Reconeixement de gestos de la mà amb el sensor Kinect

El reconeixement dels gestos de la mà (HGR, Hand Gesture Recognition) és actualment un camp important de recerca degut a la varietat de situacions en les quals és necessari comunicar-se mitjançant signes, com pot ser la comunicació entre persones que utilitzen la llengua de signes i les que no. En aquest projecte es presenta un mètode de reconeixement de gestos de la mà a temps real utilitzant el sensor Kinect per Microsoft Xbox, implementat en un entorn Linux (Ubuntu) amb llenguatge de programació Python i utilitzant la llibreria de visió artifical OpenCV per a processar les dades sobre un ordinador portàtil convencional. Gràcies a la capacitat del sensor Kinect de capturar dades de profunditat d’una escena es poden determinar les posicions i trajectòries dels objectes en 3 dimensions, el que implica poder realitzar una anàlisi complerta a temps real d’una imatge o d’una seqüencia d’imatges. El procediment de reconeixement que es planteja es basa en la segmentació de la imatge per poder treballar únicament amb la mà, en la detecció dels contorns, per després obtenir l’envolupant convexa i els defectes convexos, que finalment han de servir per determinar el nombre de dits i concloure en la interpretació del gest; el resultat final és la transcripció del seu significat en una finestra que serveix d’interfície amb l’interlocutor. L’aplicació permet reconèixer els números del 0 al 5, ja que s’analitza únicament una mà, alguns gestos populars i algunes de les lletres de l’alfabet dactilològic de la llengua de signes catalana. El projecte és doncs, la porta d’entrada al camp del reconeixement de gestos i la base d’un futur sistema de reconeixement de la llengua de signes capaç de transcriure tant els signes dinàmics com l’alfabet dactilològic.

Analyse cinématique de la marche de travailleurs exposés à une surcharge mécanique sur l’articulation fémoro-tibiale (AF-T)

De nombreuses études concluent que la charge mécanique supportée par le genou, qu’elle soit reliée à l’obésité, aux sports intenses, à une altération biomécanique des structures de l’articulation ou à une exposition à des charges lourdes durant les activités occupationnelles, est considérée comme un facteur de risque important au développement de la gonarthrose. La gonarthrose reliée au travail a été le sujet de nombreuses études et plusieurs d’entre elles ont rapporté une prévalence accrue de la gonarthrose chez les travailleurs de certains domaines en particulier, comme la construction, la pose de plancher, la peinture, l’exploitation minière, l’agriculture et le travail en atelier et en milieu de la santé. Les personnes qui travaillent dans ces métiers sont exposées à des positions ou des activités nuisibles, comme travailler à genoux ou accroupi, monter des escaliers ou des échelles, transporter des changes lourdes et marcher de façon prolongée. Ces gestes surchargent l’articulation du genou, ce qui cause des modifications aux structures de l’articulation du genou ou aux adaptations neuromusculaires de patron de mouvement du genou. Ces modifications structurelles et adaptations neuromusculaires peuvent apporter des changements cinématiques à la marche qui peuvent initier la gonarthrose ou contribuer à sa progression. L’objectif principal de la présente étude était d’analyser l’effet d’une surcharge mécanique sur l’articulation fémoro-tibiale (AF-T) subie au travail lors d’une tâche de marche et comparer le patron cinématique de l’articulation fémoro-tibiale des travailleurs exposés à une surcharge mécanique à celui des travailleurs non exposés. Vingt-quatre travailleurs exposés à une surcharge mécanique et neuf travailleurs non exposés ont participé à l’étude. Les données cinématiques de la marche ont été enregistrées au niveau du genou dans des conditions cliniques en utilisant un système de suivi du mouvement électromagnétique. Les paramètres suivant ont été extraits et utilisés pour la comparaison des groupes : l’angle maximum lors du contact initial, l’angle ii maximum de flexion durant la réponse à la charge, l’angle minimum au moment de l’appui unipodal et l’étendue max-min du cycle. La comparaison des groupes pour les variables cliniques et cinématiques a été effectué par l’utilisation de tests-t bilatéraux (« Student-t tests ») et de tests ANCOVA utilisant le poids et la vitesse comme covariables. Les travailleurs exposés à une surcharge mécanique présentaient un plus grand angle de flexion de l’articulation fémoro-tibiale au contact initial, durant la réponse au chargement et à la phase unipodale et ils ont démontré une étendue d’angle moindre que les travailleurs non exposés. Nous croyons que les données cinématiques de la marche peuvent donner des idées sur les facteurs biomécaniques qui pourraient prédisposer les travailleurs au développement ou à la progression de la gonarthrose. Une meilleure compréhension de ces facteurs pourrait être un premier pas vers le développement d’une intervention plus efficace pour cette population.

Intact imitation of emotional facial actions in autism spectrum conditions.

It has been proposed that there is a core impairment in autism spectrum conditions (ASC) to the mirror neuron system (MNS): If observed actions cannot be mapped onto the motor commands required for performance, higher order sociocognitive functions that involve understanding another person's perspective, such as theory of mind, may be impaired. However, evidence of MNS impairment in ASC is mixed. The present study used an 'automatic imitation' paradigm to assess MNS functioning in adults with ASC and matched controls, when observing emotional facial actions. Participants performed a pre-specified angry or surprised facial action in response to observed angry or surprised facial actions, and the speed of their action was measured with motion tracking equipment. Both the ASC and control groups demonstrated automatic imitation of the facial actions, such that responding was faster when they acted with the same emotional expression that they had observed. There was no difference between the two groups in the magnitude of the effect. These findings suggest that previous apparent demonstrations of impairments to the MNS in ASC may be driven by a lack of visual attention to the stimuli or motor sequencing impairments, and therefore that there is, in fact, no MNS impairment in ASC. We discuss these findings with reference to the literature on MNS functioning and imitation in ASC, as well as theories of the role of the MNS in sociocognitive functioning in typical development.

To eat or not to eat? Kinematics and muscle activity of reach-to-grasp movements are influenced by the action goal, but observers do not detect these differences

Recent evidence suggests that the mirror neuron system responds to the goals of actions, even when the end of the movement is hidden from view. To investigate whether this predictive ability might be based on the detection of early differences between actions with different outcomes, we used electromyography (EMG) and motion tracking to assess whether two actions with different goals (grasp to eat and grasp to place) differed from each other in their initial reaching phases. In a second experiment, we then tested whether observers could detect early differences and predict the outcome of these movements, based on seeing only part of the actions. Experiment 1 revealed early kinematic differences between the two movements, with grasp-to-eat movements characterised by an earlier peak acceleration, and different grasp position, compared to grasp-to-place movements. There were also significant differences in forearm muscle activity in the reaching phase of the two actions. The behavioural data arising from Experiments 2a and 2b indicated that observers are not able to predict whether an object is going to be brought to the mouth or placed until after the grasp has been completed. This suggests that the early kinematic differences are either not visible to observers, or that they are not used to predict the end-goals of actions. These data are discussed in the context of the mirror neuron system

Dual drive series actuator

Industrial robotic manipulators can be found in most factories today. Their tasks are accomplished through actively moving, placing and assembling parts. This movement is facilitated by actuators that apply a torque in response to a command signal. The presence of friction and possibly backlash have instigated the development of sophisticated compensation and control methods in order to achieve the desired performance may that be accurate motion tracking, fast movement or in fact contact with the environment. This thesis presents a dual drive actuator design that is capable of physically linearising friction and hence eliminating the need for complex compensation algorithms. A number of mathematical models are derived that allow for the simulation of the actuator dynamics. The actuator may be constructed using geared dc motors, in which case the benefits of torque magnification is retained whilst the increased non-linear friction effects are also linearised. An additional benefit of the actuator is the high quality, low latency output position signal provided by the differencing of the two drive positions. Due to this and the linearised nature of friction, the actuator is well suited for low velocity, stop-start applications, micro-manipulation and even in hard-contact tasks. There are, however, disadvantages to its design. When idle, the device uses power whilst many other, single drive actuators do not. Also the complexity of the models mean that parameterisation is difficult. Management of start-up conditions still pose a challenge.

Technologies for Ambient intelligence: from Smart Objects to Sensor Networks

n the last few years, the vision of our connected and intelligent information society has evolved to embrace novel technological and research trends. The diffusion of ubiquitous mobile connectivity and advanced handheld portable devices, amplified the importance of the Internet as the communication backbone for the fruition of services and data. The diffusion of mobile and pervasive computing devices, featuring advanced sensing technologies and processing capabilities, triggered the adoption of innovative interaction paradigms: touch responsive surfaces, tangible interfaces and gesture or voice recognition are finally entering our homes and workplaces. We are experiencing the proliferation of smart objects and sensor networks, embedded in our daily living and interconnected through the Internet. This ubiquitous network of always available interconnected devices is enabling new applications and services, ranging from enhancements to home and office environments, to remote healthcare assistance and the birth of a smart environment. This work will present some evolutions in the hardware and software development of embedded systems and sensor networks. Different hardware solutions will be introduced, ranging from smart objects for interaction to advanced inertial sensor nodes for motion tracking, focusing on system-level design. They will be accompanied by the study of innovative data processing algorithms developed and optimized to run on-board of the embedded devices. Gesture recognition, orientation estimation and data reconstruction techniques for sensor networks will be introduced and implemented, with the goal to maximize the tradeoff between performance and energy efficiency. Experimental results will provide an evaluation of the accuracy of the presented methods and validate the efficiency of the proposed embedded systems.

Efficient subsequence alignment of time series

Zeitreihen sind allgegenwärtig. Die Erfassung und Verarbeitung kontinuierlich gemessener Daten ist in allen Bereichen der Naturwissenschaften, Medizin und Finanzwelt vertreten. Das enorme Anwachsen aufgezeichneter Datenmengen, sei es durch automatisierte Monitoring-Systeme oder integrierte Sensoren, bedarf außerordentlich schneller Algorithmen in Theorie und Praxis. Infolgedessen beschäftigt sich diese Arbeit mit der effizienten Berechnung von Teilsequenzalignments. Komplexe Algorithmen wie z.B. Anomaliedetektion, Motivfabfrage oder die unüberwachte Extraktion von prototypischen Bausteinen in Zeitreihen machen exzessiven Gebrauch von diesen Alignments. Darin begründet sich der Bedarf nach schnellen Implementierungen. Diese Arbeit untergliedert sich in drei Ansätze, die sich dieser Herausforderung widmen. Das umfasst vier Alignierungsalgorithmen und ihre Parallelisierung auf CUDA-fähiger Hardware, einen Algorithmus zur Segmentierung von Datenströmen und eine einheitliche Behandlung von Liegruppen-wertigen Zeitreihen.rnrnDer erste Beitrag ist eine vollständige CUDA-Portierung der UCR-Suite, die weltführende Implementierung von Teilsequenzalignierung. Das umfasst ein neues Berechnungsschema zur Ermittlung lokaler Alignierungsgüten unter Verwendung z-normierten euklidischen Abstands, welches auf jeder parallelen Hardware mit Unterstützung für schnelle Fouriertransformation einsetzbar ist. Des Weiteren geben wir eine SIMT-verträgliche Umsetzung der Lower-Bound-Kaskade der UCR-Suite zur effizienten Berechnung lokaler Alignierungsgüten unter Dynamic Time Warping an. Beide CUDA-Implementierungen ermöglichen eine um ein bis zwei Größenordnungen schnellere Berechnung als etablierte Methoden.rnrnAls zweites untersuchen wir zwei Linearzeit-Approximierungen für das elastische Alignment von Teilsequenzen. Auf der einen Seite behandeln wir ein SIMT-verträgliches Relaxierungschema für Greedy DTW und seine effiziente CUDA-Parallelisierung. Auf der anderen Seite führen wir ein neues lokales Abstandsmaß ein, den Gliding Elastic Match (GEM), welches mit der gleichen asymptotischen Zeitkomplexität wie Greedy DTW berechnet werden kann, jedoch eine vollständige Relaxierung der Penalty-Matrix bietet. Weitere Verbesserungen umfassen Invarianz gegen Trends auf der Messachse und uniforme Skalierung auf der Zeitachse. Des Weiteren wird eine Erweiterung von GEM zur Multi-Shape-Segmentierung diskutiert und auf Bewegungsdaten evaluiert. Beide CUDA-Parallelisierung verzeichnen Laufzeitverbesserungen um bis zu zwei Größenordnungen.rnrnDie Behandlung von Zeitreihen beschränkt sich in der Literatur in der Regel auf reellwertige Messdaten. Der dritte Beitrag umfasst eine einheitliche Methode zur Behandlung von Liegruppen-wertigen Zeitreihen. Darauf aufbauend werden Distanzmaße auf der Rotationsgruppe SO(3) und auf der euklidischen Gruppe SE(3) behandelt. Des Weiteren werden speichereffiziente Darstellungen und gruppenkompatible Erweiterungen elastischer Maße diskutiert.

Development and characterization of a scaffold-free 3D spheroid model of iPSC-derived human cardiomyocytes

Purpose: Cardiomyocytes are terminally differentiated cells in the adult heart and ischemia and cardiotoxic compounds can lead to cell death and irreversible decline of cardiac function. As testing platforms, isolated organs and primary cells from rodents have been the standard in research and toxicology, but there is a need for better models that more faithfully recapitulate native human biology. Hence, a new in vitro model comprising the advantages of 3D cell culture and the availability of induced pluripotent stem cells (iPSC) from human origin was developed and characterized. Methods: Human cardiomyocytes (CMs) derived from induced pluripotent stem cells (iPSCs) were studied in standard 2D culture and as cardiac microtissues (MTs) formed in hanging drops. 2D cultures were examined using immunofluorescence microscopy and Western blotting while the cardiac MTs were subjected to immunofluorescence, contractility, and pharmacological investigations. Results: iPSC-derived CMs in 2D culture showed well-formed myofibrils, cell-cell contacts positive for connexin-43, and other typical cardiac proteins. The cells reacted to pro-hypertrophic growth factors with a substantial increase in myofibrils and sarcomeric proteins. In hanging drop cultures, iPSC-derived cardiomyocytes formed spheroidal MTs within 4 days showing a homogeneous tissue structure with well-developed myofibrils extending throughout the whole spheroid without a necrotic core. MTs showed spontaneous contractions for more than 4 weeks that were recorded by optical motion tracking, sensitive to temperature, and responsive to electrical pacing. Contractile pharmacology was tested with several agents known to modulate cardiac rate and viability. Calcium-transients underlay the contractile activity and were also responsive to electrical stimulation, caffeine-induced Ca2+-release, extracellular calcium levels. Conclusions: 3D culture using iPSC-derived human cardiomyocytes provides an organoid human-based cellular platform that is free of necrosis and recapitulates vital cardiac functionality, thereby providing new and promising relevant model for the evaluation and development of new therapies and detection of cardiotoxicity.

Development and implementation of a dynamic heterogeneous proton equivalent anthropomorphic thorax phantom for the assessment of scanned proton beam therapy

DEVELOPMENT AND IMPLEMENTATION OF A DYNAMIC HETEROGENEOUS PROTON EQUIVALENT ANTHROPOMORPHIC THORAX PHANTOM FOR THE ASSESSMENT OF SCANNED PROTON BEAM THERAPY by James Leroy Neihart, B.S. APPROVED: ______________________________David Followill, Ph.D. ______________________________Peter Balter, Ph.D. ______________________________Narayan Sahoo, Ph.D. ______________________________Kenneth Hess, Ph.D. ______________________________Paige Summers, M.S. APPROVED: ____________________________ Dean, The University of Texas Graduate School of Biomedical Sciences at Houston DEVELOPMENT AND IMPLEMENTATION OF A DYNAMIC HETEROGENEOUS PROTON EQUIVALENT ANTHROPOMORPHIC THORAX PHANTOM FOR THE ASSESSMENT OF SCANNED PROTON BEAM THERAPY A THESIS Presented to the Faculty of The University of Texas Health Science Center at Houston andThe University of TexasMD Anderson Cancer CenterGraduate School of Biomedical Sciences in Partial Fulfillment of the Requirements for the Degree of MASTER OF SCIENCE by James Leroy Neihart, B.S. Houston, Texas Date of Graduation August, 2013 Acknowledgments I would like to acknowledge my advisory committee members, chair David Followill, Ph.D., Peter Balter, Ph.D, Narayan Sahoo, Ph.D., Kenneth Hess, Ph.D., Paige Summers M.S. and, for their time and effort contributed to this project. I would additionally like to thank the faculty and staff at the PTC-H and the RPC who assisted in many aspects of this project. Falk Pӧnisch, Ph.D. for his breath hold proton therapy treatment expertise, Matt Palmer and Jaques Bluett for proton dosimetry assistance, Matt Kerr for verification plan assistance, Carrie Amador, Nadia Hernandez, Trang Nguyen, Andrea Molineu, Lynda McDonald for TLD and film dosimetry assistance. Finally, I would like to thank my wife and family for their support and encouragement during my research and studies. Development and implementation of a dynamic heterogeneous proton equivalent anthropomorphic thorax phantom for the assessment of scanned proton beam therapy By: James Leroy Neihart, B.S. Chair of Advisory Committee: David Followill, Ph.D Proton therapy has been gaining ground recently in radiation oncology. To date, the most successful utilization of proton therapy is in head and neck cases as well as prostate cases. These tumor locations do not suffer from the resulting difficulties of treatment delivery as a result of respiratory motion. Lung tumors require either breath hold or motion tracking, neither of which have been assessed with an end-to-end phantom for proton treatments. Currently, the RPC does not have a dynamic thoracic phantom for proton therapy procedure assessment. Additionally, such a phantom could be an excellent means of assessing quality assurance of the procedures of proton therapy centers wishing to participate in clinical trials. An eventual goal of this phantom is to have a means of evaluating and auditing institutions for the ability to start clinical trials utilizing proton therapy procedures for lung cancers. Therefore, the hypothesis of this study is that a dynamic anthropomorphic thoracic phantom can be created to evaluate end-to-end proton therapy treatment procedures for lung cancer to assure agreement between the measured and calculated dose within 5% / 5 mm with a reproducibility of 2%. Multiple materials were assessed for thoracic heterogeneity equivalency. The phantom was designed from the materials found to be in greatest agreement. The phantom was treated in an end-to-end treatment four times, which included simulation, treatment planning and treatment delivery. Each treatment plan was delivered three times to assess reproducibility. The dose measured within the phantom was compared to that of the treatment plan. The hypothesis was fully supported for three of the treatment plans, but failed the reproducibility requirement for the most aggressive treatment plan.

Use of Costas arrays in subpixel metrology

Subpixel methods increase the accuracy and efficiency of image detectors, processing units, and algorithms and provide very cost-effective systems for object tracking. A recently proposed method permits micropixel and submicropixel accuracies providing certain design constraints on the target are met. In this paper, we explore the use of Costas arrays - permutation matrices with ideal auto-ambiguity properties - for the design of such targets.

Force sensing for measuring human body movement

The research developed in this thesis explores the sensing and inference of human movement in a dynamic way, as opposed to conventional measurement systems, that are only concerned with discrete evaluations of stimuli in sequential time. Typically, conventional approaches are used to infer the dynamic movement of the body; such as vision and motion tracking devices, with either a human diagnosis or complex image processing algorithm to classify the movement. This research is therefore the first of its kind to attempt and provide a movement classifying algorithm through the use of minimal sensing points, with the application for this novel system, to classify human movement during a golf swing. There are two main categories of force sensing. Firstly, array-type systems consisting of many sensing elements, and are the most commonly researched and commercially available. Secondly, reduced force sensing element systems (RFSES) also known as distributive systems have only been recently exploited in the academic world. The fundamental difference between these systems is that array systems handle the data captured from each sensor as unique outputs and suffer the effects of resolution. The effect of resolution, is the error in the load position measurement between sensing elements, as the output is quantized in terms of position. This can be compared to a reduced sensor element system that maximises that data received through the coupling of data from a distribution of sensing points to describe the output in discrete time. Also this can be extended to a coupling of transients in the time domain to describe an activity or dynamic movement. It is the RFSES that is to be examined and exploited in the commercial sector due to its advantages over array-based approaches such as reduced design, computational complexity and cost.

The functional subdivision of the visual brain : Is there a real illusion effect on action? A multi-lab replication study

Acknowledgements We thank Brian Roberts and Mike Harris for responding to our questions regarding their paper; Zoltan Dienes for advice on Bayes factors; Denise Fischer, Melanie Römer, Ioana Stanciu, Aleksandra Romanczuk, Stefano Uccelli, Nuria Martos Sánchez, and Rosa María Beño Ruiz de la Sierra for help collecting data; Eva Viviani for managing data collection in Parma. We thank Maurizio Gentilucci for letting us use his lab, and the Centro Intradipartimentale Mente e Cervello (CIMeC), University of Trento, and especially Francesco Pavani for lending us his motion tracking equipment. We thank Rachel Foster for proofreading. KKK was supported by a Ph.D. scholarship as part of a grant to VHF within the International Graduate Research Training Group on Cross-Modal Interaction in Natural and Artificial Cognitive Systems (CINACS; DFG IKG-1247) and TS by a grant (DFG – SCHE 735/3-1); both from the German Research Council.

Prospective motion correction of 3D echo-planar imaging data for functional MRI using optical tracking.

We evaluated the performance of an optical camera based prospective motion correction (PMC) system in improving the quality of 3D echo-planar imaging functional MRI data. An optical camera and external marker were used to dynamically track the head movement of subjects during fMRI scanning. PMC was performed by using the motion information to dynamically update the sequence's RF excitation and gradient waveforms such that the field-of-view was realigned to match the subject's head movement. Task-free fMRI experiments on five healthy volunteers followed a 2×2×3 factorial design with the following factors: PMC on or off; 3.0mm or 1.5mm isotropic resolution; and no, slow, or fast head movements. Visual and motor fMRI experiments were additionally performed on one of the volunteers at 1.5mm resolution comparing PMC on vs PMC off for no and slow head movements. Metrics were developed to quantify the amount of motion as it occurred relative to k-space data acquisition. The motion quantification metric collapsed the very rich camera tracking data into one scalar value for each image volume that was strongly predictive of motion-induced artifacts. The PMC system did not introduce extraneous artifacts for the no motion conditions and improved the time series temporal signal-to-noise by 30% to 40% for all combinations of low/high resolution and slow/fast head movement relative to the standard acquisition with no prospective correction. The numbers of activated voxels (p<0.001, uncorrected) in both task-based experiments were comparable for the no motion cases and increased by 78% and 330%, respectively, for PMC on versus PMC off in the slow motion cases. The PMC system is a robust solution to decrease the motion sensitivity of multi-shot 3D EPI sequences and thereby overcome one of the main roadblocks to their widespread use in fMRI studies.

Quantitative analysis of accuracy of an inertial/acoustic 6DOF tracking system in motion

An increasing number of neuroscience experiments are using virtual reality to provide a more immersive and less artificial experimental environment. This is particularly useful to navigation and three-dimensional scene perception experiments. Such experiments require accurate real-time tracking of the observer's head in order to render the virtual scene. Here, we present data on the accuracy of a commonly used six degrees of freedom tracker (Intersense IS900) when it is moved in ways typical of virtual reality applications. We compared the reported location of the tracker with its location computed by an optical tracking method. When the tracker was stationary, the root mean square error in spatial accuracy was 0.64 mm. However, we found that errors increased over ten-fold (up to 17 mm) when the tracker moved at speeds common in virtual reality applications. We demonstrate that the errors we report here are predominantly due to inaccuracies of the IS900 system rather than the optical tracking against which it was compared. (c) 2006 Elsevier B.V. All rights reserved.

Application of a hybrid tracking algorithm to motion analysis

An algorithm for tracking multiple feature positions in a dynamic image sequence is presented. This is achieved using a combination of two trajectory-based methods, with the resulting hybrid algorithm exhibiting the advantages of both. An optimizing exchange algorithm is described which enables short feature paths to be tracked without prior knowledge of the motion being studied. The resulting partial trajectories are then used to initialize a fast predictor algorithm which is capable of rapidly tracking multiple feature paths. As this predictor algorithm becomes tuned to the feature positions being tracked, it is shown how the location of occluded or poorly detected features can be predicted. The results of applying this tracking algorithm to data obtained from real-world scenes are then presented.