Dissertations / Theses on the topic 'Guerre pour la reconnaissance'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Guerre pour la reconnaissance.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
Shtembari, Arber. "Après la guerre : Mobilisations et luttes pour la reconnaissance. Contribution à une analyse sociohistorique de la construction de l'Etat au Kosovo (1945-2012)." Thesis, Limoges, 2016. http://www.theses.fr/2016LIMO0057.
Full textThis thesis examines jointly, the mobilizations and the classification struggles of the post-war groups in Kosovo after 1999, focusing on the access procedures toward their legal and legitimate recognition. It also analyzes the State formation process in Kosovo and the production of its symbolic forms of consecration. Two main contributions of this work are: First, it highlights a number of issues on post-war groups formation, identification, lifestyles and definition (civils victims, war veterans, war prisoners, families of missing persons, etc.) needing reflection and it questions the conventional wisdom. Second, it examines the complex relationships between the symbolic domination work of the State in Kosovo and the struggles of post-war groups in freeing from their social condition
Parenteau, Danic. "La guerre pour l'Esprit hégélien." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1998. http://www.collectionscanada.ca/obj/s4/f2/dsk2/tape15/PQDD_0008/MQ28451.pdf.
Full textMasse, Henri. "Une guerre pour les Malouines." Metz, 1997. http://docnum.univ-lorraine.fr/public/UPV-M/Theses/1997/Masse.Henri.LMZ9710.pdf.
Full textThe malouines (falklands - malvinas) war of 1982 : the falklands islands, their colonizations, disputes about soveraignty, importance of these islands in maritime and naval history (battle of 1914 cruise of the graf spee in 1939). The angle-argentine dispute, from the british occupations of 1833 to the crisis of 1982, argentine landings, british reations, the task force, naval, air ans ground forces and operations, blocus and exclusion zones, british bombings and presence of special forces, landing in san carlos and argentine surrender looses balance and aftermath of the war. Technical figures and historical elements about aircrafts, ships and armaments, the heavy air transport, the british marchant ships in the falklands war, bibliography
Thalineau, Alain. "La lutte inégale pour la reconnaissance." Habilitation à diriger des recherches, Université Paris VIII Vincennes-Saint Denis, 2005. http://tel.archives-ouvertes.fr/tel-00818248.
Full textGrondin, François. "Reconnaissance de locuteurs pour robot mobile." Mémoire, Université de Sherbrooke, 2012. http://savoirs.usherbrooke.ca/handle/11143/1632.
Full textManh, Anne-Gaëlle. "Modèles déformables pour la reconnaissance d'adventices." Montpellier 2, 2001. http://www.theses.fr/2001MON20208.
Full textKulikova, Maria. "Reconnaissance de forme pour l'analyse de scène." Phd thesis, Université de Nice Sophia-Antipolis, 2009. http://tel.archives-ouvertes.fr/tel-00477661.
Full textBoulay, Bernard. "Reconnaissance de postures pour l'interprétation d'activité humaine." Phd thesis, Université de Nice Sophia-Antipolis, 2007. http://tel.archives-ouvertes.fr/tel-00311741.
Full textPietropaoli, Bastien. "Reconnaissance de contexte stable pour l'habitat intelligent." Phd thesis, Université Rennes 1, 2013. http://tel.archives-ouvertes.fr/tel-00917776.
Full textDuchenne, Olivier. "Alignement élastique d'images pour la reconnaissance d'objet." Phd thesis, Ecole Normale Supérieure de Paris - ENS Paris, 2012. http://tel.archives-ouvertes.fr/tel-01063352.
Full textBoumaza, Rachid. "Perception multisensorielle pour la reconnaissance d'objets tridimensionnels." Toulouse 3, 1994. http://www.theses.fr/1994TOU30098.
Full textHizem, Walid. "Capteur intelligent pour la reconnaissance de visage." Evry, Institut national des télécommunications, 2009. http://www.theses.fr/2009TELE0003.
Full textIllumination variation is one of the factors that has the greatest impact on the performance of a facial recognition system, especially in a mobility situation where the operator cannot control lighting. In this work, we present a new sensor that reduces ambient light; the resulting image shows greater stability in relation to changes in ambient light. This sensor relies on a reduction of exposure time, so as to capture only a small quantity of ambient light, and during the exposure, a flash emitting a near-infrared light is activated. The resulting image is therefore dependent upon the luminance of the flash. A second characteristic of this sensor is the simultaneous production of a near-infrared image and a normal image acquired in ambient light. Besides this new sensor, we also aimed in among this and in view of a future implementation of our approach, we elaborated a method to detect landmarks in near-infrared images. This algorithm is based on the use of simple operators that has been implemented. The stability of the images in relation to the lighting changes allowed us to elaborate a simple method. Using the landmarks detected and the edge image, we constructed a face-recognition algorithm, inspired by elastic graph matching, in order to build a model of the face. We compared the performance of our system to that of basic face-recognition algorithms, and achieved recognition levels equal to those of classic elastic graph matching
Fua, Pascal. "Une approche variationnelle pour la reconnaissance d'objets." Paris 11, 1989. http://www.theses.fr/1989PA112357.
Full textDelépine, Anne-Sophie. "Polyamines pour la reconnaissance d'anions d'intérêt biologique." Brest, 2009. http://www.theses.fr/2009BRES2009.
Full textPhysico-chernicalproperties of cyclic and linear polyamines are now well known since they are recognized to form highly stable complexes with metallic cations, and to interact with anionic substrates in aqueous medium aller protonation of the nitrogen atoms. As for cation complexation, there is a growing interest in the molecular recognition of anionic species because of their potential applications in environmental, industrial and health-related areas. Phosphate-type anions are ubiquitous as well in human activity effluents as in biological structures. 0ur work was then devoted to the study of inorganic and organic polyphosphates complexation, especially triphosphate and adénosine triphosphate (ATP), by di- et tri-topic ligands derived from a cyclic tetraamine (cyclen), and two linear tetraamines (N,N’-bis(2-aminoethyl)-l,3-propanediamine and triethylenetetramine), linked by rigid benzyl or pyridinyl spacer. We fisrtly report the synthesis of two families of ligands previously developed in ow group, as well and we describe a third class of ligands obtained by a new easy to run selective mono-Nalkylation of triethylenetetraamine using the bisaminal tool. The effect of both basicity and geometry of these ligands on the complexation of inorganic and organic polyphosphates were then investigated using potentiometry and NMR spectroscopy. These studies allowed a better understanding of the key features governing the ligand-substrate interactions. Among them, η-stacking interactions between the aromatic spacer of the ligand and the adenine ring of ATP, and the importance of the nitrogen atom of the pyridyl spacer as additional anchoring point were proved to stabilize efficiently the host-guest complexes
Pietropaoli, Paoli. "Reconnaissance de contexte stable pour l'habitat intelligent." Thesis, Rennes 1, 2013. http://www.theses.fr/2013REN1S148/document.
Full textSmart home is a major subject of interest. It helps to assist elderly or disabled people, improve comfort, safety, and also save energy. Today, ubiquitous computing is developed and integrated into the smart home providing context-awareness. Unfortunately, understanding what happens in a home is not always easy. In this thesis, we explain how context can be used to deploy services tailored to the activities and needs of residents. Understanding context requires the installation of sensors but also the abstraction of raw data into easily understandable data usable by humans and services. We present a multi-layer architecture of data fusion used to obtain contextual information of different levels of abstraction. The implementation of the lower layers is presented in detail with the application of the theory of belief functions for the abstraction of raw sensor data. Finally, are presented the deployment of a prototype that allowed us to validate our approach and the deployed services
Ben, Ameur Rihab. "Fusion multimodale pour la reconnaissance d'espèces d'arbres." Thesis, Université Grenoble Alpes (ComUE), 2018. http://www.theses.fr/2018GREAA005/document.
Full textInformation fusion systems allow the combination of data issued from different sources of information while considering their quality. Combining data from heterogeneous sources makes it possible to take advantage of the complementarity of the data and thus potentially have higher performances than those obtained when using a single source of information.The use of these systems is interesting in the context of tree species recognition through the fusion of information issued from two modalities : leaves and barks. A single modality may represent different sources of information, each describing one of its most relevant characteristics. This makes it possible to reproduce the strategy adopted by botanists who base themselves on these same criteria. The adoption of this strategy is part of the enhancement of the educational aspect. In this context, a merger system is conceivable in order to combine the data issued from one modality as well as the data issued from different modalities. In the context of tree species recognition, we treat a real problem since the photos of leaves and bark are taken in the natural environment. The processing of this type of data is complicated because of their specificities due firstly to the nature of the objects to be recognized (age, inter-species similarity and intra-species variability) and secondly to the environment.Errors can be accumulated during the pre-fusion process. The merit of the fusion is to take into account all the imperfections that can taint the available data and try to model them well. The fusion is more effective if the data is well modeled. The theory of belief functions represents one of the best theoretical frameworks able to manage and represent uncertainty, inaccuracy, conflict, etc. This theory is important because of its wealth of tools to manage the various sources of imperfections as well as the specificities of the available data. In the framework of this theory, it is possible to model the data through the construction of mass functions. It is also possible to manage the computational complexity thanks to the approximations allowing to reduce the number of focal elements. Conflict being one of the most present sources of imperfections, can be dealt through the selection of the best combination rule.By merging sources of information with different degrees of reliability, it is possible that the least reliable source affects the data issued from the most reliable one. One of the solutions for this problem is to try to improve the performances of the least reliable source. Thus, by merging with other sources, it will provide useful information and will in turn contribute in improving the performance of the fusion system.The performance improvement of an information source can be effected through the correction of mass functions. In this context, the correction can be made based on measures of the relevance or sincerity of the studied source. The confusion matrices present a data source from which meta-knowledge characterizing the state of a source can be extracted. In this manuscript, the proposed fusion system is a hierarchical fusion system set up within the framework of belief function theory. It allows to merge data from leaves and barks and provides the user with a list of the most likely species while respecting the educational purpose of the application. The computational complexity of this fusion system is quite small allowing, in the long term, to implement the application on a Smart-phone
Saxena, Shreyas. "Apprentissage de représentations pour la reconnaissance visuelle." Thesis, Université Grenoble Alpes (ComUE), 2016. http://www.theses.fr/2016GREAM080/document.
Full textIn this dissertation, we propose methods and data driven machine learning solutions which address and benefit from the recent overwhelming growth of digital media content.First, we consider the problem of improving the efficiency of image retrieval. We propose a coordinated local metric learning (CLML) approach which learns local Mahalanobis metrics, and integrates them in a global representation where the l2 distance can be used. This allows for data visualization in a single view, and use of efficient ` 2 -based retrieval methods. Our approach can be interpreted as learning a linear projection on top of an explicit high-dimensional embedding of a kernel. This interpretation allows for the use of existing frameworks for Mahalanobis metric learning for learning local metrics in a coordinated manner. Our experiments show that CLML improves over previous global and local metric learning approaches for the task of face retrieval.Second, we present an approach to leverage the success of CNN models forvisible spectrum face recognition to improve heterogeneous face recognition, e.g., recognition of near-infrared images from visible spectrum training images. We explore different metric learning strategies over features from the intermediate layers of the networks, to reduce the discrepancies between the different modalities. In our experiments we found that the depth of the optimal features for a given modality, is positively correlated with the domain shift between the source domain (CNN training data) and the target domain. Experimental results show the that we can use CNNs trained on visible spectrum images to obtain results that improve over the state-of-the art for heterogeneous face recognition with near-infrared images and sketches.Third, we present convolutional neural fabrics for exploring the discrete andexponentially large CNN architecture space in an efficient and systematic manner. Instead of aiming to select a single optimal architecture, we propose a “fabric” that embeds an exponentially large number of architectures. The fabric consists of a 3D trellis that connects response maps at different layers, scales, and channels with a sparse homogeneous local connectivity pattern. The only hyperparameters of the fabric (the number of channels and layers) are not critical for performance. The acyclic nature of the fabric allows us to use backpropagation for learning. Learning can thus efficiently configure the fabric to implement each one of exponentially many architectures and, more generally, ensembles of all of them. While scaling linearly in terms of computation and memory requirements, the fabric leverages exponentially many chain-structured architectures in parallel by massively sharing weights between them. We present benchmark results competitive with the state of the art for image classification on MNIST and CIFAR10, and for semantic segmentation on the Part Labels dataset
Vazquez, Rodriguez Juan Fernando. "Transformateurs multimodaux pour la reconnaissance des émotions." Electronic Thesis or Diss., Université Grenoble Alpes, 2023. http://www.theses.fr/2023GRALM057.
Full textMental health and emotional well-being have significant influence on physical health, and are especially important for healthy aging. Continued progress on sensors and microelectronics has provided a number of new technologies that can be deployed in homes and used to monitor health and well-being. These can be combined with recent advances in machine learning to provide services that enhance the physical and emotional well-being of individuals to promote healthy aging. In this context, an automatic emotion recognition system can provide a tool to help assure the emotional well-being of frail people. Therefore, it is desirable to develop a technology that can draw information about human emotions from multiple sensor modalities and can be trained without the need for large labeled training datasets.This thesis addresses the problem of emotion recognition using the different types of signals that a smart environment may provide, such as visual, audio, and physiological signals. To do this, we develop different models based on the Transformer architecture, which has useful characteristics such as their capacity to model long-range dependencies, as well as their capability to discern the relevant parts of the input. We first propose a model to recognize emotions from individual physiological signals. We propose a self-supervised pre-training technique that uses unlabeled physiological signals, showing that that pre-training technique helps the model to perform better. This approach is then extended to take advantage of the complementarity of information that may exist in different physiological signals. For this, we develop a model that combines different physiological signals and also uses self-supervised pre-training to improve its performance. We propose a method for pre-training that does not require a dataset with the complete set of target signals, but can rather, be trained on individual datasets from each target signal.To further take advantage of the different modalities that a smart environment may provide, we also propose a model that uses as inputs multimodal signals such as video, audio, and physiological signals. Since these signals are of a different nature, they cover different ways in which emotions are expressed, thus they should provide complementary information concerning emotions, and therefore it is appealing to use them together. However, in real-world scenarios, there might be cases where a modality is missing. Our model is flexible enough to continue working when a modality is missing, albeit with a reduction in its performance. To address this problem, we propose a training strategy that reduces the drop in performance when a modality is missing.The methods developed in this thesis are evaluated using several datasets, obtaining results that demonstrate the effectiveness of our approach to pre-train Transformers to recognize emotions from physiological signals. The results also show the efficacy of our Transformer-based solution to aggregate multimodal information, and to accommodate missing modalities. These results demonstrate the feasibility of the proposed approaches to recognizing emotions from multiple environmental sensors. This opens new avenues for deeper exploration of using Transformer-based approaches to process information from environmental sensors and allows the development of emotion recognition technologies robust to missing modalities. The results of this work can contribute to better care for the mental health of frail people
Saeed, Usman. "Analyse des lèvres pour reconnaissance des personnes." Phd thesis, Télécom ParisTech, 2010. http://pastel.archives-ouvertes.fr/pastel-00005849.
Full textSaeed, Usman. "Analyse des lèvres pour reconnaissance des personnes." Phd thesis, Paris, Télécom ParisTech, 2010. https://pastel.hal.science/pastel-00005849.
Full textIn this doctoral dissertation we focus on a local feature of the human face namely the lip and analyse it for its relevance and influence on person recognition. In depth study is carried out with respect to various steps involved, such as detection, evaluation, normalization and the applications of the human lip motion. Initially we present a lip detection algorithm that is based on the fusion of two independent methods. The first method is based on edge detection and the second one on region segmentation, each having distinct characteristics and thus exhibit different strengths and weaknesses. We exploit these strengths by combining the two methods using fusion. Next we extract features which model the behavioural aspect of lip motion during speech and exploit them for person recognition. The behavioural features include static features and dynamic features based on optical flow. These features are used to build client model by Gaussian Mixture Model (GMM) and finally the classification is achieved using a Bayesian decision rule. Lastly we propose a temporal normalization method for handling the variation caused by lip motion during speech. Given a group of videos for a person uttering the same sentence multiple times we study the lip motion in one of the videos and select certain key frames as synchronization frames. We then synchronize these frames from the first video with the remaining videos of the same person. Finally all the videos are normalized temporally by interpolation using lip morphing
Idan, Yizhak. "Contribution à l'étude des réseaux de neurones formels pour la reconnaissance des formes : application pour la reconnaissance de chiffres manuscrits /." Paris : École nationale supérieure des télécommunications, 1993. http://catalogue.bnf.fr/ark:/12148/cb35579882x.
Full textBarrat, Sabine. "Modèles graphiques probabilistes pour la reconnaissance de formes." Phd thesis, Université Nancy II, 2009. http://tel.archives-ouvertes.fr/tel-00530755.
Full textDefretin, Joseph. "Stratégies de vision active pour la reconnaissance d'objets." Phd thesis, École normale supérieure de Cachan - ENS Cachan, 2011. http://tel.archives-ouvertes.fr/tel-00696044.
Full textRoy, Patrice C. "Modèle possibiliste pour la reconnaissance d'activités habitat intelligent." Thèse, Université de Sherbrooke, 2012. http://savoirs.usherbrooke.ca/handle/11143/5171.
Full textBazeille, Stéphane. "Vision sous-marine monoculaire pour la reconnaissance d'objets." Brest, 2008. http://www.theses.fr/2008BRES2023.
Full textIn underwater context, traditional sensing methods like sonar are used at large range for detection and classification of objects. For a few years, the sonar sensor has been complemented by a vision sensor more efficient at short range for the approach, the object recognition and the intervention phases. Indeed, the camera has noticeable advantages like for example high resolution, simple interpretation or low cost. Today, it equips nearly any scientific, industrial or military underwater vehicles. Currently, underwater vehicles are rather distance controlled by a manipulator, and automatic processing is really uncommon. However, automatic processing is an essential technology for the AUV development. These kinds of vehicles are very popular today with the expansion of the market related to the security and the exploitation of the marine resources. This thesis aims at supplying the required advances and promoting the use of video technologies. The proposed study addresses the problem of automatic processing for underwater objects recognition, with a particular focus on man-made objects. Observed underwater scenes are traditionally simpler but more limited in depth than urban scenes or inside building scenes. Nevertheless, this context presents very specific difficulties like lighting variations and water turbidity which limit visibility and degrade considerably images. As a consequence processing is difflcult and require the development of new robotic vision algorithms
CANAMERO, MATESANZ DOLORES. "Replace : un modele pour la reconnaissance de plans." Paris 11, 1995. http://www.theses.fr/1995PA112516.
Full textLebourgeois, Frank. "Approche mixte pour la reconnaissance des documents imprimes." Lyon, INSA, 1991. http://www.theses.fr/1991ISAL0013.
Full textA recognition system for multi font printed documents using contextual informations about typography, structure of document and syntax, has been developed. First, a quick bottom up method to separate text from image and recognize logical structure of documents has been achieved. A mixed approach has been used to recognize individual characters. A first stage realizes a compaction at the character level compared to a dynamically built librairy of shapes. The high redundancy of character's image in printed document justifies this approach. A second stage structurally recognizes the previously built models of characters. A mixed syntaxic and statistic stage is used simultanous. It o perform a high recognition rate
Sur, Frédéric. "Décision à contrario pour la reconnaissance de formes." Paris 9, 2004. https://portail.bu.dauphine.fr/fileviewer/index.php?doc=2004PA090048.
Full textShape recognition is a field of computer vision which has many applications. It addresses the problem of finding out whether a query shape lies or not in a shape database, up to a certain invariance. Most shape recognition methods simply sort shapes from the database along some similarity measure to the query shape. Their Achilles' heel is the decision stage, which should aim at giving a clear-cut answer to the question: "do these two shapes look alike"? In this PhD thesis, the proposed solution consists in bounding the "number of false alarms" of the query shape among the database shapes. A grouping stage improves the level of confidence in the obtained detections. All along the thesis, a contrario decisions are made: a background model is designed, then the rarer an event is for this model, the more significant it ought to be considered
Camus, Matthieu. "Identification audio pour la reconnaissance de la parole." Paris 5, 2011. http://www.theses.fr/2011PA05S014.
Full textThis PhD thesis takes place within the framework of the speech recognition in audio contents. The purpose of this work is to adapt the principles of audio identification to speech recognition as well as to design and to develop robust identification techniques. Audio identification systems by audio fingerprinting are designed to music track indexation but do not handle the specificities of the speech signal. At first, various methods of audio identification by fingerprint are studied as well as a first work of adaptation to speech recognition. This work is followed by the development of an audio identification system by fingerprint dedicated to the ask of acoustic-phonetic decoding. New types of subfingerprint based on usual speech parameters are then proposed. Secondly, the various types of variability of the speech signal are described as well as the main parameters of acoustic representation of the speech signal. The robustness of various types of subfingerprint in extrincic variability and in intrinsic variability is estimated. In the presence of disturbances related to the environment and to the conditions of transmission of the speech signal (CTIMIT), a type of subfingerprint stemming from the audio identification turns out then the most robust
Das, Srijan. "Mécanismes d'attention spatio-temporels pour la reconnaissance d'activité." Thesis, Université Côte d'Azur, 2020. https://tel.archives-ouvertes.fr/tel-03177892.
Full textThis thesis targets recognition of human actions in videos. Action recognition is a complicated task in the field of computer vision due to its high complex challenges. With the emergence of deep learning and large scale datasets from internet sources, substantial improvements have been made in video understanding. For instance, state-of-the-art 3D convolutional networks like I3D pre-trained on huge datasets like Kinetics have successfully boosted the recognition of actions from internet videos. But, these networks with rigid kernels applied across the whole space-time volume cannot address the challenges exhibited by Activities of Daily Living (ADL). We are particularly interested in discriminative video representation for ADL. Besides the challenges in generic videos, ADL exhibits - (i) fine-grained actions with short and subtle motion like pouring grain and pouring water, (ii) actions with similar visual patterns differing in motion patterns like rubbing hands and clapping, and finally (iii) long complex actions like cooking. In order to address these challenges, we have made three key contributions. The first contribution includes - a multi-modal fusion strategy to take the benefits of multiple modalities into account for classifying actions. However the question remains, how to combine multiple modalities in an end-to-end manner? How can we make use of the 3D information to guide the current state-of-the-art RGB networks for action classification? To this end, we propose articulated pose driven attention mechanisms for action classification. We propose, three variants of spatio-temporal attention mechanisms exploiting RGB and 3D pose modalities to address the aforementioned challenges (i) and (ii) for short actions. Our third main contribution is a Temporal Model on top of our attention based model. The video representation retaining dense temporal information enables the temporal model to model long complex actions which is crucial for ADL.We have evaluated our first contribution on three small-scale public datasets: CAD-60, CAD-120 and MSRDailyActivity3D. On the other hand, we have evaluated our remaining two contributions on four public datasets: a large scale human activity dataset: NTU-RGB+D 120, its subset NTU-RGB+D 60, a real-world challenging human activity dataset: Toyota Smarthome and a small scale human-object interaction dataset Northwestern UCLA. Our experiments show that the methods proposed in this thesis outperform the state-of-the-art results
Brassard, Louis. "Reconnaissance visuelle pour un robot-cueilleur de tomates." Thèse, Chicoutimi : Université du Québec à Chicoutimi, 1990. http://theses.uqac.ca.
Full textHiyadi, Hajar. "Reconnaissance 3D de gestes pour l'interaction homme-système." Thesis, Université Paris-Saclay (ComUE), 2016. http://www.theses.fr/2016SACLE052/document.
Full textThe goal of Human System Interaction(HSI) research is to increase the performance of human system interaction in order to make it similarto human-human interaction. As for communication between humans, gestural communication is also widely used in human system interaction. This thesis is about gesture recognition for natural human system interaction based on gestures. The objectif of works conducted in this thesis is to propose recognition approches for different kind of dynamic gesture: simple gesture and composed gesture. First of all, we proposed a novel 3D gesture descriptor computed by human body joints angles provided by Kinect sensor. Second, we proposed two dynamic gestures recognition approaches: a) simple gestures recognition approach, b) composed gestures recognition approach. The first approach is based on Hidden Markov Models (HMM). One HMM was created for each gesture. The joints angles variations have been used as input for HMMs. Then,this method has been combined with the Dynamic Time Warping algorithm in order to eliminate bad classification. The second approach treats the case of composed and successive gestures in the same sequence. This approach combines Dynamic Time Warping method with an adaptative window, hence the name: Adaptive Dynamic Time Warping. Two versions have been proposed: Forward and Backward version for online and offline recognition
Klaser, Alexander. "Apprentissage pour la reconnaissance d'actions humaines en vidéo." Phd thesis, Grenoble, 2010. http://tel.archives-ouvertes.fr/tel-00514814.
Full textCette thèse s'intéresse à la reconnaissance des actions humaines dans des données vidéo réalistes, tels que les films. À cette fin, nous développons des algorithmes d'extraction de caractéristiques visuelles pour la classification et la localisation d'actions.
Dans une première partie, nous étudions des approches basées sur les sacs-de-mots pour la classification d'action. Dans le cas de vidéo réalistes, certains travaux récents qui utilisent le modèle sac-de-mots pour la représentation d'actions ont montré des résultats prometteurs. Par conséquent, nous effectuons une comparaison approfondie des méthodes existantes pour la détection et la description des caractéristiques locales. Ensuite, nous proposons deux nouvelles approches pour la descriptions des caractéristiques locales en vidéo. La première méthode étend le concept d'histogrammes sur les orientations de gradient dans le domaine spatio-temporel. La seconde méthode est basée sur des trajectoires de points d'intérêt détectés spatialement. Les deux descripteurs sont évalués avec une représentation par sac-de-mots et montrent une amélioration par rapport à l'état de l'art pour la classification d'actions.
Dans une seconde partie, nous examinons comment la détection de personnes peut contribuer à la reconnaissance d'actions. Tout d'abord, nous développons une approche qui combine la détection de personnes avec une représentation sac-de-mots. La performance est évaluée pour la classification d'actions à plusieurs niveaux d'échelle spatiale. Ensuite, nous explorons la localisation spatio-temporelle des actions humaines dans les films. Nous étendons une approche de suivi de personnes pour des vidéos réalistes. En outre, nous développons une représentation d'actions qui est adaptée aux détections de personnes. Nos expériences suggèrent que la détection de personnes améliore significativement la localisation d'actions. De plus, notre système montre une grande amélioration par rapport à l'état de l'art actuel.
Klaser, Alexander. "Apprentissage pour la reconnaissance d'actions humaines en vidéo." Phd thesis, Grenoble, 2010. http://www.theses.fr/2010GRENM039.
Full textThis dissertation targets the recognition of human actions in realistic video data, such as movies. To this end, we develop state-of-the-art feature extraction algorithms that robustly encode video information for both, action classification and action localization. In a first part, we study bag-of-features approaches for action classification. Recent approaches that use bag-of-features as representation have shown excellent results in the case of realistic video data. We, therefore, conduct an extensive comparison of existing methods for local feature detection and description. We, then, propose two new approaches to describe local features in videos. The first method extends the concept of histograms over gradient orientations to the spatio-temporal domain. The second method describes trajectories of local interest points detected spatially. Both descriptors are evaluated in a bag-of-features setup and show an improvement over the state-of-the-art for action classification. In a second part, we investigate how human detection can help action recognition. Firstly, we develop an approach that combines human detection with a bag-of-features model. The performance is evaluated for action classification with varying resolutions of spatial layout information. Next, we explore the spatio-temporal localization of human actions in Hollywood movies. We extend a human tracking approach to work robustly on realistic video data. Furthermore we develop an action representation that is adapted to human tracks. Our experiments suggest that action localization benefits significantly from human detection. In addition, our system shows a large improvement over current state-of-the-art approaches
Vables, Jean. "Les titres de combattants et la reconnaissance de la nation." Montpellier 1, 1995. http://www.theses.fr/1995MON10007.
Full textCreated by the french state after the first world war, then during the successive fightsfrance had to pass through, the titles of fighters are, nowadays, alloted as well within humanitarian aid or peace keeping missions. Trough the years, the grant of these titles given by the state has gone through a lot fo changes which appear in the different assumptions that that define them. This heterogeneity entails, in the juridic point of view, difficult statement and reconciliation between the national homage due to the fighters, and the respect of the equality of the generations of the fight. However, the study of the titles of fighters shows that the crystallisation among these patents of patriotism represents a powerful symbol from which was born what should be called the world of the fighters. This several millions citizens community is setting much value upon the office national des anciens combattants et victimes de guerre which spreading out is due to its status of national institution, and that is represented on the hole territory of the republic
Ritchie, David. "Algorithmes Haute-Performance pour la Reconnaissance de Formes Moléculaires." Habilitation à diriger des recherches, Université Henri Poincaré - Nancy I, 2011. http://tel.archives-ouvertes.fr/tel-00587962.
Full textPortet, François. "Pilotage d'algorithmes pour la reconnaissance en ligne d'arythmies cardiaques." Phd thesis, Université Rennes 1, 2005. http://tel.archives-ouvertes.fr/tel-00011942.
Full textErdogmus, Nesli. "Utilisation des données 3D pour la reconnaissance du visage." Phd thesis, Télécom ParisTech, 2012. http://pastel.archives-ouvertes.fr/pastel-00982374.
Full textPoinsot, Audrey. "Traitements pour la reconnaissance biométrique multimodale : algorithmes et architectures." Thesis, Dijon, 2011. http://www.theses.fr/2011DIJOS010.
Full textIncluding multiple sources of information in personal identity recognition reduces the limitations of each used characteristic and gives the opportunity to greatly improve performance. This thesis presents the design work done in order to build an efficient generalpublic recognition system, which can be implemented on a low-cost hardware platform. The chosen solution explores the possibilities offered by multimodality and in particular by the fusion of face and palmprint. The algorithmic chain consists in a processing based on Gabor filters and score fusion. A real database of 130 subjects has been designed and built for the study. High performance has been obtained and confirmed on a virtual database, which consists of two common public biometric databases (AR and PolyU). Thanks to a comprehensive study on the architecture of the DSP components and some implementations carried out on a DSP belonging to the TMS320c64x family, it has been proved that it is possible to implement the system on a single DSP with short processing times. Moreover, an algorithms and architectures development work for FPGA implementation has demonstrated that these times can be significantly reduced
Besacier, Laurent. "Un modèle parallèle pour la reconnaissance automatique du locuteur." Avignon, 1998. http://www.theses.fr/1998AVIG0119.
Full textALANE, ABDELNASSER. "Graphes d'aspects pour la reconnaissance d'objets polyedriques : approche compilee." Paris 6, 1992. http://www.theses.fr/1992PA066384.
Full textAvila, Manuel. "Optimisation de modèles markoviens pour la reconnaissance de l'écrit." Rouen, 1996. http://www.theses.fr/1996ROUES034.
Full textEUDE, VIRGINIE. "Modelisation spatio-temporelle floue pour la reconnaissance d'activites militaires." Paris 6, 1998. http://www.theses.fr/1998PA066120.
Full textAberbour, Mourad. "Architecture d'un systeme heterogene pour la reconnaissance de formes." Paris 6, 1999. http://www.theses.fr/1999PA066005.
Full textBEASSE, CHRISTOPHE. "Approche perceptuelle pour la reconnaissance de formes sur images." Rennes 1, 1993. http://www.theses.fr/1993REN10123.
Full textAndriès, Julien. "De nouveaux acétylures métalliques pour la reconnaissance moléculaire : Chimie." Rennes 1, 2004. http://www.theses.fr/2004REN10145.
Full textPortet, François. "Pilotages d'algorithmes pour la reconnaissance en ligne d'arythmies cardiaques." Rennes 1, 2005. https://tel.archives-ouvertes.fr/tel-00011942v2.
Full textHérault, Romain. "Vision et apprentissage statistique pour la reconnaissance d'items comportementaux." Compiègne, 2007. http://www.theses.fr/2007COMP1715.
Full textThis work consists in the detection of behavioral items in order to prevent driver drowsiness. Videos were shot from within a car, and each picture of the video was characterized by six behavioral items. Our work consists in the retrieval of these items, picture by picture. The study was decomposed into two phases: 1) A Head and facial action tracking. A framework to 3D head pose and facial action tracking with an adaptive appearance model based on a mixture model is proposed to deal with face occlusion ; 2) A recognition of the behavioral items based on data retrieved from the tracking. We propose a new criterion leading to an adaptation of maximum likelihood estimation. The model outputs proper conditional probabilities into a user-defined interval. This criterion is applied to MLPs and IOHMMs for the recognition of the behavioral items
Verdot, Alexandra. "Le réseau de professions libérales : plaidoyer pour une reconnaissance." Aix-Marseille 3, 2009. http://www.theses.fr/2009AIX32041.
Full textFor several years now, the networking has significantly expended. The liberal professions are highly concerned by this phenomenon. Due to the complexification of the clients requests and the specialization of the professional areas, the network appeared to be an efficient way to meet both the practitioners economical and professional expectations and the ones of their clients. The network allows to reach the objective of multidisciplinarity by allowing the practitioners to practice their activity as part of a group and by offering to the clients a global approach of their needs. Nevertheless, the network of professions raises the issue of the ethics regarding the profession, especially when it takes the form of an interprofessional network. Hence, the legislator had to define a legal frame for the network. But instead of creating a thorough legal status, the legislator had only dealt with some aspects of the subject. However, this state of the law doesn’t imply the impossibility for the network to have a legal existence per se. Considering it is increasingly used by the liberal profession and the fact that it has allowed a modernization of the professions, the network of professions has to be analyzed like an independent structure from the people who compose it. Qualifying the network of professions as a member and as an actor of the liberal profession enhances the economical and professional extra value that it generates
BAILLET-JACQUOT, STEPHANIE. "Synthese d'oligonucleotides modifies pour la reconnaissance de sequences d'adn." Université Louis Pasteur (Strasbourg) (1971-2008), 1994. http://www.theses.fr/1994STR13062.
Full text