Imagine that a robot fetched this thesis for you from a book shelf. How doyou think the robot would have been programmed? One possibility is thatexperienced engineers had written low level descriptions of all imaginabletasks, including grasping a small book from this particular shelf. A secondoption would be that the robot tried to learn how to grasp books from yourshelf autonomously, resulting in hours of trial-and-error and several bookson the floor.In this thesis, we argue in favor of a third approach where you teach therobot how to grasp books from your shelf through grasping by demonstration.It is based on the idea of robots learning grasping actions by observinghumans performing them. This imposes minimum requirements on the humanteacher: no programming knowledge and, in this thesis, no need for specialsensory devices. It also maximizes the amount of sources from which therobot can learn: any video footage showing a task performed by a human couldpotentially be used in the learning process. And hopefully it reduces theamount of books that end up on the floor. This document explores the challenges involved in the creation of such asystem. First, the robot should be able to understand what the teacher isdoing with their hands. This means, it needs to estimate the pose of theteacher's hands by visually observing their in the absence of markers or anyother input devices which could interfere with the demonstration. Second,the robot should translate the human representation acquired in terms ofhand poses to its own embodiment. Since the kinematics of the robot arepotentially very different from the human one, defining a similarity measureapplicable to very different bodies becomes a challenge. Third, theexecution of the grasp should be continuously monitored to react toinaccuracies in the robot perception or changes in the grasping scenario.While visual data can help correcting the reaching movement to the object,tactile data enables accurate adaptation of the grasp itself, therebyadjusting the robot's internal model of the scene to reality. Finally,acquiring compact models of human grasping actions can help in bothperceiving human demonstrations more accurately and executing them in a morehuman-like manner. Moreover, modeling human grasps can provide us withinsights about what makes an artificial hand design anthropomorphic,assisting the design of new robotic manipulators and hand prostheses. All these modules try to solve particular subproblems of a grasping bydemonstration system. We hope the research on these subproblems performed inthis thesis will both bring us closer to our dream of a learning robot andcontribute to the multiple research fields where these subproblems arecoming from. / QC 20111125

Made available in DSpace on 2014-06-11T19:35:14Z (GMT). No. of bitstreams: 0 Previous issue date: 2004Bitstream added on 2014-06-13T19:45:18Z : No. of bitstreams: 1 matthes_na_dr_fran.pdf: 707612 bytes, checksum: 2287942d8b3b09f0e7cd1207b3e489f8 (MD5) / Universidade Estadual Paulista (UNESP) / Pesquisa de natureza qualitativa que explora a noção de sujeito moriniana no estudo do sujeito-professor, focalizado como homo complexus, sapiens/demens, capaz de racionalidade e de emoção. Sob a ótica da complexidade, a reflexão caminha pelo desvelamento do lado poético do sujeito-professor, buscando evidenciar a presença e a importância da sensibilidade e do imaginário na formação e na ação do agente educativo. Esse caminhar pelo poético significa embrenhar-se pelo estado de encantamento, pelo prazer estético, conhecer as emoções imbricadas no sujeito e ressaltar a importância desse cultivo como alimento de um sentimento humano muitas vezes ausente na vida real. Entendendo a ação educativa como essencialmente humana, o trabalho aproxima a docência da ação do Assistente Social e, dessa forma, ambas emergem, no contexto educacional, como ações humanas carregadas de significado, valores e intenções, interferindo na realidade humano-social. Pensar os vínculos entre Educação e Serviço Social pressupõe uma relação dialógica que ultrapassa a fronteira da especialização e se amplia na interação humana entre os agentes protagonistas da ação educativa. Para enriquecer a pesquisa, foram feitas entrevistas abertas, de natureza narrativa, com professores de Ensino Fundamental, Médio e de Serviço Social. A interpretação dos dados, expressos descritivamente, deu consistência e significado à pesquisa bibliográfica. As conclusões apontam para a inseparabilidade racional/ poético, e, sobretudo, para a importância do poético num cotidiano educativo que pretende remeter à associação de conceitos e ações sociais tais como emancipação humana e transformação social. O fechamento do trabalho abre aos educadores o convite à auto-reflexão sobre a própria... / A qualitative-natured research which explores the notion of subject, according to Morin, in the study of the subject-teacher, focused as Homo Complexus or Sapiens/Demens, who is capable of rationality and emotion. Within the complexity sight, the reflection tends to disclose the subject-teacher's poetic side, trying to make clear the presence and the importance of the sensibility and imaginary in the educational agent's formation and action. This poetic side means to be involved in enchantment, esthetic pleasure; experience the hidden emotions in the subject; and highlight the significance to cultivate such important food to a feeling which human beings lack in real life a lot of times. Understanding the educational action as essentially human, the paper approximates teaching to Social Worker's action and, this way, both emerge, in the educational context, as human actions which are full of meaning, value and intention, intervening in the human-social reality. Thinking about the Education and Social Work chains presupposes a dialogic connection which pushes back the boundaries of specialization and gets larger in the human interaction among educational action protagonists. To enrich the research, some narrative-natured interviews were given by elementary and high school, and Social Work teachers. The data interpretation, descriptively expressed, gave support and meaning to the bibliographic research. The conclusions point out the rational/poetic inseparability, and, essentially, the poetic importance in an educational quotidian which intends to go beyond the concepts association and social actions such as human emancipation and social transformation. The work closing invites educators to the self-reflection upon their own particularity, upon the singular way to integrate their rationality into the human dimension, and upon the art potential in everybody's world's vision formation and in the final citizenship building.

Submitted by Renata Lopes (renatasil82@gmail.com) on 2017-05-30T19:45:09Z No. of bitstreams: 1 dhiegocristianooliveiradasilvasad.pdf: 1920111 bytes, checksum: c7bccda6c65e798776738b9581721c98 (MD5) / Approved for entry into archive by Adriana Oliveira (adriana.oliveira@ufjf.edu.br) on 2017-06-01T11:37:10Z (GMT) No. of bitstreams: 1 dhiegocristianooliveiradasilvasad.pdf: 1920111 bytes, checksum: c7bccda6c65e798776738b9581721c98 (MD5) / Made available in DSpace on 2017-06-01T11:37:10Z (GMT). No. of bitstreams: 1 dhiegocristianooliveiradasilvasad.pdf: 1920111 bytes, checksum: c7bccda6c65e798776738b9581721c98 (MD5) Previous issue date: 2013-02-22 / CAPES - Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / Este trabalho apresenta uma nova abordagem para a descrição de movimento em vídeos usando múltiplos filtros passa-banda que agem como estimadores derivativos de primeira ordem. A resposta dos filtros em cada quadro do vídeo é extraída e codificada em histogramas de gradientes para reduzir a sua dimensionalidade. Essa combinação é realizada através de tensores de orientação. O grande diferencial deste trabalho em relação à maioria das abordagens encontradas na literatura é que nenhuma característica local é extraída e nenhum método de aprendizagem é realizado previamente, isto é, o descritor depende unicamente do vídeo de entrada. Para o problema de reconhecimento da ação humana utilizando a base de dados KTH, nosso descritor alcançou a taxa de reconhecimento de 93,3% usando três filtros da família Daubechies combinado com mais um filtro extra que é a correlação entre esses três filtros. O descritor resultante é então classificado através do SVM utilizando um protocolo two-fold. Essa classificação se mostra superior para a maioria das abordagens que usam descritores globais e pode ser comparável aos métodos do estado-da-arte. / This work presents a novel approach for motion description in videos using multiple band-pass filters that act as first order derivative estimators. The filters response on each frame are coded into individual histograms of gradients to reduce their dimensionality. They are combined using orientation tensors. No local features are extracted and no learning is performed, i.e., the descriptor depends uniquely on the input video. Motion description can be enhanced even using multiple filters with similar or overlapping fre quency response. For the problem of human action recognition using the KTH database, our descriptor achieved the recognition rate of 93,3% using three Daubechies filters, one extra filter designed to correlate them, two-fold protocol and a SVM classifier. It is su perior to most global descriptor approaches and fairly comparable to the state-of-the-art methods.

Submitted by Renata Lopes (renatasil82@gmail.com) on 2017-06-06T17:54:07Z No. of bitstreams: 1 felipeandradecaetano.pdf: 7461489 bytes, checksum: 93cea870d7bf162be4786d1d6ffb2ec9 (MD5) / Approved for entry into archive by Adriana Oliveira (adriana.oliveira@ufjf.edu.br) on 2017-06-07T11:06:08Z (GMT) No. of bitstreams: 1 felipeandradecaetano.pdf: 7461489 bytes, checksum: 93cea870d7bf162be4786d1d6ffb2ec9 (MD5) / Made available in DSpace on 2017-06-07T11:06:08Z (GMT). No. of bitstreams: 1 felipeandradecaetano.pdf: 7461489 bytes, checksum: 93cea870d7bf162be4786d1d6ffb2ec9 (MD5) Previous issue date: 2014-08-29 / Trajetórias densas têm se mostrado um método extremamente promissor na área de reconhecimento de ações humanas. Baseado nisso, propomos um novo tipo de descritor de vídeos, calculado a partir da relação do fluxo ótico que compõe a trajetória com o gradiente de sua vizinhança e sua localidade espaço-temporal. Tensores de orientação são usados para acumular informação relevante ao longo do vídeo, representando tendências de direção do descritor para aquele tipo de movimento. Além disso, um método para aglomerar trajetórias usando o seu formato como métrica é proposto. Isso permite acu- mular características de movimentos distintos em tensores separados e diferenciar com maior facilidade trajetórias que são criadas por movimentos reais das que são geradas a partir do movimento de câmera. O método proposto foi capaz de atingir os melhores níveis de reconhecimento conhecidos para métodos com a restrição de métodos autodescritores em bases populares — Hollywood2 (Acima de 46%) e KTH (Acima de 94%). / Dense trajectories has been shown as a very promising method in the human action recognition area. Based on that, we propose a new kind of video descriptor, calculated from the relationship between the trajectory’s optical flow with the gradient field in its neighborhood and its spatio-temporal location. Orientation tensors are used to accumulate relevant information over the video, representing the tendency of direction for that kind of movement. Furthermore, a method to cluster trajectories using their shape is proposed. This allow us to accumulate different motion patterns in different tensors and easier distinguish trajectories that are created by real movements from the trajectories generated by the camera’s movement. The proposed method is capable to achieve the best known recognition rates for methods based on the self-descriptor constraint in popular datasets — Hollywood2 (up to 46%) and KTH (up to 94%).

The aim is to present specific methodology of the austrian school with laying stress on prerequisits which determine its understanding of phenomena.

Nous nous intéressons dans cette thèse à la modélisation des interactions entre personnes, objets et scènes. Nous montrons l’intérêt de combiner ces trois sources d’information pour améliorer la classification d’action et la compréhension automatique des scènes. Dans la première partie, nous cherchons à exploiter le contexte fourni par les objets et la scène pour améliorer la classification des actions humaines dans les photographies. Nous explorons différentes variantes du modèle dit de “bag-of-features” et proposons une méthode tirant avantage du contexte scénique. Nous proposons ensuite un nouveau modèle exploitant les objets pour la classification d’action basé sur des paires de détecteurs de parties du corps et/ou d’objet. Nous évaluons ces méthodes sur notre base de données d’images nouvellement collectée ainsi que sur trois autres jeux de données pour la classification d’action et obtenons des résultats proches de l’état de l’art. Dans la seconde partie de cette thèse, nous nous attaquons au problème inverse et cherchons à utiliser l’information contextuelle fournie par les personnes pour aider à la localisation des objets et à la compréhension des scènes. Nous collectons une nouvelle base de données de time-lapses comportant de nombreuses interactions entre personnes, objets et scènes. Nous développons une approche permettant de décrire une zone de l’image par la distribution des poses des personnes qui interagissent avec et nous utilisons cette représentation pour améliorer la localisation d’objets. De plus, nous démontrons qu’utiliser des informations provenant des personnes détectées peut améliorer plusieurs étapes de l’algorithme utilisé pour la compréhension des scènes d’intérieur. Pour finir, nous proposons des annotations 3D de notre base de time-lapses et montrons comment estimer l’espace utilisé par différentes classes d’objets dans une pièce. Pour résumer, les contributions de cette thèse sont les suivantes : (i) nous mettons au point des modèles pour la classification d’image tirant avantage du contexte scénique et des objets environnants et nous proposons une nouvelle base de données pour évaluer leurs performances, (ii) nous développons un nouveau modèle pour améliorer la localisation d’objet grâce à l’observation des acteurs humains interagissant avec une scène et nous le testons sur un nouveau jeu de vidéos comportant de nombreuses interactions entre personnes, objets et scènes, (iii) nous proposons la première méthode pour évaluer les volumes occupés par différentes classes d’objets dans une pièce, ce qui nous permet d’analyser les différentes étapes pour la compréhension automatique de scène d’intérieur et d’en identifier les principales sources d’erreurs. / In this thesis, we focus on modeling interactions between people, objects and scenes and show benefits of combining corresponding cues for improving both action classification and scene understanding. In the first part, we seek to exploit the scene and object context to improve action classification in still images. We explore alternative bag-of-features models and propose a method that takes advantage of the scene context. We then propose a new model exploiting the object context for action classification based on pairs of body part and object detectors. We evaluate our methods on our newly collected still image dataset as well as three other datasets for action classification and show performance close to the state of the art. In the second part of this thesis, we address the reverse problem and aim at using the contextual information provided by people to help object localization and scene understanding. We collect a new dataset of time-lapse videos involving people interacting with indoor scenes. We develop an approach to describe image regions by the distribution of human co-located poses and use this pose-based representation to improve object localization. We further demonstrate that people cues can improve several steps of existing pipelines for indoor scene understanding. Finally, we extend the annotation of our time-lapse dataset to 3D and show how to infer object labels for occupied 3D volumes of a scene. To summarize, the contributions of this thesis are the following: (i) we design action classification models for still images that take advantage of the scene and object context and we gather a new dataset to evaluate their performance, (ii) we develop a new model to improve object localization thanks to observations of people interacting with an indoor scene and test it on a new dataset centered on person, object and scene interactions, (iii) we propose the first method to evaluate the volumes occupied by different object classes in a room that allow us to analyze the current 3D scene understanding pipeline and identify its main source of errors.

Les travaux de cette thèse portent sur l’élaboration d’une approche d’anticipation des comportements possibles de l’opérateur humain lorsqu’il ne respecte pas certaines règles de sécurité. Le non-respect des règles de sécurité, considéré comme une erreur humaine, constitue la source majeure d’incidents/accidents dans le domaine des agroéquipements. Ce domaine caractérisé par un manque de formalisation de son REX. L’approche proposée consiste à définir une méthodologie permettant de proposer des plans d’actions humaines possibles résultant d’un non-respect des règles de sécurité et de les évaluer par la suite. La génération des plans d’actions alternatifs aux prescriptions est réalisée à travers un outil que nous avons développé, baptisé A2PG (Alternative Action Plan Generator). Ce dernier, s’inspirant des modèles de l’opérateur humain, est basé sur les paramètres suivants à définir : la tâche à réaliser et le catalogue d’actions qui contient l’ensemble des actions, des pré-conditions nécessaires et de sécurité associées à chaque action ainsi que les effets de l’exécution de l’action. Le non-respect peut être modélisé au niveau d’A2PG par la variation d’au moins un de ses paramètres (sauf les pré-conditions nécessaires). Nous nous sommes intéressés plus particulièrement à la variation des pré-conditions de sécurité, c'est-à-dire la non-prise en compte par l’opérateur humain des pré-conditions de sécurité. Des algorithmes de génération des plans d’actions alternatifs ont été mises en œuvre. L’identification des plans a été réalisée à travers une adaptation de l’algorithme SHOP2 qui se base sur le planificateur HTN (Hierarchical Task Network). Les plans alternatifs sont élaborer par un algorithme qui permet principalement de définir les combinaisons de pré-conditions de sécurité à considéré dans la spécification d’A2PG et dont au moins une pré-condition de sécurité est supprimée. L’applicabilité de l’approche a été démontrée sur le cas des tondeuses à gazon autoportées. / These research works concern the development of an approach anticipating the possible human behaviours when they do not respect safety rules. The failure in complying with safety rules, considered human error, is the major source of incidents/accidents in agricultural equipment field. The proposed approach consists in defining a tool for generation of human action plans. An action plan is a sequence of actions allowing the achievement goal. The identification of these plans is done through the implementation of algorithms of planning methods based on hirerachical methods. These allow the decomposition of tasks into sub-tasks according to the chose specification of the generator. This specification consists in defining the parameters of the generator in order to simulate the failure in complying with safety rule. It concerns the following input parameters; task to achieve, safety preconditions, action effects, actions, list. Work then focus on the defining of a strategy based on the expert judgements to assess the human action plans, produced by the generator, in terms of credibility. The developed approach is a part of an improvement human factors consideration in risk analysis of agricultural equipment. Finally, this approach is demonstrated by its application to the riding lawn mower.

Human actions are the essence of a human life and a natural product of the human mind. Analysis of human activities by a machine has attracted the attention of many researchers. This analysis is very important in a variety of domains including surveillance, video retrieval, human-computer interaction, athlete performance investigation, etc. This dissertation makes three major contributions to automatic analysis of human actions. First, we conjecture that the relationship between body joints of two actors in the same posture can be described by a 3D rigid transformation. This transformation simultaneously captures different poses and various sizes and proportions. As a consequence of this conjecture, we show that there exists a fundamental matrix between the imaged positions of the body joints of two actors, if they are in the same posture. Second, we propose a novel projection model for cameras moving at a constant velocity in 3D space, \emph cameras, and derive the Galilean fundamental matrix and apply it to human action recognition. Third, we propose a novel use for the invariant ratio of areas under an affine transformation and utilizing the epipolar geometry between two cameras for 2D model-based tracking of human body joints. In the first part of the thesis, we propose an approach to match human actions using semantic correspondences between human bodies. These correspondences are used to provide geometric constraints between multiple anatomical landmarks ( e.g. hands, shoulders, and feet) to match actions observed from different viewpoints and performed at different rates by actors of differing anthropometric proportions. The fact that the human body has approximate anthropometric proportion allows for innovative use of the machinery of epipolar geometry to provide constraints for analyzing actions performed by people of different anthropometric sizes, while ensuring that changes in viewpoint do not affect matching. A novel measure in terms of rank of matrix constructed only from image measurements of the locations of anatomical landmarks is proposed to ensure that similar actions are accurately recognized. Finally, we describe how dynamic time warping can be used in conjunction with the proposed measure to match actions in the presence of nonlinear time warps. We demonstrate the versatility of our algorithm in a number of challenging sequences and applications including action synchronization , odd one out, following the leader, analyzing periodicity etc. Next, we extend the conventional model of image projection to video captured by a camera moving at constant velocity. We term such moving camera Galilean camera. To that end, we derive the spacetime projection and develop the corresponding epipolar geometry between two Galilean cameras. Both perspective imaging and linear pushbroom imaging form specializations of the proposed model and we show how six different ``fundamental" matrices including the classic fundamental matrix, the Linear Pushbroom (LP) fundamental matrix, and a fundamental matrix relating Epipolar Plane Images (EPIs) are related and can be directly recovered from a Galilean fundamental matrix. We provide linear algorithms for estimating the parameters of the the mapping between videos in the case of planar scenes. For applying fundamental matrix between Galilean cameras to human action recognition, we propose a measure that has two important properties. First property makes it possible to recognize similar actions, if their execution rates are linearly related. Second property allows recognizing actions in video captured by Galilean cameras. Thus, the proposed algorithm guarantees that actions can be correctly matched despite changes in view, execution rate, anthropometric proportions of the actor, and even if the camera moves with constant velocity. Finally, we also propose a novel 2D model based approach for tracking human body parts during articulated motion. The human body is modeled as a 2D stick figure of thirteen body joints and an action is considered as a sequence of these stick figures. Given the locations of these joints in every frame of a model video and the first frame of a test video, the joint locations are automatically estimated throughout the test video using two geometric constraints. First, invariance of the ratio of areas under an affine transformation is used for initial estimation of the joint locations in the test video. Second, the epipolar geometry between the two cameras is used to refine these estimates. Using these estimated joint locations, the tracking algorithm determines the exact location of each landmark in the test video using the foreground silhouettes. The novelty of the proposed approach lies in the geometric formulation of human action models, the combination of the two geometric constraints for body joints prediction, and the handling of deviations in anthropometry of individuals, viewpoints, execution rate, and style of performing action. The proposed approach does not require extensive training and can easily adapt to a wide variety of articulated actions.

Motion classification and action localization have rapidly become essential tasks in computer vision and video analytics. In particular, Human Action Recognition (HAR), which has important applications in clinical assessments, activity monitoring, and sports performance evaluation, has drawn a lot of attention in research communities. Nevertheless, the high-dimensional and time-continuous nature of motion data creates non-trivial challenges in action detection and action recognition. In this degree project, on a set of recorded unannotated mixed workouts, we test and evaluate unsupervised and semi-supervised machine learning models to identify the correct location, i.e., a timestamp, of various exercises in videos and to study different approaches in clustering detected actions. This is done by modelling the data via the two-step clustering pipeline using the Bag-of-Visual-Words (BoVW) approach. Moreover, the concept of repetition counting is under consideration as a parallel task. We find that clustering alone tends to produce cluster solutions with a mixture of exercises and is not sufficient to solve the exercise recognition problem. Instead, we use clustering as an initial step to aggregate similar exercises. This allows us to effectively find many repetitions of similar exercises for their further annotation. When combined with a subsequent Support Vector Machine (SVM) classifier, the BoVW concept proved itself, achieving an accuracy score of 95.5% on the labelled subset. Much attention has also been paid to various methods of dimensionality reduction and benchmarking their ability to encode the original data into a lower-dimensional latent space. / Rörelseklassificering och handlingslokalisering har snabbt blivit viktiga uppgifter inom datorseende och videoanalys. I synnerhet har HAR fångat en stor uppmärksamhet i forskarsamhällen, då den har viktiga tillämpningar i kliniska bedömningar, aktivitetsövervakning och utvärdering av sportprestanda.Likväl så skapar den högdimensionella och tidskontinuerliga naturen hos rörelsedata icke-triviala utmaningar i handlingsdetektering och handlingsigenkänning. I detta examensarbete testar vi samt utvärderar oövervakade och semi-övervarakde maskininlärningsmodeller på en samling av inspelade blandade träningspass, som inte är noterade. Detta är för att identifiera den korrekta positionen, d.v.s en tidsstämpel, för olika övningar i videofilmer och för att studera olika tillvägagångssätt för att gruppera upptäckta handlingar. Detta görs genom att modellera data via tvåstegs klustringspipeline, med tillämpning av BoVW-metoden. Som en parallell uppgift övervägs även repetitionsräkning som koncept. Vi finner att kluster enbart tenderar att producera klusterlösningar med en blandning av övningar och är därför inte tillräckligt för att lösa problemet med övningsigenkänning. Istället, använder vi klustring som ett första steg för att sammanställa liknande övningar. Detta gör att vi effektivt kan hitta många upprepningar av liknande övningar för att vidare hantera dess anteckningar. Detta, kombinerad med en efterföljande SVM-klassificerare, visade sig att BoVWkonceptet är mycket effektivt, vilket uppnådde en noggrannhet på 95, 5% på den märkta delmängden. Mycket uppmärksamhet har också ägnats åt olika metoder för dimensionalitetsreduktion och jämförelse av dessa metoders förmåga att koda originaldata till ett dimensionellt lägre latentutrymme.

The first part of the thesis deals with the constitution of the modern conception of history as an independent ontological region, which is characterized by its reflexivity, i.e. the same word history does mean both action and knowledge, information about it. From this perspective, attention is paid to the main stages of development of historiography. We start with constitution of the modern conception of history in the Enlightenment and its philosophical explanation in Kant (§ 2). Followed by an analysis of the historical method developed by Droysen, being shown how the methodological limitations of this approach were associated with understanding the historical reflexivity as identity, inherited from idealistic philosophy (§ 3). A rejection of the sociological approaches in historiography refers to fundamental differences in the conception of the relationship of knowledge and action in both types of disciplines (§ 4). Great attention is paid to the renaissance of historiography attaching to enforcement cultural-anthropological paradigm, in which it was seen as a solution of problems connected with historicism and social science approach (§ 5). The second part concentrates on the analysis of the basic philosophical assumptions of cultural anthropology. Exploration leads to the establishment of the...