Дисертації з теми "Filtrage (mathématiques)"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-50 дисертацій для дослідження на тему "Filtrage (mathématiques)".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Переглядайте дисертації для різних дисциплін та оформлюйте правильно вашу бібліографію.
Rabut, Christophe. "B-splines polyharmoniques cardinales : interpolation, quasi-interpolation, filtrage." Toulouse 3, 1990. http://www.theses.fr/1990TOU30046.
Повний текст джерелаOliveira, Paula Manuela L. P. Milheiro de. "Etudes asymptotiques en filtrage non linéaire avec petit bruit d'observation." Aix-Marseille 1, 1990. http://www.theses.fr/1990AIX11313.
Повний текст джерелаCérou, Frédéric. "Filtrage non linéaire sans bruit de dynamique : comportement en temps long et algorithmes numériques." Aix-Marseille 1, 1995. http://www.theses.fr/1995AIX11076.
Повний текст джерелаKlaine, Luc. "Filtrage et restauration myopes des images numériques." Rennes 1, 2004. http://www.theses.fr/2004REN10161.
Повний текст джерелаGégout-Petit, Anne. "Filtrage d'un processus partiellement observé et équations différentielles stochastiques rétrogrades réfléchies." Aix-Marseille 1, 1995. http://www.theses.fr/1995AIX11006.
Повний текст джерелаRahmani, Pejman. "Restauration avec filtrage explicite des images multicomposantes." Rennes 1, 2008. http://www.theses.fr/2008REN1S182.
Повний текст джерелаThe main purpose of this thesis is to implement an automatic image processing scheme for restoring the degraded multispectral aerial images. In this work, the considered degradations are defocusing blur and additive, white and gaussian noise. Image processing is adapted to each spectral band by decomposing the image restoration process into two optimized sequential steps: Denoising and Deconvolution. In the first step, an iterative filter which is controlled by an optimal iteration number estimation, achieves the best compromise between the value of the usual criteria and PSF preservation. In the second step, a regularized deconvolution is performed on the almost noiseless version of observed image which is obtained from first step. A regularization parameter estimation method is introduced in order to make the scheme fully automatic. Finally, the performance of the proposed scheme is illustrated on degraded synthetic images and also on real aerial images acquired by the multi-hyper spectral CASI and AISA sensors
Rossi, Vivien. "Filtrage non linéaire par noyaux de convolution : application à un procédé de dépollution biologique." Montpellier, ENSA, 2004. http://www.theses.fr/2004ENSA0013.
Повний текст джерелаDaumail, Laurent. "Étude de quelques problèmes de stabilisation stochastique et de filtrage non linéaire." Metz, 2002. http://docnum.univ-lorraine.fr/public/UPV-M/Theses/2002/Daumail.Laurent.SMZ0224.pdf.
Повний текст джерелаDietsch, Marie-Noëlle. "Sur quelques problèmes de filtrage non linéaire." Metz, 2000. http://docnum.univ-lorraine.fr/public/UPV-M/Theses/2000/Dietsch.Marie_Noelle.SMZ0035.pdf.
Повний текст джерелаSekko, Edgar. "Quelques applications du filtrage optimal à la déconvolution." Lyon 1, 1998. http://www.theses.fr/1998LYO10028.
Повний текст джерелаLenoir, Philippe. "Développement de méthodes et d'outils dédiés à la conception des dispositifs de filtrage microonde complexes." Limoges, 2005. https://aurore.unilim.fr/theses/nxfile/default/15b5565c-b4e4-4129-a043-ee952ad9b708/blobholder:0/2005LIMO0047.pdf.
Повний текст джерелаThe work presented in this manuscript concerns the development of methods and tools dedicated to the design of complex microwave filtering devices. The design of telecommunication satellite multiplexing systems requires a rigorous and fast modeling of each of its components. In this framework, a dynamic inverter model is developed, which makes possible to replace the global electromagnetic modeling of each channel, by associating the circuit model of the filter with a simplified electromagnetic model. In a second time, a methodology is developped for the design of filters realising symetrical and assymmetrical transfer functions with two pass bands. This method is associated to an approximate synthesis technique, which allows to simplify the filter realization. These works done in collaboration with the company Alcatel Space has been validated by the realization of experimental models
Said, Salem. "Estimation et filtrage des processus dans les groupes de Lie matriciels." Grenoble INPG, 2009. http://www.theses.fr/2009INPG0102.
Повний текст джерелаSignals subject to nonlinear constraints are numerous in Physics and Engineering applications. Recent work have pointed the necessity of intrinsic geometrical methods to process such signals. The work presented in this thesis aims at providing new algorithm within this framework. Some problems in wave Physics and motion capture have been formalised and resolved. Signals subject to nonlinear constraints are modelled like processes taking values in matrix Lie groups. The problems considered in this work are filtering and nonparametric estimation problems. In order to propose new solutions, we have proposed new methods based on probability theory and processes dynamics, mainly based on the important property of stability
Loiseau, Yannick. "Recherche flexible d'information par filtrage flou qualitatif." Toulouse 3, 2004. http://www.theses.fr/2004TOU30263.
Повний текст джерелаWith the raise of electronic data, efficient information retrieval systems become necessary. To represent these information and the user needs, a better agreement between human and computer is needed. Our approach uses the fuzzy pattern matching to define a linguistic data representation, based on linked vague terms classes to model relations and ambiguity in language, defining a possibilistic concepts ontology. By representing user needs likewise, we match them with the information, and exploit links to evaluate vague searches with more relevant results. Lastly, all needs are kept in the final evaluation to discriminate documents using methods from multicriteria techniques. We first present several database and information retrieval aspects, and their integration with fuzzy techniques. The theoretic model of this approach is exposed, and applied to these two fields. Lastly, we illustrate the system and evaluate its real performances and advantages
Favetto, Benjamin. "Observations bruitées d'une diffusion : estimation, filtrage, applications." Phd thesis, Université René Descartes - Paris V, 2010. http://tel.archives-ouvertes.fr/tel-00524565.
Повний текст джерелаEl, Kolei Salima. "Estimation des modèles à volatilité stochastique par filtrage et déconvolution." Nice, 2012. http://www.theses.fr/2012NICE4095.
Повний текст джерелаThis thesis deals with the estimation of the state and/or the parameters of state-space models. The motivations come from financial applications, namely, from the estimation of the stochastic volatility and the parameters of its dynamics. Here, we consider two models : the Taylor SV model and the Heston model. After presenting the filtering methods, we propose a new approach of M-estimation based on a déconvolution strategy for linear state space models. We show that this method leads to a consistent and asymptotically normal estimator with an explicit variance, allowing constructing asymptotic confidence interval in practice. For the SV model, a thorough comparison with filtering methods and other classical methods is given on simulated and real data. This study shows the performance of our new approach. The Heston model is an example of complex state space models and, due to the nonlinearity, we cannot apply our approach. Nevertheless, filtering methods can be used for this model and we show how the filters update the estimation of the volatility and the parameters thanks to the observation of option prices. This illustrates the flexibility of these methods. Finally, we analyze the model risk induces by an error in the estimation of the parameters. Our objective consists in understanding the behavior of the filtering methods when the model is not well parameterized. A theoretical analysis consists in isolating the model risk due to the uncertainty of the parameters from the error of estimation for linear (and weakly nonlinear) models. An application of this result is given for the Heston model
Busvelle, Eric. "Immersion des systèmes stochastiques et filtres finis; filtrage particulaire." Rouen, 1991. http://www.theses.fr/1991ROUES043.
Повний текст джерелаRius, Éric. "Modélisation de la technologie uniplanaire par la méthode des différences finies : application au couplage et au filtrage." Brest, 1994. http://www.theses.fr/1994BRES2021.
Повний текст джерелаQuertier-Dagorn, Benjamin. "Systéme de filtrage numérique pour le corrélateur de l'interféromètre ALMA." Bordeaux 1, 2004. http://www.theses.fr/2004BOR12814.
Повний текст джерелаThe ALMA project is a large interferometric array for radio astronomy at millimeter and sub-millimeter wavelengths. The 64-antenna array which will operate in the Atacama desert (Chile) at an elevation of 5000m will make ALMA a unique instrument in terms of sensitivity and image precision. An innovative architecture has been selected for the correlator that performs the detection of radio astronomic signals. The digital filtering sub-system is at the heart of the correlator versatility and performances because it offers high spectral resolutions for different observing modes. During the thesis work, two digital filtering prototypes have been built and tested, then several architectures have been studied and compared. The selected architecture implements a “local oscillator – mixer” device and is based on an optimized 2-stage design of the filtering function. This architecture has been adopted for the ALMA correlator
Guilmart, Christophe. "Filtrage de segments informatifs dans des vidéos." Phd thesis, École normale supérieure de Cachan - ENS Cachan, 2011. http://tel.archives-ouvertes.fr/tel-00668307.
Повний текст джерелаNjonkou, Fankam Marc-Aurèle. "Analyse du mouvement dans les séquences d'images et filtrage linéaire récursif." Rouen, 1997. http://www.theses.fr/1997ROUES046.
Повний текст джерелаAmbellouis, Sébastien. "Analyse du mouvement dans les séquences d'images par une méthode récursive de filtrage spatio-temporel sélectif." Lille 1, 2000. https://pepite-depot.univ-lille.fr/LIBRE/Th_Num/2000/50376-2000-77-78.pdf.
Повний текст джерелаSchiltz, René Jean. "Sur quelques problèmes concernant le calcul de Malliavin et son application à la théorie du filtrage non linéaire." Metz, 1997. http://docnum.univ-lorraine.fr/public/UPV-M/Theses/1997/Schiltz.Jean.SMZ9726.pdf.
Повний текст джерелаThe aim of this work is to some problems of Malliavin calculus and its application to nonlinear filtering theory. It is divided in five chapters and one appendix. In chapter I we present some generalities on the Malliavin calculus and the theory of nonlinear filtering. We give the main ideas of these two theories and we recall the classical results that we need in the following chapters. The aim of chapters II, III and V is to study diffusions with time dependent coefficients under different conditions. In chapter II we suppose that on a sub-manifold of codimension 1 we have an exponential degenerencence condition, weaker than the general Hörmander condition. In chapter III we study diffusions generated by an infinity of Brownian motions and in chapter V we consider diffusions on riemannian manifolds. In the latter chapters, we establish a Malliavin calculus permitting to prove the existence of a smooth density for these diffusions. Furthermore, the results of Malliavin calculus are used to show that the unnormalized filter associated with a nonlinear filtering system, which admits the diffusion studied in the previous chapter as signal process, has a smooth density. In chapter IV we consider a nonlinear filtering system with an observation process depending on a white noise of order E. We define a suboptimal filter of finite dimension and we show that the error commited by replacing the filter by the suboptimal filter is of order E. In the appendix we derive the filtering equations associated with a nonlinear filering system with an infinite dimensional signal process and we give a robust form of the Zakai equation in the case of non correlated noises
Neveux, Philippe. "Restauration de signaux pour systèmes incertains." Lyon 1, 2000. http://www.theses.fr/2000LYO10012.
Повний текст джерелаAlbert, Luc. "Quelques analyses de complexité en moyenne sur les algorithmes de multi-filtrage, d'unification et de requête multiple." Paris 11, 1990. http://www.theses.fr/1990PA112226.
Повний текст джерелаGagnon, Ludovick. "Méthode de Legendre-Galerkin appliquée au contrôle de l'équation des ondes. Filtrage des hautes fréquences." Thesis, Université Laval, 2012. http://www.theses.ulaval.ca/2012/29513/29513.pdf.
Повний текст джерелаFlorchinger, Patrick. "Filtrage non linéaire avec bruits corrélés et observation non bornée : étude numérique d'une équation de Zakaï." Metz, 1989. http://www.theses.fr/1989METZ001S.
Повний текст джерелаWang, Xiao-Min. "Contribution à l'étude de la commande et du filtrage optimaux des systèmes implicites singuliers." Nice, 1988. http://www.theses.fr/1988NICE4235.
Повний текст джерелаBorges, Geovany Araujo. "Cartographie de l'environnement et localisation robuste pour la navigation de robots mobiles." Montpellier 2, 2002. http://www.theses.fr/2002MON20034.
Повний текст джерелаOuzina, Mostafa. "Théorème du support en théorie du filtrage non-linéaire." Rouen, 1998. http://www.theses.fr/1998ROUES029.
Повний текст джерелаBarkaoui, Ahmed. "La désagrégation temporelle des séries d'observations économiques." Paris 10, 1995. http://www.theses.fr/1995PA100055.
Повний текст джерелаThis thesis treats the problem encountered in econometric modeling when temporal observations on certain variables are available only in a temporally aggregated fora. The practical solution consists of estimating disaggregated series which are consistent with the observed data (temporal disaggregation procedures). This estimation can be done only by aggregated series or by using some related series -if available- observed in the suit time periods. The analysis of the principal procedures used in statistic organisms or in econometric software’s, has allowed to propose -for a given problem- a criterion of selection based on a priori known on time series and on statistical tests. The problem of temporal disaggregation was extended to the case of a vector of variables when the sum of the latters is observed in disaggregated data. Two applications were performed: the first was performed on the construction of the quarterly series of productive investment (fbcf) by activity branch. The second on the estimation of monthly merchant gdp. If we assume that the disaggregated series can be generated by whatever completely specified dynamic model, new methods can resolve the problem using the states space representation and the kalean filter and smoothing technics
Sellami, Afef. "Méthodes de quantification optimale pour le filtrage et applications à la finance." Phd thesis, Université Paris Dauphine - Paris IX, 2005. http://tel.archives-ouvertes.fr/tel-00011586.
Повний текст джерелаNeycenssac, Franck. "Segmentation d'images : intérêt d'un filtrage multi-échelle calculé par intégration du Laplacien d'une Gaussienne sur son écart-type." Toulouse 3, 1991. http://www.theses.fr/1991TOU30203.
Повний текст джерелаBui, Quang Paul. "Approximation particulaire et méthode de Laplace pour le filtrage bayésien." Phd thesis, Université Rennes 1, 2013. http://tel.archives-ouvertes.fr/tel-00910173.
Повний текст джерелаKaafar, Mohamed Ali. "Securiting Internet coordinates systems." Nice, 2007. http://www.theses.fr/2007NICE4023.
Повний текст джерелаIdea is that if network distances between Internet nodes can be embedded in an appropriate space, unmeasured distances can be estimated using a simple distance computation in that space. Recently, these coordinates-based systems have been shown to be accurate, with very low distance prediction error. However, most, if not all, of current proposals for coordinate systems assume that the nodes partaking in the system cooperate fully and honestly with each other – that is that the information reported by probed nodes is correct – this could also make them quite vulnerable to malicious attacks. In particular, insider attacks executed by potentially colluding) legitimate users or nodes infiltrating the system could prove very effective. As the use of overlays and applications relying on coordinates increases, one could imagine the release of worms and other malware, exploiting such cooperation, which could seriously disrupt the operations of these systems and therefore the virtual networks and applications relying on them for distance measurements. In this thesis, we first identify such attacks, and through a simulation study, we observed their impact on two recently proposed positioning systems, namely Vivaldi and NPS. We experimented with attack strategies, carried out by malicious nodes that provide biased coordinates information and delay measurement probes, and that aim to (i) introduce disorder in the system, (ii) fool honest nodes to move far away from their correct positions and (iii) isolate particular target nodes in the system through collusion. Our findings confirm the susceptibility of the coordinate systems to such attacks. Our major contribution is therefore a model for malicious behavior detection during coordinates embedding. We first show that the dynamics of a node, in a coordinate system without abnormal or malicious behavior, can be modeled by a Linear State Space model and tracked by a Kalman filter. Then we show, that the obtained model can be generalized in the sense that the parameters of a filter calibrated at a node can be used effectively to model and predict the dynamic behavior at another node, as long as the two nodes are not too far apart in the network. This leads to the proposal of a Surveyor infrastructure: Surveyor nodes are trusted, honest nodes that use each other exclusively to position themselves in the coordinate space, and are therefore immune to malicious behavior in the system. During their own coordinate embedding, other nodes can then use the filter parameters of a nearby Surveyor as a representation of normal, clean system behavior to detect and filter out abnormal or malicious activity. A combination of simulations and PlanetLab experiments are used to demonstrate the validity, generality, and effectiveness of the proposed approach for both Vivaldi and NPS. Finally, we address the issue of asserting the accuracy of Internet coordinates advertised by nodes of Internet coordinate systems during distance estimations. Indeed, some nodes may even lie deliberately about their coordinates to mount various attacks against applications and overlays. Our proposed method consists in two steps: 1) establish the correctness of a node’s claimed coordinate by using the Surveyor infrastructure and malicious embedding neighbor detection; and 2) issue a time limited validity certificate for each verified coordinate. Validity periods are computed based on an analysis of coordinate inter-shift times observed by Surveyors. By doing this, each surveyor can estimate the time until the next shift and thus, can limit the validity of the certificate it issues to regular nodes for their calculated coordinates. Our method is illustrated using a trace collected from a Vivaldi system deployed on PlanetLab, where intershift times are shown to follow long-tail distribution (log-normal distribution in most cases, or Weibull distribution otherwise). We show the effectiveness of our method by measuring the impact of a variety of attacks, experimented on PlanetLab, on distance estimates
Souilah, Noureddine. "Contribution au problème de déconvolution." Ecully, Ecole centrale de Lyon, 1993. http://www.theses.fr/1993ECDL0021.
Повний текст джерелаMarangé, Pascale. "Synthèse et filtrage robuste de la commande pour des systèmes manufacturiers sûrs de fonctionnement." Reims, 2008. http://theses.univ-reims.fr/exl-doc/GED00000826.pdf.
Повний текст джерелаThe work presented in this thesis, focuses on the control design by automatic control engineers who can have different levels of competence. The use of real plant can involve control design errors. This raises two original problems; the validation and verification of the control and the requirement to take into the designer. These problems require an approach taking into account the human part. The contributions developed in this thesis focuse on adapting the system to designer knowledge and on the system safety. On the first point, it highlights the educational importance to work on the global system rather than a part. An approach is based on the functional decomposition of the plant to adapt the specifications. This approach helps maintain the global vision of system. On the second point 2 approaches are envisaged to ensure the safety. The first, offline, is based on previous work performed. Supervisory control allows to obtain a sure, robust and without deadlock controller. The second approach, online, uses a filter. This approach allows sending to the plant only validated outputs. The main difficulties of filter lie firstly in its specifications, and secondly in its explanatory capabilities for the designer. A filter structure with 2 levels is proposed. The first one: system validation filter, assuring the plant safety. The second one: functional validation filter enables to verify if specifications are conformed. The proposed approach to ensure that the constraints are properly defined is to formally verify, using the model-checker. The verification procedure determines the sufficient constraints set to avoid deterioration situations. Two applications are presented
Dugas, Olivier. "Localisation relative à six degrés de liberté basée sur les angles et sur le filtrage probabiliste." Master's thesis, Université Laval, 2014. http://hdl.handle.net/20.500.11794/25607.
Повний текст джерелаWhen a team of robots have to collaborate, it is useful to allow them to localize each other in order to maintain flight formations, for example. The solution of cooperative localization is of particular importance to teams of aerial or underwater robots operating in areas devoid of landmarks. The problem becomes harder if the localization system must be low-cost and lightweight enough that only consumer-grade cameras can be used. This paper presents an analytical solution to the six degrees of freedom cooperative localization problem using bearing only measurements. Probabilistic filters are integrated to this solution to increase it's accuracy. Given two mutually observing robots, each one equipped with a camera and two markers, and given that they each take a picture at the same moment, we can recover the coordinate transformation that expresses the pose of one robot in the frame of reference of the other. The novelty of our approach is the use of two pairs of bearing measurements for the pose estimation instead of using both bearing and range measurements. The accuracy of the results is verified in extensive simulations and in experiments with real hardware. In experiments at distances between 3:0 m and 15:0 m, we show that the relative position is estimated with less than 0:5 % error and that the mean orientation error is kept below 2:2 deg. An approximate generalization is formulated and simulated for the case where each robot's camera is not colinear with the same robot's markers. Passed the precision limit of the cameras, we show that an unscented Kalman filter can soften the error on the relative position estimations, and that an quaternion-based extended Kalman filter can do the same to the error on the relative orientation estimations. This makes our solution particularly well suited for deployment on fleets of inexpensive robots moving in 6 DoF such as blimps.
Ben, Amor Selwa. "Observation et commande de systèmes non linéaires temps-discret." Lyon 1, 1997. http://www.theses.fr/1997LYO10124.
Повний текст джерелаCalmettes, Vincent. "Étude d'adoucissement de spectre pour récepteur GPS." École nationale supérieure de l'aéronautique et de l'espace (Toulouse ; 1972-2007), 2001. http://www.theses.fr/2001ESAE0016.
Повний текст джерелаSeaux, Jean-François. "Conception, optimisation et test de dispositifs intégrant des matériaux en couche mince supraconducteurs ou ferroélectriques pour des applications de filtrage dans le domaine spatial." Limoges, 2005. http://aurore.unilim.fr/theses/nxfile/default/41920dfd-a8ee-4cd3-8ed9-7dcfa9d61606/blobholder:0/2005LIMO0048.pdf.
Повний текст джерелаThe research work presented in this memory relates to the realization of innovating microwave filtering devices from thin layer superconductors or ferroelectrics for space applications. The high-temperature superconductor planar technology makes it possible to obtain at the same time compact circuits and excellent electric performances. C-band eight-pole self-equalized quasi-elliptic filters for an input multiplexer (IMUX) have been designed. Moreover, a Ka-band preselect filter has been studied. We have also searched to tune the superconductive filters after their manufacture using ferroelectric materials. An electromagnetic method has been developed to characterize BST deposits on adapted substrates. The goal was to realize reconfigurable or tunable devices
Akkoul, Smaïl. "Filtrage et déconvolution en imagerie de bioluminescence chez le petit animal." Phd thesis, Université d'Orléans, 2010. http://tel.archives-ouvertes.fr/tel-00585392.
Повний текст джерелаGiremus, Audrey. "Apport des techniques de filtrage particulaire pour la navigation avec les systèmes de navigation inertiels et le GPS." Toulouse, ENSAE, 2005. http://www.theses.fr/2005ESAE0026.
Повний текст джерелаChen, Mingkun. "Classification de variables autour de variables latentes avec filtrage de l’information : application à des données en grande dimension." Nantes, 2014. http://archive.bu.univ-nantes.fr/pollux/show.action?id=dc97aa41-ffd6-432b-a740-06382adaca0a.
Повний текст джерелаWith the development of high-throughput analysis techniques, researchers have adopted systematic approaches to describe simultaneously a large number of variables. However, one of the important challenges lies in the diffculty to summarise and interpret this enormous quantity of information. We adopt a clustering of variables approach (CLV) which allows us to highlight disjunctive structures, and therefore, reduce the dimensionality of the problem and facilitate the interpretation of the data at hand. However, in order to further improve the relevance of such approaches, two directions of investigation are proposed. The first direction involves filtering the data by setting aside atypical variables or variables associated with noise. For this purpose, a strategy to create an additional group of variables, called noise cluster, and a strategy based on the definition of sparse latent variables are proposed and compared. The second direction concerns the development of a clustering of variables procedure directed to the explanation of a response variable. The implementation of iterative algorithms provides a sequence of group latent variables with good predictive performance. These latent variables are also easy to interpret since each predictive component is associated with a subset of variables assumed to have a one-dimensional structure
Chorot, Thierry. "Modélisation commande et observation des systèmes mécaniques hamiltoniens : application à un pont roulant." Lyon 1, 1991. http://www.theses.fr/1991LYO10200.
Повний текст джерелаSentenac, Thierry. "Surveillance de scènes dynamiques avec une caméra CCD dans le proche infrarouge : application à la détection couplée de feu et de déplacements d'objets." Toulouse, INPT, 2002. http://www.theses.fr/2002INPT042H.
Повний текст джерелаBourennane, El-Bay. "Conception et implantation d'un détecteur de contours optimisé sous forme d'un circuit Asic." Dijon, 1994. http://www.theses.fr/1994DIJOS012.
Повний текст джерелаZerubia, Josiane. "La représentation et le traitement de signaux bruités." Nice, 1988. http://www.theses.fr/1988NICE4207.
Повний текст джерелаChebira, Abdennasser. "Détection d'obstacles en temps réel par reconstruction de l'environnement 2d à partir de capteurs infrarouges id : modélisation capteur et scène, représentation d'imprécisions et incertitudes par des modèles probalistes et flous." Paris 11, 1994. http://www.theses.fr/1994PA112042.
Повний текст джерелаJridi, Maher. "Etude, modélisation et amélioration des performances des convertisseurs analogique numérique entrelacés dans le temps." Bordeaux 1, 2007. http://www.theses.fr/2007BOR13517.
Повний текст джерелаLétienne, Antoine. "Super-Résolution : Développement d'algorithmes rapides et évaluation de performance." Paris 13, 2010. http://www.theses.fr/2010PA132020.
Повний текст джерелаAbstract The super-resolution (SR) aims at improving the quality of an image by ex-ploiting variations between images of the same sequence. After registration, the most accurate algorithms consist in the construction of a large linear system and the inversion by iterative and costly techniques. In order to reduce the computational cost, a usual assumption is to consider only translation motion between images. We consider the original context of fast reconstruction of small moving objects in a scene, where motions are not restricted to translations. We extended to complex motion the Shift & Add method, one of the fastest but whose the theoretical justification is restricted to discrete translations of high-resolution pixel, and to the non-regularized case. First, our work provided a detailed characterization of the behaviour of this technique, and a generalization of its justification to non-discrete translations in a regularized context. We then evaluated the performance of our approach to identify its working domain and its limits, and to justify empirically its use for motions more complex than translation when we have enough images. We have developed a complete processing chain for the fast automatic reconstruction of a SR frame from a selected object in a video, and integrating the registration step that represents 80% of the execution time. We qualitatively illustrate our method on real data