lo cual es muy útil al trabajar con ambientes virtuales. También se presenta la integración de la interfaz con el sistema operativo de robots ROS para usarlo en conjunto con las librerías que han sido desarrolladas para el control de la cámara Microsoft Kinect con la cual se puede obtener una matriz de distancias de puntos en el espacio, permitiendo de esta manera utilizar la interfaz en ambientes reales. Finalmente se realizaron experimentos para comprobar hipótesis sobre la variable de percepción del tiempo de contacto además de verificar el correcto funcionamiento del dispositivo de sustitución sensorial tanto en ambientes reales como en ambientes simulados así como comprobar hipótesis sobre la validéz del uso del flujo vibrotáctil para la determinación del tiempo de contacto.

Depth-based face recognition using local quantized patterns adapted for range data

A depth-based face recognition algorithm specially adapted to high range resolution data acquired by the new Microsoft Kinect 2 sensor is presented. A novel descriptor called Depth Local Quantized Pattern descriptor has been designed to make use of the extended range resolution of the new sensor. This descriptor is a substantial modification of the popular Local Binary Pattern algorithm. One of the main contributions is the introduction of a quantification step, increasing its capacity to distinguish different depth patterns. The proposed descriptor has been used to train and test a Support Vector Machine classifier, which has proven to be able to accurately recognize different people faces from a wide range of poses. In addition, a new depth-based face database acquired by the new Kinect 2 sensor have been created and made public to evaluate the proposed face recognition system.