Dissertations / Theses on the topic 'Human Motion Data Analysis'

Human motion analysis is one of the major problems in computer vision research. It deals with the study of the motion of human body in video data from different aspects, ranging from the tracking of body parts and reconstruction of 3D human body configuration, to higher level of interpretation of human action and activities in image sequences. When human motion is observed through video camera, it is perspectively distorted and may appear totally different from different viewpoints. Therefore it is highly challenging to establish correct relationships between human motions across video sequences with different camera settings. In this work, we investigate the geometric invariance in the motion of human body, which is critical to accurately understand human motion in video data regardless of variations in camera parameters and viewpoints. In human action analysis, the representation of human action is a very important issue, and it usually determines the nature of the solutions, including their limits in resolving the problem. Unlike existing research that study human motion as a whole 2D/3D object or a sequence of postures, we study human motion as a sequence of body pose transitions. We also decompose a human body pose further into a number of body point triplets, and break down a pose transition into the transition of a set of body point triplets. In this way the study of complex non-rigid motion of human body is reduced to that of the motion of rigid body point triplets, i.e. a collection of planes in motion. As a result, projective geometry and linear algebra can be applied to explore the geometric invariance in human motion. Based on this formulation, we have discovered the fundamental ratio invariant and the eigenvalue equality invariant in human motion. We also propose solutions based on these geometric invariants to the problems of view-invariant recognition of human postures and actions, as well as analysis of human motion styles. These invariants and their applicability have been validated by experimental results supporting that their effectiveness in understanding human motion with various camera parameters and viewpoints.
Ph.D.
School of Electrical Engineering and Computer Science
Engineering and Computer Science
Computer Science PhD

This thesis presents a new human-like upper limb and hand motion generating method. The work is based on Functional Principal Component Analysis and Quadratic Programming. The human-like motion generating problem is formulated in a framework of minimizing the difference of the dynamic profile of the optimal trajectory and the known types of trajectory. Statistical analysis is applied to the pre-captured human motion records to work in a low dimensional space. A novel PCA FPCA hybrid motion recognition method is proposed. This method is implemented on human grasping data to demonstrate its advantage in human motion recognition. One human grasping hierarchy is also proposed during the study. The proposed method of generating human-like upper limb and hand motion explores the ability to learn the motion kernels from human demonstration. Issues in acquiring motion kernels are also discussed. The trajectory planning method applies different weight on the extracted motion kernels to approximate the kinematic constraints of the task. Multiple means of evaluation are implemented to illustrate the quality of the generated optimal human-like trajectory compared to the real human motion records.

With the recent advent of Web 2.0, mobile computing, and pervasive sensing technologies, human activities can readily be logged, leaving digital traces of di.erent forms. For instance, human communication activities recorded in online social networks allow user interactions to be represented as “network” data. Also, human daily activities can be tracked in a smart house, where the log of sensor triggering events can be represented as “sequence” data. This thesis research aims to develop computational data mining algorithms using the generative modeling approach to extract salient patterns (motifs) embedded in such network and sequence data, and to apply them for human behavior analysis. Motifs are de.ned as the recurrent over-represented patterns embedded in the data, and have been known to be e.ective for characterizing complex networks. Many motif extraction methods found in the literature assume that a motif is either present or absent. In real practice, such salient patterns can appear partially due to their stochastic nature and/or the presence of noise. Thus, the probabilistic approach is adopted in this thesis to model motifs. For network data, we use a probability matrix to represent a network motif and propose a mixture model to extract network motifs. A component-wise EM algorithm is adopted where the optimal number of stochastic motifs is automatically determined with the help of a minimum message length criterion. Considering also the edge occurrence ordering within a motif, we model a motif as a mixture of .rst-order Markov chains for the extraction. Using a probabilistic approach similar to the one for network motif, an optimal set of stochastic temporal network motifs are extracted. We carried out rigorous experiments to evaluate the performance of the proposed motif extraction algorithms using both synthetic data sets and real-world social network data sets and mobile phone usage data sets, and obtained promising results. Also, we found that some of the results can be interpreted using the social balance and social status theories which are well-known in social network analysis. To evaluate the e.ectiveness of adopting stochastic temporal network motifs for not only characterizing human behaviors, we incorporate stochastic temporal network motifs as local structural features into a factor graph model for followee recommendation prediction (essentially a link prediction problem) in online social networks. The proposed motif-based factor graph model is found to outperform signi.cantly the existing state-of-the-art methods for the prediction task. For extract motifs from sequence data, the probabilistic framework proposed for the stochastic temporal network motif extraction is also applicable. One possible way is to make use of the edit distance in the probabilistic framework so that the subsequences with minor ordering variations can .rst be grouped to form the initial set of motif candidates. A mixture model can then be used to determine the optimal set of temporal motifs. We applied this approach to extract sequence motifs from a smart home data set which contains sensor triggering events corresponding to some activities performed by residents in the smart home. The unique behavior extracted for each resident based on the detected motifs is also discussed. Keywords: Stochastic network motifs, .nite mixture models, expectation maxi­mization algorithms, social networks, stochastic temporal network motifs, mixture of Markov chains, human behavior analysis, followee recommendation, signed social networks, activity of daily living, smart environments

Animation of human motion is one of the most challenging topics in computer graphics. This is due to the large number of degrees of freedom of the body and to our ability to detect unnatural motion. Keyframing and interpolation remains the form of animation that is preferred by most animators because of the control and flexibility it provides. However this is a labour intensive process that requires skills that take years to acquire. Human motion capture techniques provide accurate measurement of the motion of a performer that can be mapped onto an animated character to provide strikingly natural animation. This raises the problem of how to allow an animator to modify captured movement to produce a desired animation whilst preserving the natural quality. This thesis introduces a new approach to the animation of human motion based on combining the flexibility of keyframing with the visual quality of motion capture data. In particular it addresses the problem of synthesising natural inbetween motion for sparse keyframes. This thesis proposes to obtain this motion by sampling high quality human motion capture data. The problem of keyframe interpolation is formulated as a search problem in a graph. This presents two difficulties: The complexity of the search makes it impractical for the large databases of motion capture required to model human motion. The second difficulty is that the global temporal structure in the data may not be preserved in the search. To address these difficulties this thesis introduces a layered framework that both reduces the complexity of the search and preserves the global temporal structure of the data. The first layer is a simplification of the graph obtained by clustering methods. This layer enables efficient planning of the search for a path between start and end keyframes. The second layer directly samples segments of the original motion data to synthesise realistic inbetween motion for the keyframes. A number of additional contributions are made including novel representations for human motion, pose similarity cost functions, dynamic programming algorithms for efficient search and quantitative evaluation methods. Results of realistic inbetween motion are presented with databases of up to 120 sequences (35000 frames). Key words: Human Motion Synthesis, Motion Capture, Character Animation, Graph Search, Clustering, Unsupervised Learning, Markov Models, Dynamic Programming.

Human motion analysis is a very important task for computer vision with a spectrum of potential applications. This thesis presents a novel approach to the problem of human motion understanding. The main contribution of the thesis is that fuzzy qualitative description has been developed for studying human motion from image sequences.

Die dreidimensionale Erfassung der Form und Lage eines beliebigen Objekts durch die flexiblen Methoden und Verfahren der Photogrammetrie spielt für ein breites Spektrum technisch-industrieller und naturwissenschaftlicher Einsatzgebiete eine große Rolle. Die Anwendungsmöglichkeiten reichen von Messaufgaben im Automobil-, Maschinen- und Schiffbau über die Erstellung komplexer 3D-Modelle in Architektur, Archäologie und Denkmalpflege bis hin zu Bewegungsanalysen in Bereichen der Strömungsmesstechnik, Ballistik oder Medizin. In der Nahbereichsphotogrammetrie werden dabei verschiedene optische 3D-Messsysteme verwendet. Neben flächenhaften Halbleiterkameras im Einzel- oder Mehrbildverband kommen aktive Triangulationsverfahren zur Oberflächenmessung mit z.B. strukturiertem Licht oder Laserscanner-Systeme zum Einsatz. 3D-Kameras auf der Basis von Photomischdetektoren oder vergleichbaren Prinzipien erzeugen durch die Anwendung von Modulationstechniken zusätzlich zu einem Grauwertbild simultan ein Entfernungsbild. Als Einzelbildsensoren liefern sie ohne die Notwendigkeit einer stereoskopischen Zuordnung räumlich aufgelöste Oberflächendaten in Videorate. In der 3D-Bewegungsanalyse ergeben sich bezüglich der Komplexität und des Rechenaufwands erhebliche Erleichterungen. 3D-Kameras verbinden die Handlichkeit einer Digitalkamera mit dem Potential der dreidimensionalen Datenakquisition etablierter Oberflächenmesssysteme. Sie stellen trotz der noch vergleichsweise geringen räumlichen Auflösung als monosensorielles System zur Echtzeit-Tiefenbildakquisition eine interessante Alternative für Aufgabenstellungen der 3D-Bewegungsanalyse dar. Der Einsatz einer 3D-Kamera als Messinstrument verlangt die Modellierung von Abweichungen zum idealen Abbildungsmodell; die Verarbeitung der erzeugten 3D-Kameradaten bedingt die zielgerichtete Adaption, Weiter- und Neuentwicklung von Verfahren der Computer Vision und Photogrammetrie. Am Beispiel der Untersuchung des zwischenmenschlichen Bewegungsverhaltens sind folglich die Entwicklung von Verfahren zur Sensorkalibrierung und zur 3D-Bewegungsanalyse die Schwerpunkte der Dissertation. Eine 3D-Kamera stellt aufgrund ihres inhärenten Designs und Messprinzips gleichzeitig Amplituden- und Entfernungsinformationen zur Verfügung, welche aus einem Messsignal rekonstruiert werden. Die simultane Einbeziehung aller 3D-Kamerainformationen in jeweils einen integrierten Ansatz ist eine logische Konsequenz und steht im Vordergrund der Verfahrensentwicklungen. Zum einen stützen sich die komplementären Eigenschaften der Beobachtungen durch die Herstellung des funktionalen Zusammenhangs der Messkanäle gegenseitig, wodurch Genauigkeits- und Zuverlässigkeitssteigerungen zu erwarten sind. Zum anderen gewährleistet das um eine Varianzkomponentenschätzung erweiterte stochastische Modell eine vollständige Ausnutzung des heterogenen Informationshaushalts. Die entwickelte integrierte Bündelblockausgleichung ermöglicht die Bestimmung der exakten 3D-Kamerageometrie sowie die Schätzung der distanzmessspezifischen Korrekturparameter zur Modellierung linearer, zyklischer und signalwegeffektbedingter Fehleranteile einer 3D-Kamerastreckenmessung. Die integrierte Kalibrierroutine gleicht in beiden Informationskanälen gemessene Größen gemeinsam, unter der automatischen Schätzung optimaler Beobachtungsgewichte, aus. Die Methode basiert auf dem flexiblen Prinzip einer Selbstkalibrierung und benötigt keine Objektrauminformation, wodurch insbesondere die aufwendige Ermittlung von Referenzstrecken übergeordneter Genauigkeit entfällt. Die durchgeführten Genauigkeitsuntersuchungen bestätigen die Richtigkeit der aufgestellten funktionalen Zusammenhänge, zeigen aber auch Schwächen aufgrund noch nicht parametrisierter distanzmessspezifischer Fehler. Die Adaptivität und die modulare Implementierung des entwickelten mathematischen Modells gewährleisten aber eine zukünftige Erweiterung. Die Qualität der 3D-Neupunktkoordinaten kann nach einer Kalibrierung mit 5 mm angegeben werden. Für die durch eine Vielzahl von meist simultan auftretenden Rauschquellen beeinflusste Tiefenbildtechnologie ist diese Genauigkeitsangabe sehr vielversprechend, vor allem im Hinblick auf die Entwicklung von auf korrigierten 3D-Kameradaten aufbauenden Auswertealgorithmen. 2,5D Least Squares Tracking (LST) ist eine im Rahmen der Dissertation entwickelte integrierte spatiale und temporale Zuordnungsmethode zur Auswertung von 3D-Kamerabildsequenzen. Der Algorithmus basiert auf der in der Photogrammetrie bekannten Bildzuordnung nach der Methode der kleinsten Quadrate und bildet kleine Oberflächensegmente konsekutiver 3D-Kameradatensätze aufeinander ab. Die Abbildungsvorschrift wurde, aufbauend auf einer 2D-Affintransformation, an die Datenstruktur einer 3D-Kamera angepasst. Die geschlossen formulierte Parametrisierung verknüpft sowohl Grau- als auch Entfernungswerte in einem integrierten Modell. Neben den affinen Parametern zur Erfassung von Translations- und Rotationseffekten, modellieren die Maßstabs- sowie Neigungsparameter perspektivbedingte Größenänderungen des Bildausschnitts, verursacht durch Distanzänderungen in Aufnahmerichtung. Die Eingabedaten sind in einem Vorverarbeitungsschritt mit Hilfe der entwickelten Kalibrierroutine um ihre opto- und distanzmessspezifischen Fehler korrigiert sowie die gemessenen Schrägstrecken auf Horizontaldistanzen reduziert worden. 2,5D-LST liefert als integrierter Ansatz vollständige 3D-Verschiebungsvektoren. Weiterhin können die aus der Fehlerrechnung resultierenden Genauigkeits- und Zuverlässigkeitsangaben als Entscheidungskriterien für die Integration in einer anwendungsspezifischen Verarbeitungskette Verwendung finden. Die Validierung des Verfahrens zeigte, dass die Einführung komplementärer Informationen eine genauere und zuverlässigere Lösung des Korrespondenzproblems bringt, vor allem bei schwierigen Kontrastverhältnissen in einem Kanal. Die Genauigkeit der direkt mit den Distanzkorrekturtermen verknüpften Maßstabs- und Neigungsparameter verbesserte sich deutlich. Darüber hinaus brachte die Erweiterung des geometrischen Modells insbesondere bei der Zuordnung natürlicher, nicht gänzlich ebener Oberflächensegmente signifikante Vorteile. Die entwickelte flächenbasierte Methode zur Objektzuordnung und Objektverfolgung arbeitet auf der Grundlage berührungslos aufgenommener 3D-Kameradaten. Sie ist somit besonders für Aufgabenstellungen der 3D-Bewegungsanalyse geeignet, die den Mehraufwand einer multiokularen Experimentalanordnung und die Notwendigkeit einer Objektsignalisierung mit Zielmarken vermeiden möchten. Das Potential des 3D-Kamerazuordnungsansatzes wurde an zwei Anwendungsszenarien der menschlichen Verhaltensforschung demonstriert. 2,5D-LST kam zur Bestimmung der interpersonalen Distanz und Körperorientierung im erziehungswissenschaftlichen Untersuchungsgebiet der Konfliktregulation befreundeter Kindespaare ebenso zum Einsatz wie zur Markierung und anschließenden Klassifizierung von Bewegungseinheiten sprachbegleitender Handgesten. Die Implementierung von 2,5D-LST in die vorgeschlagenen Verfahren ermöglichte eine automatische, effektive, objektive sowie zeitlich und räumlich hochaufgelöste Erhebung und Auswertung verhaltensrelevanter Daten. Die vorliegende Dissertation schlägt die Verwendung einer neuartigen 3D-Tiefenbildkamera zur Erhebung menschlicher Verhaltensdaten vor. Sie präsentiert sowohl ein zur Datenaufbereitung entwickeltes Kalibrierwerkzeug als auch eine Methode zur berührungslosen Bestimmung dichter 3D-Bewegungsvektorfelder. Die Arbeit zeigt, dass die Methoden der Photogrammetrie auch für bewegungsanalytische Aufgabenstellungen auf dem bisher noch wenig erschlossenen Gebiet der Verhaltensforschung wertvolle Ergebnisse liefern können. Damit leistet sie einen Beitrag für die derzeitigen Bestrebungen in der automatisierten videographischen Erhebung von Körperbewegungen in dyadischen Interaktionen
The three-dimensional documentation of the form and location of any type of object using flexible photogrammetric methods and procedures plays a key role in a wide range of technical-industrial and scientific areas of application. Potential applications include measurement tasks in the automotive, machine building and ship building sectors, the compilation of complex 3D models in the fields of architecture, archaeology and monumental preservation and motion analyses in the fields of flow measurement technology, ballistics and medicine. In the case of close-range photogrammetry a variety of optical 3D measurement systems are used. Area sensor cameras arranged in single or multi-image configurations are used besides active triangulation procedures for surface measurement (e.g. using structured light or laser scanner systems). The use of modulation techniques enables 3D cameras based on photomix detectors or similar principles to simultaneously produce both a grey value image and a range image. Functioning as single image sensors, they deliver spatially resolved surface data at video rate without the need for stereoscopic image matching. In the case of 3D motion analyses in particular, this leads to considerable reductions in complexity and computing time. 3D cameras combine the practicality of a digital camera with the 3D data acquisition potential of conventional surface measurement systems. Despite the relatively low spatial resolution currently achievable, as a monosensory real-time depth image acquisition system they represent an interesting alternative in the field of 3D motion analysis. The use of 3D cameras as measuring instruments requires the modelling of deviations from the ideal projection model, and indeed the processing of the 3D camera data generated requires the targeted adaptation, development and further development of procedures in the fields of computer graphics and photogrammetry. This Ph.D. thesis therefore focuses on the development of methods of sensor calibration and 3D motion analysis in the context of investigations into inter-human motion behaviour. As a result of its intrinsic design and measurement principle, a 3D camera simultaneously provides amplitude and range data reconstructed from a measurement signal. The simultaneous integration of all data obtained using a 3D camera into an integrated approach is a logical consequence and represents the focus of current procedural development. On the one hand, the complementary characteristics of the observations made support each other due to the creation of a functional context for the measurement channels, with is to be expected to lead to increases in accuracy and reliability. On the other, the expansion of the stochastic model to include variance component estimation ensures that the heterogeneous information pool is fully exploited. The integrated bundle adjustment developed facilitates the definition of precise 3D camera geometry and the estimation of range-measurement-specific correction parameters required for the modelling of the linear, cyclical and latency defectives of a distance measurement made using a 3D camera. The integrated calibration routine jointly adjusts appropriate dimensions across both information channels, and also automatically estimates optimum observation weights. The method is based on the same flexible principle used in self-calibration, does not require spatial object data and therefore foregoes the time-consuming determination of reference distances with superior accuracy. The accuracy analyses carried out confirm the correctness of the proposed functional contexts, but nevertheless exhibit weaknesses in the form of non-parameterized range-measurement-specific errors. This notwithstanding, the future expansion of the mathematical model developed is guaranteed due to its adaptivity and modular implementation. The accuracy of a new 3D point coordinate can be set at 5 mm further to calibration. In the case of depth imaging technology – which is influenced by a range of usually simultaneously occurring noise sources – this level of accuracy is very promising, especially in terms of the development of evaluation algorithms based on corrected 3D camera data. 2.5D Least Squares Tracking (LST) is an integrated spatial and temporal matching method developed within the framework of this Ph.D. thesis for the purpose of evaluating 3D camera image sequences. The algorithm is based on the least squares image matching method already established in photogrammetry, and maps small surface segments of consecutive 3D camera data sets on top of one another. The mapping rule has been adapted to the data structure of a 3D camera on the basis of a 2D affine transformation. The closed parameterization combines both grey values and range values in an integrated model. In addition to the affine parameters used to include translation and rotation effects, the scale and inclination parameters model perspective-related deviations caused by distance changes in the line of sight. A pre-processing phase sees the calibration routine developed used to correct optical and distance-related measurement specific errors in input data and measured slope distances reduced to horizontal distances. 2.5D LST is an integrated approach, and therefore delivers fully three-dimensional displacement vectors. In addition, the accuracy and reliability data generated by error calculation can be used as decision criteria for integration into an application-specific processing chain. Process validation showed that the integration of complementary data leads to a more accurate, reliable solution to the correspondence problem, especially in the case of difficult contrast ratios within a channel. The accuracy of scale and inclination parameters directly linked to distance correction terms improved dramatically. In addition, the expansion of the geometric model led to significant benefits, and in particular for the matching of natural, not entirely planar surface segments. The area-based object matching and object tracking method developed functions on the basis of 3D camera data gathered without object contact. It is therefore particularly suited to 3D motion analysis tasks in which the extra effort involved in multi-ocular experimental settings and the necessity of object signalling using target marks are to be avoided. The potential of the 3D camera matching approach has been demonstrated in two application scenarios in the field of research into human behaviour. As in the case of the use of 2.5D LST to mark and then classify hand gestures accompanying verbal communication, the implementation of 2.5D LST in the proposed procedures for the determination of interpersonal distance and body orientation within the framework of pedagogical research into conflict regulation between pairs of child-age friends facilitates the automatic, effective, objective and high-resolution (from both a temporal and spatial perspective) acquisition and evaluation of data with relevance to behaviour. This Ph.D. thesis proposes the use of a novel 3D range imaging camera to gather data on human behaviour, and presents both a calibration tool developed for data processing purposes and a method for the contact-free determination of dense 3D motion vector fields. It therefore makes a contribution to current efforts in the field of the automated videographic documentation of bodily motion within the framework of dyadic interaction, and shows that photogrammetric methods can also deliver valuable results within the framework of motion evaluation tasks in the as-yet relatively untapped field of behavioural research

Human motion analysis is as a broad area of computer vision that has strongly attracted the interest of researchers in the last decades. Motion analysis covers topics such as human motion tracking and estimation, action and behavior recognition or segmentation of human motion. All these fields are challenging due to different reasons, but mostly because of viewing perspectives, clutter and the imprecise semantics of actions and human motion. The computer vision community has addressed human motion analysis from several perspectives. Earlier approaches often relied on articulated human body models represented in the three-dimensional world. However, due to the traditionally high difficulty and cost of estimating such an articulated structure from video, research has focus on the development of human motion analysis approaches relying on low-level features. Although obtaining impressive results in several tasks, low-level features are typically conditioned by appearance and viewpoint, thus making difficult their application on different scenarios. Nonetheless, the increase in computational power, the massive availability of data and the irruption of consumer-depth cameras is changing the scenario, and with that change human motion analysis through articulated models can be reconsidered. Analyzing and understanding of human motion through 3-dimensional information is still a crucial issue in order to obtain richer models of dynamics and behavior. In that sense, articulated models of the human body offer a compact and view-invariant representation of motion that can be used to leverage motion analysis. In this dissertation, we present several approaches for motion analysis. In particular, we address the problem of pose inference, action recognition and temporal clustering of human motion. Articulated models are the leitmotiv in all the presented approaches. Firstly, we address pose inference by formulating a layered analysis-by-synthesis framework where models are used to generate hypothesis that are matched against video. Based on the same articulated representation upon which models are built, we propose an action recognition framework. Actions are seen as time-series observed through the articulated model and generated by underlying dynamical systems that we hypothesize that are generating the time-series. Such an hypothesis is used in order to develop recognition methods based on time-delay embeddings, which are analysis tools that do not make assumptions on the form of the form of the underlying dynamical system. Finally, we propose a method to cluster human motion sequences into distinct behaviors, without a priori knowledge of the number of actions in the sequence. Our approach relies on the articulated model representation in order to learn a distance metric from pose data. This metric aims at capturing semantics from labeled data in order to cluster unseen motion sequences into meaningful behaviors. The proposed approaches are evaluated using publicly available datasets in order to objectively measure our contributions.
L’anàlisi del moviment humà es una area de visió per computador que, en les últimes dècades, ha atret l'interès de la comunitat científica. L’anàlisi de moviment inclou temes com el seguiment del cos humà, el reconeixement d'accions i patrons de comportament, o la segmentació del moviment humà. Tots aquests camps suposen un repte a causa de diferents raons, però especialment a la perspectiva de captura de les escenes a analitzar i també a l’absència d'una semàntica precisa associada a les accions i el moviment humà. La comunitat de visió per computador ha abordat l’anàlisi del moviment humà des de diverses perspectives. Els primers enfocaments es basen en models articulats del cos humà. Aquests models representen el cos com una estructura esqueletal tridimensional. No obstant, a causa de la dificultat i el cost computacional de l’estimació d'aquesta estructura articulada a partir de vídeo, la investigació s'ha anat enfocant, en els últims anys, cap a l’anàlisi de moviment humà basat en característiques de baix nivell. Malgrat obtenir resultats impressionants en diverses tasques, les característiques de baix nivell estan normalment condicionades per l’aparença i punt de vista, cosa que fa difícil la seva aplicació en diferents escenaris. Avui dia, l'augment de la potència de càlcul, la disponibilitat massiva de dades i la irrupció de les càmares de profunditat de baix cost han proporcionat un escenari que permet reconsiderar l’anàlisi de moviment humà a través de models articulats. L'anàlisi i comprensió del moviment humà a través de la informació tridimensional segueix sent un enfocament crucial per obtenir millors models dinàmics al voltant del moviment del cos humà. Per això, els models articulats del cos humà, que ofereixen una representació compacta i invariant al punt de vista de la captura, són una eina per potenciar l'anàlisi de moviment. En aquesta tesi, es presenten diversos enfocaments per a l'anàlisi de moviment. En particular, s'aborda el problema de l'estimació de pose, el reconeixement d'accions i el clustering temporal del moviment humà. Els models articulats són el leitmotiv en tots els plantejaments presentats. En primer lloc, plantegem l’estimació de pose mitjançant la formulació d'un mètode jeràrquic d'anàlisi per síntesi en que els models s'utilitzen per generar hipòtesis que es contrasten amb vídeo. Fent servir la mateixa representació articulada del cos humà, es proposa una formulació del moviment humà per al reconeixement d'accions. La nostra hipòtesi és que les accions formen un conjunt de sistemes dinàmics subjacents que generen observacions en forma de sèries temporals. Aquestes sèries temporals són observades a través del model articulat. Aquesta hipòtesi s'utilitza amb la finalitat de desenvolupar mètodes de reconeixement basats en time-delay embeddings, una eina d’anàlisi de sèries temporals que no fa suposicions sobre la forma del sistema dinàmic subjacent. Finalment, es proposa un mètode per segmentar seqüències de moviment del cos humà en diferents comportaments o accions, sense necessitar un coneixement a priori del nombre d'accions en la seqüència. El nostre enfocament utilitza els models articulats del cos humà per aprendre una distància mètrica. Aquesta mètrica té com a objectiu capturar la semàntica implícita de les anotacions que es puguin trobar en altres bases de dades que continguin seqüències de moviment. Amb la finalitat de mesurar objectivament les nostres contribucions, els mètodes proposats són avaluats utilitzant bases de dades publiques.

The topic for this thesis is the analysis of human movement, or more specifically, markerless analysis of human movement from video material. By markerless analysis is meant that the full image material is used as input in contrast with traditional marker systems that only use the positions of marker centers. The basic idea is to use more of the information in the images to improve the analysis. Starting of with the aim of markerless analysis an application is designed that use, to the subject added texture to estimate the position of the knee joint center in real images. The approach show the plausibility of using subject texture for estimation purposes. Another issue that is addressed is how one can generate synthetic image data. Using basic tools of graphics programming a virtual environment used to synthesize data is created. This environment is also used to evaluate some different camera solutions. One method to make three dimensional reconstruction from multiple images of an object is tested using the synthetic data. The method is based on a "brute force" approach and does not show good performance in terms of computing speed. With appropriate representations of the three dimensional objects, mathematical methods might speed up the analysis.

L'objectif de ce travail est de développer des méthodes avancées d'apprentissage pour l’analyse et l'interprétation automatique du mouvement humain à partir de sources d'information diverses, telles que les images, les vidéos, les cartes de profondeur, les données de type “MoCap” (capture de mouvement), les signaux audio et les données issues de capteurs inertiels. A cet effet, nous proposons plusieurs modèles neuronaux et des algorithmes d’entrainement associés pour l’apprentissage supervisé et semi-supervisé de caractéristiques. Nous proposons des approches de modélisation des dépendances temporelles, et nous montrons leur efficacité sur un ensemble de tâches fondamentales, comprenant la détection, la classification, l’estimation de paramètres et la vérification des utilisateurs (la biométrie). En explorant différentes stratégies de fusion, nous montrons que la fusion des modalités à plusieurs échelles spatiales et temporelles conduit à une augmentation significative des taux de reconnaissance, ce qui permet au modèle de compenser les erreurs des classifieurs individuels et le bruit dans les différents canaux. En outre, la technique proposée assure la robustesse du classifieur face à la perte éventuelle d’un ou de plusieurs canaux. Dans un deuxième temps nous abordons le problème de l’estimation de la posture de la main en présentant une nouvelle méthode de régression à partir d’images de profondeur. Dernièrement, dans le cadre d’un projet séparé (mais lié thématiquement), nous explorons des modèles temporels pour l'authentification automatique des utilisateurs de smartphones à partir de leurs habitudes de tenir, de bouger et de déplacer leurs téléphones. Dans ce contexte, les données sont acquises par des capteurs inertiels embraqués dans les appareils mobiles
The research goal of this work is to develop learning methods advancing automatic analysis and interpreting of human motion from different perspectives and based on various sources of information, such as images, video, depth, mocap data, audio and inertial sensors. For this purpose, we propose a several deep neural models and associated training algorithms for supervised classification and semi-supervised feature learning, as well as modelling of temporal dependencies, and show their efficiency on a set of fundamental tasks, including detection, classification, parameter estimation and user verification. First, we present a method for human action and gesture spotting and classification based on multi-scale and multi-modal deep learning from visual signals (such as video, depth and mocap data). Key to our technique is a training strategy which exploits, first, careful initialization of individual modalities and, second, gradual fusion involving random dropping of separate channels (dubbed ModDrop) for learning cross-modality correlations while preserving uniqueness of each modality-specific representation. Moving forward, from 1 to N mapping to continuous evaluation of gesture parameters, we address the problem of hand pose estimation and present a new method for regression on depth images, based on semi-supervised learning using convolutional deep neural networks, where raw depth data is fused with an intermediate representation in the form of a segmentation of the hand into parts. In separate but related work, we explore convolutional temporal models for human authentication based on their motion patterns. In this project, the data is captured by inertial sensors (such as accelerometers and gyroscopes) built in mobile devices. We propose an optimized shift-invariant dense convolutional mechanism and incorporate the discriminatively-trained dynamic features in a probabilistic generative framework taking into account temporal characteristics. Our results demonstrate, that human kinematics convey important information about user identity and can serve as a valuable component of multi-modal authentication systems

Anterior cruciate knee ligament injuries are common and well known, especially amongst athletes.These injuries often require surgeries and long rehabilitation programs, and can lead to functionloss and re-injuries (Marshall et al., 1977). This work aims to explore the possibility of applyingsupervised classification on knee functionality, using different types of models, and testing differentdivisions of classes. The data used is gathered through a performance test, where individualsperform one-leg hops with motion sensors attached to their bodies. The obtained data representsthe position over time, and is considered functional data.With functional data analysis (FDA), a process can be analysed as a continuous function of time,instead of being reduced to finite data points. FDA includes many useful tools, but also somechallenges. A functional observation can for example be differentiated, a handy tool not found inthe multivariate tool-box. The speed, and acceleration, can then be calculated from the obtaineddata. How to define "similarity" is, on the other hand, not as obvious as with points. In this work,an FDA-approach is taken on classifying knee kinematic data, from a long-term follow-up studyon knee ligament injuries.This work studies kernel functional classifiers, and k-nearest neighbours models, and performssignificance tests on the model accuracy, using re-sampling methods. Additionally, depending onhow similarity is defined, the models can distinguish different features of the data. Attempts atutilising more information through incorporation of ensemble-methods, does not exceed the singlemodels it is created from. Further, it is shown that classification on optimised sub-domains, canbe superior to classifiers using the full domain, in terms of predictive power.
Främre korsbandsskador är vanliga och välkända skador, speciellt bland idrottsutövare. Skadornakräver ofta operationer och långa rehabiliteringsprogram, och kan leda till funktionell nedsättningoch återskador (Marshall et al., 1977). Målet med det här arbetet är att utforska möjligheten attklassificera knän utifrån funktionalitet, där utfallet är känt. Detta genom att använda olika typerav modeller, och genom att testa olika indelningar av grupper. Datat som används är insamlatunder ett prestandatest, där personer hoppat på ett ben med rörelsesensorer på kroppen. Deninsamlade datan representerar position över tid, och betraktas som funktionell data.Med funktionell dataanalys (FDA) kan en process analyseras som en kontinuerlig funktion av tid,istället för att reduceras till ett ändligt antal datapunkter. FDA innehåller många användbaraverktyg, men även utmaningar. En funktionell observation kan till exempel deriveras, ett händigtverktyg som inte återfinns i den multivariata verktygslådan. Hastigheten och accelerationen kandå beräknas utifrån den insamlade datan. Hur "likhet" är definierat, å andra sidan, är inte likauppenbart som med punkt-data. I det här arbetet används FDA för att klassificera knärörelsedatafrån en långtidsuppföljningsstudie av främre korsbandsskador.I detta arbete studeras både funktionella kärnklassificerare och k-närmsta grannar-metoder, och ut-för signifikanstest av modellträffsäkerheten genom omprovtagning. Vidare kan modellerna urskiljaolika egenskaper i datat, beroende på hur närhet definieras. Ensemblemetoder används i ett försökatt nyttja mer av informationen, men lyckas inte överträffa någon av de enskilda modellerna somutgör ensemblen. Vidare så visas också att klassificering på optimerade deldefinitionsmängder kange en högre förklaringskraft än klassificerare som använder hela definitionsmängden.

In this study, we developed an animation tool to animate 3D virtual characters. The tool offers facilities to integrate motion capture data with a 3D character mesh and animate the mesh by using Skeleton Subsurface Deformation and Dual Quaternion Skinning Methods. It is a compact tool, so it is possible to distribute, install and use the tool with ease. This tool can be used to illustrate medical kinematic gait data for educational purposes. For validation, we obtained medical motion capture data from two separate sources and animated a 3D mesh model by using this data. The animations are presented to physicians for evaluation. The results show that the tool is sufficient in displaying obvious gait patterns of the patients. The tool provides interactivity for inspecting the movements of patient from different angles and distances. We animate anonymous virtual characters which provide anonymity of the patient.

Motion capture technology is recognised as a standard tool in the computer animation pipeline. It provides detailed movement for animators; however, it also introduces problems and brings concerns for creating realistic and convincing motion for character animation. In this thesis, the post-processing techniques are investigated that result in realistic motion generation. Anumber of techniques are introduced that are able to improve the quality of generated motion from motion capture data, especially when integrating motion transitions from different motion clips. The presented motion data reconstruction technique is able to build convincing realistic transitions from existing motion database, and overcome the inconsistencies introduced by traditional motion blending techniques. It also provides a method for animators to re-use motion data more efficiently. Along with the development of motion data transition reconstruction, the motion capture data mapping technique was investigated for skeletal movement estimation. The per-frame based method provides animators with a real-time and accurate solution for a key post-processing technique. Although motion capture systems capture physically-based motion for character animation, no physical information is included in the motion capture data file. Using the knowledge of biomechanics and robotics, the relevant information for the captured performer are able to be abstracted and a mathematical-physical model are able to be constructed; such information is then applied for physics-based motion data correction whenever the motion data is edited.

Thesis (Ph. D.) -- University of Maryland, College Park, 2004.
Thesis research directed by: Computer Science. Title from t.p. of PDF. Includes bibliographical references. Published by UMI Dissertation Services, Ann Arbor, Mich. Also available in paper.

Visual analysis of human motion is one of the active research areas in computer vision. The trend shifts from computing motion fields to understanding actions. In this thesis, an action coding scheme based on trajectories of the features calculated with respect to a part based coordinate system is presented. The part based coordinate system is formed using an axis based representation. The features are extracted from images segmented in the form of silhouettes. We present some preliminary experiments that demonstrate the potential of the method in action similarity analysis.

From an early age, people display the ability to quickly and effortlessly interpret the orientation and movement of human body parts, thereby allowing one to infer the intentions of others who are nearby and to comprehend an important nonverbal form of communication. The ease with which one accomplishes this task belies the difficulty of a problem that has challenged computational systems for decades, human motion analysis. Technological developments over years have resulted into many systems for measuring body segment positions and angles between segments. In these systems human body is typically considered as a system of rigid links connected by joints. The motion is estimated by the use of measurements from mechanical, optical, magnetic, or inertial trackers. Among all kinds of sensors, optical sensing encompasses a large and varying collection of technologies. In a computer vision context, human motion analysis is a topic that studies methods and applications in which two or more consecutive images from an image sequences, e.g. captured by a video camera, are processed to produce information based on the apparent human body motion in the images. Many different disciplines employ motion analysis systems to capture movement and posture of human body for applications such as medical diagnostics, virtual reality, human-computer interaction etc. This thesis gives an insight into the state of the art human motion analysissystems, and provides new methods for capturing human motion.

En aquest treball s’explora el reconeixement d’accions humanes i l'estimació de la seva postura en seqüències d'imatges. A diferència de les tècniques tradicionals d’aprenentatge a partir d’imatges 2D o vídeo amb la sortida anotada, en aquesta Tesi abordem aquest objectiu amb la informació de moviment 3D capturat, que ens ajudar a tancar el llaç entre les característiques 2D de la imatge i les interpretacions sobre el moviment humà.
En este trabajo se exploran el reconocimiento de acciones humanas y la estimación de su postura en secuencias de imágenes. A diferencia de las técnicas tradicionales de aprendizaje a partir de imágenes 2D o vídeo con la salida anotada, en esta Tesis abordamos este objetivo con la información de movimiento 3D capturado, que nos ayudar a cerrar el lazo entre las caracteríssticas 2D de la imagen y las interpretaciones sobre el movimiento humano.
In this work, we explore human action recognition and pose estimation problems. Different from traditional works of learning from 2D images or video sequences and their annotated output, we seek to solve the problems with additional 3D motion capture information, which helps to fill the gap between 2D image features and human interpretations.

Thesis (Ph. D.) -- University of Maryland, College Park, 2006.
Thesis research directed by: Electrical Engineering. Title from t.p. of PDF. Includes bibliographical references. Published by UMI Dissertation Services, Ann Arbor, Mich. Also available in paper.

Human behavior recognition and analysis have been considered as a core technology that can facilitate a variety of applications. However, accurate detection and recognition of human behavior is still a big challenge that attracts a lot of research efforts. Among all the research works, motion sensors-based human behavior recognition is promising as it is low cost, low power, and easy to carry. In this dissertation, we use motion sensors to study human behaviors. First, we present Ultigesture (UG) wristband, a hardware platform for detecting and analyzing human behavior. The hardware platform integrates an accelerometer, gyroscope, and compass sensor, providing a combination of (1) fully open Application Programming Interface (API) for various application development, (2) appropriate form factor for comfortable daily wear, and (3) affordable cost for large scale adoption. Second, we study the hand gesture recognition problem when a user performs gestures continuously. we propose a novel continuous gesture recognition algorithm. It accurately and automatically separates hand movements into segments, and merges adjacent segments if needed, so that each gesture only exists in one segment. Then, we apply the Hidden Markov Model to classify each segment into one of predefined hand gestures. Experiments with human subjects show that the recognition accuracy is 99.4% when users perform gestures discretely, and 94.6% when users perform gestures continuously. Third, we study the hand gesture recognition problem when a user is moving. We propose a novel mobility-aware hand gesture segmentation algorithm to detect and segment hand gestures. We also propose a Convolutional Neural Network to classify hand gestures with mobility noises. For the leave-one-subject-out cross-validation test, experiments with human subjects show that the proposed segmentation algorithm achieves 94.0% precision, and 91.2% recall when the user is moving. The proposed hand gesture classification algorithm is 16.1%, 15.3%, and 14.4% more accurate than state-of-the-art work when the user is standing, walking, and jogging, respectively. Finally, we present a tennis ball speed estimation system, TennisEye, which uses a racket-mounted motion sensor to estimate ball speed. We divide the tennis shots into three categories: serve, groundstroke, and volley. For a serve, we propose a regression model to estimate the ball speed. In addition, we propose a physical model and a regression model for both groundstroke and volley shots. Under the leave-one-subject-out cross-validation test, evaluation results show that TennisEye is 10.8% more accurate than the state-of-the-art work.

Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2008.
Includes bibliographical references (p. 52-56).
Many data-driven animation techniques are capable of producing high quality motions of human characters. Few techniques, however, are capable of generating motions that are consistent with physically simulated environments. Physically simulated characters, in contrast, are automatically consistent with the environment, but their motions are often unnatural because they are difficult to control. We present a model-predictive controller that yields natural motions by guiding simulated humans toward real motion data. During simulation, the predictive component of the controller solves a quadratic program to compute the forces for a short window of time into the future. These forces are then applied by a low-gain proportional-derivative component, which makes minor adjustments until the next planning cycle. The controller is fast enough for interactive systems such as games and training simulations. It requires no precomputation and little manual tuning. The controller is resilient to mismatches between the character dynamics and the input motion, which allows it to track motion capture data even where the real dynamics are not known precisely. The same principled formulation can generate natural walks, runs, and jumps in a number of different physically simulated surroundings.
by Marco da Silva.
S.M.

L'émergence de capteurs de profondeur capturant la structure 3D de la scène et du corps humain offre de nouvelles possibilités pour l'étude du mouvement et la compréhension des comportements humains. Cependant, la conception et le développement de modules de reconnaissance de comportements à la fois précis et efficaces est une tâche difficile en raison de la variabilité de la posture humaine, la complexité du mouvement et les interactions avec l'environnement. Dans cette thèse, nous nous concentrons d'abord sur le problème de la reconnaissance d'actions en représentant la trajectoire du corps humain au cours du temps, capturant ainsi simultanément la forme du corps et la dynamique du mouvement. Le problème de la reconnaissance d'actions est alors formulé comme le calcul de similitude entre la forme des trajectoires dans un cadre Riemannien. Les expériences menées sur quatre bases de données démontrent le potentiel de la solution en termes de précision/temps de latence de la reconnaissance d'actions. Deuxièmement, nous étendons l'étude aux comportements plus complexes en analysant l'évolution de la forme de la posture pour décomposer la séquence en unités de mouvement. Chaque unité de mouvement est alors caractérisée par la trajectoire de mouvement et l'apparence autour des mains, de manière à décrire le mouvement humain et l'interaction avec les objets. Enfin, la séquence de segments temporels est modélisée par un classifieur Bayésien naïf dynamique. Les expériences menées sur quatre bases de données évaluent le potentiel de l'approche dans différents contextes de reconnaissance et détection en ligne de comportements
The emergence of RGB-D sensors providing the 3D structure of both the scene and the human body offers new opportunities for studying human motion and understanding human behaviors. However, the design and development of models for behavior recognition that are both accurate and efficient is a challenging task due to the variability of the human pose, the complexity of human motion and possible interactions with the environment. In this thesis, we first focus on the action recognition problem by representing human action as the trajectory of 3D coordinates of human body joints over the time, thus capturing simultaneously the body shape and the dynamics of the motion. The action recognition problem is then formulated as the problem of computing the similarity between shape of trajectories in a Riemannian framework. Experiments carried out on four representative benchmarks demonstrate the potential of the proposed solution in terms of accuracy/latency for a low-latency action recognition. Second, we extend the study to more complex behaviors by analyzing the evolution of the human pose shape to decompose the motion stream into short motion units. Each motion unit is then characterized by the motion trajectory and depth appearance around hand joints, so as to describe the human motion and interaction with objects. Finally, the sequence of temporal segments is modeled through a Dynamic Naive Bayesian Classifier. Experiments on four representative datasets evaluate the potential of the proposed approach in different contexts, including recognition and online detection of behaviors

This research aims to address one of the most challenging problems in the field of computer vision and computer graphics, that is, the reconstruction of smooth 3D human motions from monocular video containing unrestricted human movement. The objective is to propose novel methods which differ from the traditional kinematics/dynamics formulations and image based reconstruction methods to provide an alternative highly automated way for human animation from the most widely available source that records human movements and activities. Such methods should be relatively low-cost while avoiding many limitations that come up with current motion tracking equipment.Monocular images or video sequences are chosen as the source of the project, due to the fact that they are widely available through many ways, such as film making and even simple home videos. Most of such monocular images or video sequences are generally uncalibrated, i.e., the information on the camera from which these images are taken is not available. In addition, although 2D joint locations and body silhouettes can be extracted from the images, accuracy of such 2D feature extractions may not be satisfactory by current image processing techniques. Using such monocular image sequence as the input source, many techniques and algorithms are proposed in this research.A 3D skeletal human model based on human anatomy is constructed with angular constraints encoded in the joints according to the biomechanical and physiological knowledge. The model is simple and yet sufficient to simulate realistic human motions, while the computational expense is much lower when dealing with skeletal model than with any other human models. Relative lengths of every body part of the human model are adjusted to be consistent with the human subject in the source images before reconstruction. That is achieved by preciously acquired geometry information on the human subject of interest.A Motion Trend Analysis (MTA) method is proposed in this research to automatically reconstruct the 3D postures of the human subject of interest directly from the extracted 2D joint locations (with possible noise tolerance) at each image frame. This method utilized the information on previously reconstructed postures to assist positioning the joints of the human model to their proper 3D locations in the current frame. To ensure a reliable starting point in the reconstruction, manual adjustment may be required to improve the accuracy of the first three posture recoveries. 3D positional coherence of every joint between adjacent recovered postures can be obtained and maintained at a satisfactory level. Objective Function (OF) is defined to represent the 2D residuals between the extracted feature points and the corresponding features resulted from projecting the reconstructed human model to the projection plane. The OF also includes considerations of all 3D positional discrepancies at every joint between adjacent postures. By translating the pelvis joint and rotating each joint of the human model, a proper human posture that resembles the one represented in the monocular image can be created by searching for the minimum value of the OF. To balance 2D residuals and 3D discrepancies, weighting parameters (WP) determination routine was developed which is able to dynamically adjust the WP values for the 2D and 3D factors in an OF.3D acquisition of smooth and reasonable human motion is the main focus of this research. Such human motions are in high demand for applications involving virtual human movements. A Motion Level Control (MLC) algorithm was proposed to be integrated with the MTA system to further ensure the rotational coherence of the reconstruction results in 3D and improve the efficiency of the search process. Application of MLC can be divided into two modules: the relocation of the pelvis joint and the recoveries of the skeleton segments rotations. Based on MLC, the computational cost of the search procedure for the pelvis relocation and the skeleton adjustment in the human posture recovery will be significantly reduced. At the same time, rotational consistency of each body segment in the reconstructed motion can reach a satisfactory level. Experimental results from the proposed algorithm are highly satisfactory.This research also attempts to acquire smooth yet reasonable 3D human motions from the monocular images with body occlusion or based on extracted silhouettes. Existing techniques for recovering human postures usually require as input a human motion sequence where every body segment is visible at all time. Such requirement might not always be satisfied. The human motion to be reconstructed could contain occlusions where part or the body is obscured by other object in the scene or by another part of the human body itself. The input video could also be not clear enough to provide acceptable 2D joint extractions. This research extends the developed MTA and MLC and proposes novel methods to acquire the smooth and reasonable human postures under such circumstances. Experiments have produced very promising results.There are still many challenges ahead, especially on the preprocessing of the monocular images such as the accurate extraction of joint locations and fullyautomatic posture recoveries. Besides, the Objective Function and biomechanical constraints should be further studied to improve the general performance of the motion reconstruction system. Human motion reconstruction algorithm without accurate 2D inputs in terms of joint features or silhouettes should also be explored. The human motion reconstruction obtained from this research currently can handle 2D input with minor extraction errors. A more applicable system that can tolerate more input errors will be highly desirable and hence should attract some research attention. Technical issues to be explored and addressed in the future are identified and discussed in this thesis.

Thesis (Ph. D.)--University of California, San Diego, 2006.
Title from first page of PDF file (viewed June 7, 2006). Available via ProQuest Digital Dissertations. Vita. Includes bibliographical references (p. 104-112).

Modern technology o ers us highly evolved data collection devices. They allow us to observe data densely over continua such as time, distance, space and so on. The observations are normally assumed to follow certain continuous and smooth underline functions of the continua. Thus the analysis must consider two important properties of functional data: infinite dimension and the smoothness. Traditional multivariate data analysis normally works with low dimension and independent data. Therefore, we need to develop new methodology to conduct functional data analysis. In this thesis, we first study the linear relationship between a scalar variable and a group of functional variables using three di erent discrete methods. We combine this linear relationship with the idea from least angle regression to propose a new variable selection method, named as functional LARS. It is designed for functional linear regression with scalar response and a group of mixture of functional and scalar variables. We also propose two new stopping rules for the algorithm, since the conventional stopping rules may fail for functional data. The algorithm can be used when there are more variables than samples. The performance of the algorithm and the stopping rules is compared with existed algorithms by comprehensive simulation studies. The proposed algorithm is applied to analyse motion data including scalar response, more than 200 scalar covariates and 500 functional covariates. Models with or without functional variables are compared. We have achieved very accurate results for this complex data particularly the models including functional covariates. The research in functional variable selection is limited due to its complexity and onerous computational burdens. We have demonstrated that the proposed functional LARS is a very e cient method and can cope with functional data very large dimension. The methodology and the idea have the potential to be used to address other challenging problems in functional data analysis.

Thesis (M.S.)--Worcester Polytechnic Institute.
Keywords: association rule mining; logistic regression; statistical significance of rules; window-based association rule mining; data mining; sleep data. Includes bibliographical references (leaves 166-167).

Human body analysis is one of the broadest areas within the computer vision field. Researchers have put a strong effort in the human body analysis area, specially over the last decade, due to the technological improvements in both video cameras and processing power. Human body analysis covers topics such as person detection and segmentation, human motion tracking or action and behavior recognition. Even if human beings perform all these tasks naturally, they build-up a challenging problem from a computer vision point of view. Adverse situations such as viewing perspective, clutter and occlusions, lighting conditions or variability of behavior amongst persons may turn human body analysis into an arduous task. In the computer vision field, the evolution of research works is usually tightly related to the technological progress of camera sensors and computer processing power. Traditional human body analysis methods are based on color cameras. Thus, the information is extracted from the raw color data, strongly limiting the proposals. An interesting quality leap was achieved by introducing the multiview concept. That is to say, having multiple color cameras recording a single scene at the same time. With multiview approaches, 3D information is available by means of stereo matching algorithms. The fact of having 3D information is a key aspect in human motion analysis, since the human body moves in a three-dimensional space. Thus, problems such as occlusion and clutter may be overcome with 3D information. The appearance of commercial depth cameras has supposed a second leap in the human body analysis field. While traditional multiview approaches required a cumbersome and expensive setup, as well as a fine camera calibration; novel depth cameras directly provide 3D information with a single camera sensor. Furthermore, depth cameras may be rapidly installed in a wide range of situations, enlarging the range of applications with respect to multiview approaches. Moreover, since depth cameras are based on infra-red light, they do not suffer from illumination variations. In this thesis, we focus on the study of depth data applied to the human body analysis problem. We propose novel ways of describing depth data through specific descriptors, so that they emphasize helpful characteristics of the scene for further body analysis. These descriptors exploit the special 3D structure of depth data to outperform generalist 3D descriptors or color based ones. We also study the problem of person detection, proposing a highly robust and fast method to detect heads. Such method is extended to a hand tracker, which is used throughout the thesis as a helpful tool to enable further research. In the remainder of this dissertation, we focus on the hand analysis problem as a subarea of human body analysis. Given the recent appearance of depth cameras, there is a lack of public datasets. We contribute with a dataset for hand gesture recognition and fingertip localization using depth data. This dataset acts as a starting point of two proposals for hand gesture recognition and fingertip localization based on classification techniques. In these methods, we also exploit the above mentioned descriptor proposals to finely adapt to the nature of depth data.%, and enhance the results in front of traditional color-based methods.
L’anàlisi del cos humà és una de les àrees més àmplies del camp de la visió per computador. Els investigadors han posat un gran esforç en el camp de l’anàlisi del cos humà, sobretot durant la darrera dècada, degut als grans avenços tecnològics, tant pel que fa a les càmeres com a la potencia de càlcul. L’anàlisi del cos humà engloba varis temes com la detecció i segmentació de persones, el seguiment del moviment del cos, o el reconeixement d'accions. Tot i que els essers humans duen a terme aquestes tasques d'una manera natural, es converteixen en un difícil problema quan s'ataca des de l’òptica de la visió per computador. Situacions adverses, com poden ser la perspectiva del punt de vista, les oclusions, les condicions d’il•luminació o la variabilitat de comportament entre persones, converteixen l’anàlisi del cos humà en una tasca complicada. En el camp de la visió per computador, l’evolució de la recerca va sovint lligada al progrés tecnològic, tant dels sensors com de la potencia de càlcul dels ordinadors. Els mètodes tradicionals d’anàlisi del cos humà estan basats en càmeres de color. Això limita molt els enfocaments, ja que la informació disponible prové únicament de les dades de color. El concepte multivista va suposar salt de qualitat important. En els enfocaments multivista es tenen múltiples càmeres gravant una mateixa escena simultàniament, permetent utilitzar informació 3D gràcies a algorismes de combinació estèreo. El fet de disposar d’informació 3D es un punt clau, ja que el cos humà es mou en un espai tri-dimensional. Això doncs, problemes com les oclusions es poden apaivagar si es disposa de informació 3D. L’aparició de les càmeres de profunditat comercials ha suposat un segon salt en el camp de l’anàlisi del cos humà. Mentre els mètodes multivista tradicionals requereixen un muntatge pesat i car, i una celebració precisa de totes les càmeres; les noves càmeres de profunditat ofereixen informació 3D de forma directa amb un sol sensor. Aquestes càmeres es poden instal•lar ràpidament en una gran varietat d'entorns, ampliant enormement l'espectre d'aplicacions, que era molt reduït amb enfocaments multivista. A més a més, com que les càmeres de profunditat estan basades en llum infraroja, no pateixen problemes relacionats amb canvis d’il•luminació. En aquesta tesi, ens centrem en l'estudi de la informació que ofereixen les càmeres de profunditat, i la seva aplicació al problema d’anàlisi del cos humà. Proposem noves vies per descriure les dades de profunditat mitjançant descriptors específics, capaços d'emfatitzar característiques de l'escena que seran útils de cara a una posterior anàlisi del cos humà. Aquests descriptors exploten l'estructura 3D de les dades de profunditat per superar descriptors 3D generalistes o basats en color. També estudiem el problema de detecció de persones, proposant un mètode per detectar caps robust i ràpid. Ampliem aquest mètode per obtenir un algorisme de seguiment de mans que ha estat utilitzat al llarg de la tesi. En la part final del document, ens centrem en l’anàlisi de les mans com a subàrea de l’anàlisi del cos humà. Degut a la recent aparició de les càmeres de profunditat, hi ha una manca de bases de dades públiques. Contribuïm amb una base de dades pensada per la localització de dits i el reconeixement de gestos utilitzant dades de profunditat. Aquesta base de dades és el punt de partida de dues contribucions sobre localització de dits i reconeixement de gestos basades en tècniques de classificació. En aquests mètodes, també explotem les ja mencionades propostes de descriptors per millor adaptar-nos a la naturalesa de les dades de profunditat.

The analysis of human motion from visual data is a central issue in the computer vision research community as it enables a wide range of applications and it still remains a challenging problem when dealing with unconstrained scenarios and general conditions. Human motion analysis is used in the entertainment industry for movies or videogame production, in medical applications for rehabilitation or biomechanical studies. It is also used for human computer interaction in any kind of environment, and moreover, it is used for big data analysis from social networks such as Youtube or Flickr, to mention some of its use cases. In this thesis we have studied human motion analysis techniques with a focus on its application for smart room environments. That is, we have studied methods that will support the analysis of people behavior in the room, allowing interaction with computers in a natural manner and in general, methods that introduce computers in human activity environments to enable new kind of services but in an unobstrusive mode. The thesis is structured in two parts, where we study the problem of 3D pose estimation from multiple views and the recognition of gestures using range sensors. First, we propose a generic framework for hierarchically layered particle filtering (HPF) specially suited for motion capture tasks. Human motion capture problem generally involve tracking or optimization of high-dimensional state vectors where also one have to deal with multi-modal pdfs. HPF allow to overcome the problem by means of multiple passes through substate space variables. Then, based on the HPF framework, we propose a method to estimate the anthropometry of the subject, which at the end allows to obtain a human body model adjusted to the subject. Moreover, we introduce a new weighting function strategy for approximate partitioning of observations and a method that employs body part detections to improve particle propagation and weight evaluation, both integrated within the HPF framework. The second part of this thesis is centered in the detection of gestures, and we have focused the problem of reducing annotation and training efforts required to train a specific gesture. In order to reduce the efforts required to train a gesture detector, we propose a solution based on online random forests that allows training in real-time, while receiving new data in sequence. The main aspect that makes the solution effective is the method we propose to collect the hard negatives examples while training the forests. The method uses the detector trained up to the current frame to test on that frame, and then collects samples based on the response of the detector such that they will be more relevant for training. In this manner, training is more effective in terms of the number of annotated frames required.
L'anàlisi del moviment humà a partir de dades visuals és un tema central en la recerca en visió per computador, per una banda perquè habilita un ampli espectre d'aplicacions i per altra perquè encara és un problema no resolt quan és aplicat en escenaris no controlats. L'analisi del moviment humà s'utilitza a l'indústria de l'entreteniment per la producció de pel·lícules i videojocs, en aplicacions mèdiques per rehabilitació o per estudis bio-mecànics. També s'utilitza en el camp de la interacció amb computadors o també per l'analisi de grans volums de dades de xarxes socials com Youtube o Flickr, per mencionar alguns exemples. En aquesta tesi s'han estudiat tècniques per l'anàlisi de moviment humà enfocant la seva aplicació en entorns de sales intel·ligents. És a dir, s'ha enfocat a mètodes que puguin permetre l'anàlisi del comportament de les persones a la sala, que permetin la interacció amb els dispositius d'una manera natural i, en general, mètodes que incorporin les computadores en espais on hi ha activitat de persones, per habilitar nous serveis de manera que no interfereixin en la activitat. A la primera part, es proposa un marc genèric per l'ús de filtres de partícules jeràrquics (HPF) especialment adequat per tasques de captura de moviment humà. La captura de moviment humà generalment implica seguiment i optimització de vectors d'estat de molt alta dimensió on a la vegada també s'han de tractar pdf's multi-modals. Els HPF permeten tractar aquest problema mitjançant multiples passades en subdivisions del vector d'estat. Basant-nos en el marc dels HPF, es proposa un mètode per estimar l'antropometria del subjecte, que a la vegada permet obtenir un model acurat del subjecte. També proposem dos nous mètodes per la captura de moviment humà. Per una banda, el APO es basa en una nova estratègia per les funcions de cost basada en la partició de les observacions. Per altra, el DD-HPF utilitza deteccions de parts del cos per millorar la propagació de partícules i l'avaluació de pesos. Ambdós mètodes són integrats dins el marc dels HPF. La segona part de la tesi es centra en la detecció de gestos, i s'ha enfocat en el problema de reduir els esforços d'anotació i entrenament requerits per entrenar un detector per un gest concret. Per tal de reduir els esforços requerits per entrenar un detector de gestos, proposem una solució basada en online random forests que permet l'entrenament en temps real, mentre es reben noves dades sequencialment. El principal aspecte que fa la solució efectiva és el mètode que proposem per obtenir mostres negatives rellevants, mentre s'entrenen els arbres de decisió. El mètode utilitza el detector entrenat fins al moment per recollir mostres basades en la resposta del detector, de manera que siguin més rellevants per l'entrenament. D'aquesta manera l'entrenament és més efectiu pel que fa al nombre de mostres anotades que es requereixen.

Human motion analysis is concerned with the study of human activity recognition, human motion tracking, and the analysis of human biomechanics. Human motion analysis has applications within areas of entertainment, sports, and healthcare. For example, activity recognition, which aims to understand and identify different tasks from motion can be applied to create records of staff activity in the operating theatre at a hospital; motion tracking is already employed in some games to provide an improved user interaction experience and can be used to study how medical staff interact in the operating theatre; and human biomechanics, which is the study of the structure and function of the human body, can be used to better understand athlete performance, pathologies in certain patients, and assess the surgical skill of medical staff. As health services strive to improve the quality of patient care and meet the growing demands required to care for expanding populations around the world, solutions that can improve patient care, diagnosis of pathology, and the monitoring and training of medical staff are necessary. Surgical workflow analysis, for example, aims to assess and optimise surgical protocols in the operating theatre by evaluating the tasks that staff perform and measurable outcomes. Human motion analysis methods can be used to quantify the activities and performance of staff for surgical workflow analysis; however, a number of challenges must be overcome before routine motion capture of staff in an operating theatre becomes feasible. Current commercial human motion capture technologies have demonstrated that they are capable of acquiring human movement with sub-centimetre accuracy; however, the complicated setup procedures, size, and embodiment of current systems make them cumbersome and unsuited for routine deployment within an operating theatre. Recent advances in pervasive sensing have resulted in camera systems that can detect and analyse human motion, and small wear- able sensors that can measure a variety of parameters from the human body, such as heart rate, fatigue, balance, and motion. The work in this thesis investigates different methods that enable human motion to be more easily, reliably, and accurately captured through ambient and wearable sensor technologies to address some of the main challenges that have limited the use of motion capture technologies in certain areas of study. Sensor embodiment and accuracy of activity recognition is one of the challenges that affect the adoption of wearable devices for monitoring human activity. Using a single inertial sensor, which captures the movement of the subject, a variety of motion characteristics can be measured. For patients, wearable inertial sensors can be used in long-term activity monitoring to better understand the condition of the patient and potentially identify deviations from normal activity. For medical staff, inertial sensors can be used to capture tasks being performed for automated workflow analysis, which is useful for staff training, optimisation of existing processes, and early indications of complications within clinical procedures. Feature extraction and classification methods are introduced in thesis that demonstrate motion classification accuracies of over 90% for five different classes of walking motion using a single ear-worn sensor. To capture human body posture, current capture systems generally require a large number of sensors or reflective reference markers to be worn on the body, which presents a challenge for many applications, such as monitoring human motion in the operating theatre, as they may restrict natural movements and make setup complex and time consuming. To address this, a method is proposed, which uses a regression method to estimate motion using a subset of fewer wearable inertial sensors. This method is demonstrated using three sensors on the upper body and is shown to achieve mean estimation accuracies as low as 1.6cm, 1.1cm, and 1.4cm for the hand, elbow, and shoulders, respectively, when compared with the gold standard optical motion capture system. Using a subset of three sensors, mean errors for hand position reach 15.5cm. Unlike human motion capture systems that rely on vision and reflective reference point markers, commonly known as marker-based optical motion capture, wearable inertial sensors are prone to inaccuracies resulting from an accumulation of inaccurate measurements, which becomes increasingly prevalent over time. Two methods are introduced in this thesis, which aim to solve this challenge using visual rectification of the assumed state of the subject. Using a ceiling-mounted camera, a human detection and human motion tracking method is introduced to improve the average mean accuracy of tracking to within 5.8cm in a laboratory of 3m x 5m. To improve the accuracy of capturing the position of body parts and posture for human biomechanics, a camera is also utilised to track the body part movements and provide visual rectification of human pose estimates from inertial sensing. For most subjects, deviations of less than 10% from the ground truth are achieved for hand positions, which exhibit the greatest error, and the occurrence of sources of other common visual and inertial estimation errors, such as measurement noise, visual occlusion, and sensor calibration are shown to be reduced.

Cette thèse se propose comme une étude géométrique de la surface faciale en 3D, dont le but est de fournir un ensemble d'entités, issues du contexte de la géométrie différentielle, à utiliser comme descripteurs faciaux dans les applications d'analyse du visage, comme la reconnaissance faciale et la reconnaissance des expressions faciales. En effet, bien que chaque visage soit unique, tous les visages sont similaires et leurs caractéristiques morphologiques sont les mêmes pour tous les individus. Par conséquent, il est primordial pour l'analyse des visages d'extraire les caractéristiques faciales les plus appropriées. Tous les traits du visage, proposés dans cette étude, sont basés uniquement sur les propriétés géométriques de la surface faciale. En effet, l'objectif final de cette recherche est de démontrer que la géométrie différentielle est un outil complet pour l'analyse des visages et que les caractéristiques géométriques conviennent pour décrire et comparer des visages et, en général, pour extraire des informations pertinentes pour l'analyse faciale dans les différents domaines d'application. Enfin, ce travail se concentre aussi sur l'analyse des troubles musculo-squelettiques en proposant une quantification objective des mouvements du visage pour aider la chirurgie maxillo-faciale et la rééducation des mouvements du visage. Ce travail de recherche explore le système de capture du mouvement 3D, en adoptant la plateforme Technologie, Sport et Santé, située au Centre d'Innovation de l'Université de Technologie de Compiègne, au sein du Laboratoire de Biomécanique et Bioingénierie (BMBI)
This thesis is intended as a geometrical study of the three-dimensional facial surface, whose aim is to provide an application framework of entities coming from Differential Geometry context to use as facial descriptors in face analysis applications, like FR and FER fields. Indeed, although every visage is unique, all faces are similar and their morphological features are the same for all mankind. Hence, it is primary for face analysis to extract suitable features. All the facial features, proposed in this study, are based only on the geometrical properties of the facial surface. Then, these geometrical descriptors and the related entities proposed have been applied in the description of facial surface in pattern recognition contexts. Indeed, the final goal of this research is to prove that Differential Geometry is a comprehensive tool oriented to face analysis and geometrical features are suitable to describe and compare faces and, generally, to extract relevant information for human face analysis in different practical application fields. Finally, since in the last decades face analysis has gained great attention also for clinical application, this work focuses on musculoskeletal disorders analysis by proposing an objective quantification of facial movements for helping maxillofacial surgery and facial motion rehabilitation. At this time, different methods are employed for evaluating facial muscles function. This research work investigates the 3D motion capture system, adopting the Technology, Sport and Health platform, located in the Innovation Centre of the University of Technology of Compiègne, in the Biomechanics and Bioengineering Laboratory (BMBI)

With the advent of marker-based motion capture, attempts have been made to recognise and quantify attributes of “type”, “content” and “behaviour” from the motion data. Current work exists to obtain quick and easy identification of human motion for use in multiple settings, such as healthcare and gaming by using activity monitors, wearable technology and low-cost accelerometers. Yet, analysing human motion and generating representative features to enable recognition and analysis in an efficient and comprehensive manner has proved elusive thus far. This thesis proposes practical solutions that are based on insights from clinicians, and learning attributes from motion capture data itself. This culminates in an application framework that learns the type, content and behaviour of human motion for recognition, quantitative clinical analysis and outcome measures. While marker-based motion capture has many uses, it also has major limitations that are explored in this thesis, not least in terms of hardware costs and practical utilisation. These drawbacks have led to the creation of depth sensors capable of providing robust, accurate and low-cost solution to detecting and tracking anatomical landmarks on the human body, without physical markers. This advancement has led researchers to develop low-cost solutions to important healthcare tasks, such as human motion analysis as a clinical aid in prevention care. In this thesis a variety of obstacles in handling markerless motion capture are identified and overcome by employing parameterisation of Axis- Angles, applying Euler Angles transformations to Exponential Maps, and appropriate distance measures between postures. While developing an efficient, usable and deployable application framework for clinicians, this thesis introduces techniques to recognise, analyse and quantify human motion in the context of identifying age-related change and mobility. The central theme of this thesis is the creation of discriminative representations of the human body using novel encoding and extraction approaches usable for both marker-based and marker-less motion capture data. The encoding of the human pose is modelled based on the spatial-temporal characteristics to generate a compact, efficient parameterisation. This combination allows for the detection of multiple known and unknown motions in real-time. However, in the context of benchmarking a major drawback exists, the lack of a clinically valid and relevant dataset to enable benchmarking. Without a dataset of this type, it is difficult to validated algorithms aimed at healthcare application. To this end, this thesis introduces a dataset that will enable the computer science community to benchmark healthcare-related algorithms.

Cette thèse vise à faire émerger de nouvelles descriptions de la variabilité des plissements du cortex humain en s'appuyant sur des techniques de fouilles de données. L'objectif principal est la conception d'algorithmes permettant de découvrir des motifs de plissement spécifiques à une sous-population d'individus. Le but final est de réaliser un dictionnaire de ces motifs et de les associer à des particularités cognitives ou architecturales, voire à des pathologies. Deux stratégies de " clustering " sont proposées pour mettre en évidence de tels motifs. La première repose sur des descripteurs de formes globaux correspondant aux invariants de moment 3D, la seconde repose sur l'estimation d'une matrice de distances entre chaque paire d'individus. Un algorithme de clustering dédié est conçu pour détecter les motifs les plus fréquents de manière robuste. Une technique de réduction de dimension est utilisée pour mettre en évidence les transitions entre motifs au sein de la population. Les méthodes algorithmiques proposées sont utilisées pour étudier la forme du cortex sensori-moteur d'une population de gauchers contrariés. Des résultats originaux sur le lien entre la forme du sillon central et la latéralité manuelle sont mis en évidence. Les méthodes développées sont ensuite utilisées pour construire le premier dictionnaire des motifs observés dans les plissements corticaux issu d'une approche algorithmique.

[eng] Like Columbus mistook America for India, we stepped into the era of misinformation mistaking it for the era of big data. Since the digital revolution in the early ’90s we started producing such a huge amount of data that we do not even know how to find our compass anymore. However, not all this data is available and accessible. In this thesis, by navigating through the seas of available, open and even purchased data on board of our knowledge of physics and complex systems, we try to draw some new routes and shortcuts to study human mobility in different contexts, scales and applications. We first introduce a simple method to treat Twitter data on the Venezuelan exodus to show how this data can consistently reproduce and uncover many different aspects of migration until now neglected. This method designs a safe route to solve many more open questions not yet explored due to the limitations of classic and other sources of migration data in many parts of the world. The same type of data provides us reasonable footprints of human mobility, which lead us to an innovative shortcut in the way in which a specific type of urban mobility is treated so far. By hoisting the sails of theoretical physics, we can add a field theoretic description of commuting in worldwide cities, which simplifies the complexity of the description of urban mobility. By means of this new framework it is possible to tackle the well known aspect of policentricity of cities, drawing urban basins of attraction and reproducing them through a field theoretic version of the gravity model. Following the same shortcut we get to discover something that has been only theorized so far in pedestrian dynamics: the navigation potential of evacuation. This potential has been used by many social interactions models, which have been used to study new and better policies to avoid cloggings and stampedes during evacuation drills, hence creating safer protocols for our buildings and public spaces. In the middle of our navigation, we suddenly bump into a new epidemic and we perform a route change. By purchasing mobile and smartphones location datasets to find our compass and cope with noisy epidemic records, we are able to uncover the so called multi-seeding effect, which has been studied mostly theoretically. This allows us to backtrace and remap the epidemic spreading in Western Europe to specific epidemic hubs. By means of metapopulation models, we confirm our hypotheses on multiseeding using different contact network topologies. Our results allow to designate efficient policies like selective lockdowns and to better prepare healthcare systems of areas which are more exposed to mobility from epidemic and mobility hubs. While the epidemic spreads in Europe, we spot the first cases on the American coasts. The same phenomenon we already saw can be observed at smaller scales in the United States, this time within cities at neighborhoods level. Here we need a high resolution Google dataset in order to see that cities mobility hierarchy leads the disease to spread faster than in sprawled urban areas. However, hierarchy also helps containment policies to better suppress the disease, whereas the same restrictions are less effective in non-hierarchical metropolitan areas. Some cities are more senstive to disease spreading and they must be accurately monitored in order to avoid the rest of cities and country to get involved. Finally, in order to suppress the disease it is very important to avoid the virus to board on long-range trips and infect new places. By means of smartphones location records, we mimic the spreading of viruses at even finer scales inside the busiest airport of Europe: Heathrow, London. By modeling the implementation of a spatial immunization system we are able to strongly reduce the outbreaks within the airport and the number of exported infections abroad. The same technique can be applied even in ordinary public buildings to create safer spaces for the everyday life in the post-Covid era. In this thesis our philosophy is to always rely on the empirical observations to design hypotheses, models and finally solutions. Thanks to the scientific method, we manage to solve complex problems in the field of human mobility with simple approaches and relatively big data. Most of the results presented in this thesis belong to published and in submission works [1–6].
[spa] Tal como Colón confundió América por India, hemos entrado en la era de la misinformación confundiendola por la era de big data. Desde la revolución digital, hemos empezado a producir una tal cantidad de datos que ya ni siquiera sabemos donde encontrar nuestra brújula. En esta tesis, navegando por los mares de los datos disponibles, a bordo de nuestro conocimiento de física y sistemas complejos, intentamos dibujar nuevas rutas y atajos para estudiar la movilidad humana en diferentes contextos, escalas y aplicaciones. Primero introducimos un método para tratar datos de Twitter sobre el éxodo venezolano para mostrar como estos datos pueden reproducir y desvelar muchos aspectos de la migración hasta ahora no accesibles. Este método diseña una ruta segura hacia la resolución de muchos temas abiertos que aún no se han explorado debido a las limitaciones de los datos clásicos. El mismo tipo de datos nos deja huellas fiables de movilidad humana, que nos llevan a un atajo novedoso en el tratamiento de la movilidad casa-trabajo. Izando las velas de la física teórica podemos añadir una descripción de campo del pendularismo en ciudades. Con este enfoque podemos atacar el problema de la policentricidad de las ciudades, dibujando cuencas de atracción urbanas y reproduciendolas através una versión de campo del gravity model. Siguiendo el mismo atajo llegamos a descubrir algo que solo se había teorizado hasta ahora en dinámicas de peatones: el potencial de navegación de evacuaciones. Este potencial se ha usado en muchos modelos de interacciones sociales, que se han usado para evitar atascos y estampidas durante las evacuaciones, entonces creando protocolos más seguros para nuestros edificios y espacios públicos. En el medio de nuestra navegación nos encontramos en una nueva epidemia y nos vemos obligados a un cambio de ruta. Adquiriendo datos de localización por antenas de móviles y por gps de smartphones para encontrar nuestra brújula, somos capaces de descubrir el denominado efecto multi-seeding, que se ha estudiado por la mayoría teoricamente. Gracias a modelos de metapoblaciones, confirmamos nuestras hipótesis sobre el multiseeding. Nuestros resultados permiten diseñar políticas eficientes como confinamientos selectivos y praparar de una manera mejor los sistemas sanitarios de las áreas más expuestas en términos de movilidad desde las fuentes epidémicas. El mismo fenómeno que hemos visto puede observarse a escalas más pequeñas en Estados Unidos, esta vez dentro de ciudades. Aquí necesitamos los datos de Google en alta resolución para ver que las ciudades jerárquicas exhiben difusiones más rápidas que en las ciudades decentralizadas. En contrapartida, la jerarquía ayuda las políticas de contención para mejor suprimir el virus, mientras que las mismas restricciones tienen un menor efecto en las áreas metropolitanas decentralizadas. Algunas ciudades son más sensibles que otras a la difusión epidémica requiriendo una supervisión estricta para evitar que el resto de ciudades y paises se infecten a su vez. Finalmente, para suprimir la epidemia es muy importante evitar que el virus no embarque en viajes de larga distancia e infecte nuevas regiones. Gracias a datos de localización gps de smartphones, imitamos la difusión de varios viruses a escalas aún más pequeñas dentro del aeropuerto de Heathrow, Londres. Modelizando un sistema de inmunización espacial conseguimos reducir fuertemente los brotes dentro del aeropuerto y el número de infecciones exportadas al extranjero. La misma técnica se puede aplicar en edificios públicos ordinarios para crear espacios más seguros para la vida de cada día en la era post-Covid. Gracias al método científico, conseguimos resolver problemas complejos en el campo de la movilidad humana con enfoques simples y datos relativamente grandes.
[cat] Tal com Colom va confondre Amèrica per l’Índia, hem entrat en l’era de la misinformació confonent-la per l’era del big data. Des de la revolució digital, hem començat a produir una tal quantitat de dades que ja ni tan sols sabem on trobar la nostra brúixola. Navegant pels mars de les dades disponibles, a bord del nostre coneixement de física i sistemes complexos, vam intentar dibuixar algunes noves rutes i dreceres per estudiar la mobilitat humana en diferents contextes, escales i aplicacions. Primer introduïm un mètode per tractar dades de Twitter sobre l’èxode veneçolà per mostrar com aquestes dades poden reproduir i revelar aspectes de la migració fins ara no accessibles. Aquest mètode dissenya una ruta segura cap a la resolució de molts més temes oberts que encara no s’han explorat a causa de les limitacions de les dades clàssics. El mateix tipus de dades ens dona empremtes de la mobilitat, que ens porten a una drecera nova en el tractament de la mobilitat casa-treball. Hissant les veles de la fìsica teòrica podem introduir una descripció de camp de la mobilitat pendular. Amb aquest enfoc és possible abordar el problema de la policentricidad de les ciutats, dibuixant conques d’atracció urbanes i reproduciendolas través una versió de camp de l’gravity model. Seguint la mateixa drecera arribem a descobrir una cosa que fins ara només s’havia teoritzat en dinàmiques de vianants: el potencial de navegació d’evacuacions. Aquest potencial s’ha usat en molts models d’interaccions socials per evitar embussos i estampides durant les evacuacions, a fi de crear protocols més segurs per als nostres edificis i espais públics. Al mig de la nostra navegació ens trobem en una nova epidèmia i ens veiem obligats a un canvi de ruta. Adquirint dades de localització per antenes de mòbils i per gps de smartphones, som capaços de descobrir l’anomenat efecte multi-seeding, que es ha estudiat per la majoria teòricament. Gràcies a models de metapoblacions, confirmem la nostra hipotesis sobre el multiseeding. Els nostres resultats permeten dissenyar polítiques eficients com confinaments selectius i praparar d’una manera millor els sistemes sanitaris d’aquelles àrees més exposades en termes de mobilitat des de les fonts epidèmiques. Mentre l’epidèmia segueix a Europa, vam detectar els primers casos a les costes Americanes. El mateix fenomen que hem vist pot observar-se a escales més petites als Estats Units, aquest cop en ciutats. Aquí necessitem les dades de Google d’alta resolució per veure que les ciutats jeràrquiques exhibeixen difusions més ràpides que a les ciutats decentralizades. Per altra banda, la jerarquia ajuda les polítiques de contenció per millor suprimir el virus, mentre que les mateixes restriccions tenen un menor efecte en les àrees metropolitanes decentralizades. Algunes ciutats són més sensibles que d’altres a la difusió epidèmica requerint una supervisió estricta per evitar que la resta de ciutats i països s’infectin al seu torn. Finalment, per suprimir l’epidèmia és molt important evitar que el virus no sigui embarcat en viatges de llarga distància i infecti noves regions. Gràcies a dades de localització GPS de smartphones, imitem la difusió de diversos virus a escales encara més petites dins de l’aeroport de Heathrow, Londres. Un sistema d’immunització espacial es capaç de reduir fortament els brots dins de l’aeroport i la quantitat de infeccions exportades a l’estranger. La mateixa tècnica es pot aplicar a edificis públics ordinaris per crear espais més segurs per al dia a dia en l’era post-Covid. Gràcies a el mètode científic, vam aconseguir resoldre problemes complexos en el camp de la mobilitat humana amb enfocaments simples i dades relativament grans.