Dissertations / Theses on the topic 'Estimation basée sur la vision'
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 'Estimation basée sur la vision.'
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.
Bellarbi, Abdelkader. "Vers l’immersion mobile en réalité augmentée : une approche basée sur le suivi robuste de cibles naturelles et sur l’interaction 3D." Thesis, Université Paris-Saclay (ComUE), 2017. http://www.theses.fr/2017SACLE005/document.
Full textPose estimation and 3D interaction are the essential basis for any Augmented Reality (AR) system. We aim to treat those two fields in order to offer a pertinent AR system that allows a mobile immersion and natural interaction. In this optic, this thesis provides an overall consistent state of the art in both pose estimation and 3D interaction for AR.In addition, this thesis details our contributions that consists of MOBIL: a binary descriptor that compares geometric moments of the patch through a binary test. Two improvements of this descriptor: MOBIL_2B and POLAR_MOBIL are proposed in order to enhance its robustness.We used this descriptor with PTAM technique to ensure the user pose estimation respectively for the selection/manipulation task and the navigation task.On the other hand, we proposed a novel 3D interaction technique called “Zoom-In”, designed for augmented reality applications. This technique is based on the zoom of the captured image. It calculates the 3D transformation relative to the selected object. This technique allows user selecting and manipulating distant virtual objects by bringing them within the user arm’s reach by zooming in the captured image, and re-estimating the user pose thanks to our proposed descriptor. Finally, we present a conclusion that describes the essential of this work and provide perspective and future work
Silveira, Filho Geraldo. "Contributions aux méthodes directes d'estimation et de commande basées sur la vision." Phd thesis, École Nationale Supérieure des Mines de Paris, 2008. http://pastel.archives-ouvertes.fr/pastel-00005340.
Full textLiu, Shiyu. "Decentralized Control and Estimation of a Flying Parallel Robot Interacting with the Environment." Electronic Thesis or Diss., Ecole centrale de Nantes, 2022. http://www.theses.fr/2022ECDN0056.
Full textAerial manipulation is an emerging domain where multirotor Unmanned Aerial Vehicles (UAVs) are equipped with onboard end-effectors for grasping, transporting and manipulating objects. To enhance the payload capacity and achieve full manipulability in 3-dimensional space, a flying parallel robot (FPR) was previously proposed in which a number of UAVs are used to collectively support a passive parallel architecture. In this thesis, the estimation and control methods dealing with the interaction with the environment are addressed, which are applied to a specific FPR composed of a moving platform and a number of rigid legs attached with quadrotors actuating the system. The second main contribution of this thesis is the proposal of decentralized strategies based on onboard and intrinsic measurements of the UAVs. Experiments show the effectiveness of the proposed methods in regulating the robot configuration, achieving precise positioning tasks through teleoperation and performing contact-based interactions with an object in the environment. In addition, a detailed analysis of the wrench feasibility of the FPR is presented, allowing to compute the Available Wrench Set (AWS) of the platform and determine the optimal leg configurations maximising the wrench feasibility of the robot accordingly to specific task requirements
Revolon, Fabrice. "Une vision de la petite entreprise basée sur les ressources." Nancy 2, 1998. http://www.theses.fr/1998NAN22004.
Full textGueye, Cheikh Ahmadou Bamba. "Localisation géographique des hôtes dans l'Internet basée sur la multilatération." Paris 6, 2006. http://www.theses.fr/2006PA066367.
Full textNoce, Aurélien. "Vision et Reconstruction 3D basée sur la Texture: Application à la Robotique Médicale." Phd thesis, Université Montpellier II - Sciences et Techniques du Languedoc, 2008. http://tel.archives-ouvertes.fr/tel-00339769.
Full textRandrianasolo, Toky. "Inférence basée sur le plan pour l'estimation de petits domaines." Thesis, Paris Est, 2013. http://www.theses.fr/2013PEST0099.
Full textThe strong demand for results at a detailed geographic level, particularly from national surveys, has raised the problem of the fragility of estimates for small areas. This thesis addresses this issue with specific methods based on the sample design. These ones consist of building new weights for each statistical unit. The first method consists of optimizing the re-weighting of a subsample survey included in an area. The second one is based on the construction of weights that depend on the statistical units as well as the areas. It consists of splitting the sampling weights of the overall estimator while satisfying two constraints : 1/ the sum of the estimates on every partition into areas is equal to the overall estimate ; 2/ the system of weights for a given area satisfies calibration properties on known auxiliary variables at the level of the area. The split estimator thus obtained behaves almost similarly as the well-known blup (best linear unbiased predictor) estimator. The third method proposes a rewriting of the blup estimator, although model-based, in the form of a homogenous linear estimator from a design-based approach. New modified blup estimators are obtained. Their precision, estimated by simulation with an application to real data, is quite close to that of the standard blup estimator. Then, the methods developed in this thesis are applied to the estimation of local mobility indicators from the 2007-2008 French National Travel Survey. When the size of an area is small in the sample, the estimates obtained with the first method are not precise enough whereas the precision remains satisfactory for the two other methods
Verney, Philippe. "Interprétation géologique de données sismiques par une méthode supervisée basée sur la vision cognitive." Phd thesis, École Nationale Supérieure des Mines de Paris, 2009. http://pastel.archives-ouvertes.fr/pastel-00005861.
Full textZhang, Yiqun. "Contribution à l'étude de la vision dynamique : une approche basée sur la géométrie projective." Compiègne, 1993. http://www.theses.fr/1993COMPD650.
Full textOuld, Aboubecrine Mohamed Mahmoud. "Sur l'estimation basée sur les records et la caractérisation des populations." Le Havre, 2011. http://www.theses.fr/2011LEHA0004.
Full textIn the first part of this work, we consider a number of k-record values from independent and identically distributed random variables with a continuous distribution function F, ou aim is to predict future k-record values under suitable assumptions on the tail of F. In the second part, we consider finite populations and investigate their characterization by regressions of order statistics under sampling without replacement. We also give some asymptotic results when the size of the population goes to infinity
Fakhri, Myriam. "PAX : une vision des processus métier basée sur la co-ingénierie de compositions de services." Thesis, Aix-Marseille, 2015. http://www.theses.fr/2015AIXM4379.
Full textThis research work deals with the services compositions at a business level: a business process is seen as a composition of services to achieve an objective, taking into account contextual information on the environment. Also, in this research, the idea of considering the compositions as a persistent artefact is developed for reuse and sharing purposes.The PAχ approach offers models of compositions in order to specify compositions at different levels of abstraction. At the intentional level, a composition of services is seen as a composition of business goals. At the orchestrated level, a composition of services is specified as a business process in which some activities and operations are abstract. At the executable level, a composition of services is a business process in which the activities are carried out by identified services. At the trace level, a composition of services is seen as the trace of the execution of a business process implemented by invocation of services. The PAχ approach provides a flexible approach based on co-engineering paradigm for defining business processes which satisfies a business need and based on the reuse of services and composition of services. The proposed approach is flexible because the realization of activities depends of the context in which the PAχ approach is deployed. The approach is based on co-engineering paradigm: it suggests involving business actors to design a process, i.e. a composition of services during execution. Co-engineering improves alignment between business needs and processes to satisfy these needs
Benzougar, Abdeljabar. "Perception de la profondeur en stéréovision monoculaire par exploitation du flou optique : approche basée sur les moments spatiaux." Poitiers, 1997. http://www.theses.fr/1997POIT2301.
Full textColliez, Johan. "Estimation robuste du mouvement dans les séquences d'images basée sur la régression par vecteurs supports." Littoral, 2009. http://www.theses.fr/2009DUNK0231.
Full textOne of the main tasks in computer vision is to extract the relevant information from an images sequence by using the regression and model adjustment theory. However, the presence of noise and ouliers has the effect of altering the task of estimating the structure of the underlying model. Hence, the need of using robust estimators against the errors inherent to natural scenes images. In this work, we propose a new robust estimator based on support vectors machines. This estimator is a weighted version of regression by support vectors. It assigns a heterogeneous penality to observations according that they belong to inliers or outliers classes. Hard and soft penalisations were considered and an iterative approach was applied to extract the dominant structure in the data set. The many simulated sets indicate that the proposed robust estimator by support vectors has a breakdown point above 50% imroving significantly the performance of the standard regression by support vector. Moreover, it permits to extract the dominant structure in the data set with a high resistance to residual structures. The robust regression approach was applied to estimate the movement in images sequence by optic flow as well as by images matching
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.
Full textWhen 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.
Dame, A. "Méthode unifiée de suivi et d'asservissement visuels basée sur l'information mutuelle." Phd thesis, Université Rennes 1, 2010. http://tel.archives-ouvertes.fr/tel-00558196.
Full textPoulin, Pierre. "Modèles physiques pour la résolution de problèmes en vision artificielle une approche basée sur la topologie algébrique calculatoire." Mémoire, Université de Sherbrooke, 2002. http://savoirs.usherbrooke.ca/handle/11143/4558.
Full textBouazza, Kheir-Eddine. "Commande basée sur des observateurs pour les systèmes non-linéaires en temps discret." Nancy 1, 2004. http://www.theses.fr/2004NAN10171.
Full textResearch activities presented in this thesis concerne the stabilisation, with obserber-based controllers, of discrete-time nonlinear systems. The approach which we proposed doesn't require a particular structure of the output contrary to the methods based on the the passivity theory. Unlike the jurdjevic-quinn method, it doesn't need the stability of the free dynamics. A lyapunov function common to a great number of systems is used for the analysis of stability. Moreover it has the advantage of being simply implementable. Using the results established previously, synthesis of a control law based on an extended kalman observer was given. The third section presents an observer based controller which stabilizes globally exponentially a class of nonlinear systems. An extension to delay systems was established. In the last section, we present a simple conditions in linear matrix inequalities form, which stbilizes asymptotically a large class of delay nonlinear systems. Some other conditions allowing the synthesis of observers for different classes of nonlinear systems were presented
Xu, Hao. "Estimation statistique d'atlas probabiliste avec les données multimodales et son application à la segmentation basée sur l'atlas." Phd thesis, Ecole Polytechnique X, 2014. http://pastel.archives-ouvertes.fr/pastel-00969176.
Full textBodo, Yann. "Élaboration d'une technique de tatouage vidéo basée sur la perturbation des vecteurs de mouvement." Phd thesis, Télécom ParisTech, 2004. http://pastel.archives-ouvertes.fr/pastel-00000917.
Full textSidibe, Ibrahima dit Bouran. "Analyse non-paramétrique des politiques de maintenance basée sur des données des durées de vie hétérogènes." Thesis, Université de Lorraine, 2014. http://www.theses.fr/2014LORR0081/document.
Full textIn the reliability literature, several researches works have been developed to deal with modeling, analysis and implementation of maintenance policies for equipments subject to random failures. The majority of these works are based on common assumptions among which the distribution function of the equipment lifetimes is assumed to be known. Furthermore, the equipment is assumed to experience only one operating environment. Such assumptions are indeed restrictive and may introduce a bias in the statistical analysis of the distribution function of the equipment lifetimes which in turn impacts optimization of maintenance policies. In the present research work, these two particular assumptions are relaxed. This relaxation allows to take into account of information related to conditions where the equipment is being operating and to focus on the statistical analysis of maintenance policies without using an intermediate parametric lifetimes distribution. The objective of this thesis consists then on the development of efficient statistical models and tools for managing the maintenance of equipments whose lifetimes distribution is unknown and defined through the heterogeneous lifetimes data. Indeed, this thesis proposes a framework for maintenance strategies determination, from lifetimes data acquisition toward the computation of optimal maintenance policies. The maintenance policies considered are assumed to be performed on used equipments. These later are conduct to experience their missions within different environments each of which is characterized by a degree of severity. In this context, a first mathematical model is proposed to evaluate costs induced by maintenance strategies. The analysis of these costs helps to establish the necessary and sufficient conditions to ensure the existence of an optimal age to perform the preventive maintenance. The maintenance costs are fully estimated by using the Kernel method. This estimation method is non-parametric and defined by two parameters, namely the kernel function and the smoothing parameter. The variability of maintenance costs estimator is deeply analyzed according to the smoothing parameter of Kernel method. From these analyses, it is shown that Kernel estimator method ensures a weak propagation of the errors due to the computation of smoothing parameter. In addition, several simulations are made to estimate the optimal replacement age. These simulations figure out that the numerical results from the Kernel method are close to the theoretical values with a weak coefficient of variation. Two probabilistic extensions of the first mathematical model are proposed and theoretically discussed. To deal with the problem of delayed preventive maintenance, an approach is proposed and discussed. The proposed approach allows evaluating the risk that could induce the delay taken to perform a preventive maintenance at the required optimal date. This approach is based on risk analysis conduct on the basis of a proposed risk function
El, Jabri Mohammed. "Etude de l'organisation spatiale du tissu conjonctif par analyse d'images basée sur une approche multiéchelles." Phd thesis, Clermont-Ferrand 2, 2008. http://www.theses.fr/2008CLF21831.
Full textTchekiken, El Hadi. "Estimation de l'orientation 3D du cœur : une approche basée sur l'analyse de la structure spatio-temporelle de l'électrocardiogramme orthogonal." Lyon, INSA, 1997. http://www.theses.fr/1997ISAL0008.
Full textThis work is about the estimation of the 3D orientation of the heart from the orthogonal electrocardiogram. The long term objective is to perform a spatio-temporal ECG-gated echocardiography technique for the acquisition of serial, but comparable images during a stress echocardiography test. We first propose a method for the determination of the position of the successive spatio-temporal QRS and T loops with reference to the body coordinates system. We determine the inertia axes which define a new coordinates system closely related to the loop's preferential space. We then study the spatial and the structural reproducibility of the ECG loops for body posture, respiration and stress. The obtained results have confirmed the beat-to-beat reproducibility and evidenced the correlation between the position of the heart and the spatial position of the ECG loops. Starting from the hypothesis that the QRS and T loops are tied to the heart, we have developed a method to estimate the orientation of any anatomic axis of the heart. For the evaluation, we proposed two approaches which allow the confrontation of the electric and the anatomic positions of the heart. The first approach is based on the spatial determination of echocardiographic planes of the four chambers and the second one on the 3D MRI of the thorax and the heart. The results show that there is a correlation between electric and anatomic positions of the heart. In this work, we also evidenced that our method is suitable for the estimation of the changes of the beat-to-beat orientation of the heart. Hence, we can consider the development of a spatio-temporal ECG-gated echocardiography technique
Du, Jun. "Estimation de l'épaisseur des coulées de lave sur la Lune et le Mercure basée sur la modélisation de la dégradation topographique de cratères d’impact." Thesis, Université Côte d'Azur (ComUE), 2019. http://www.theses.fr/2019AZUR4099.
Full textIn this study, partially buried craters on the lunar maria and the northern smooth plains of Mercury were identified using recently acquired optical, elevation, and composition data, and lava flow thicknesses near partially buried craters were estimated by numerically modeling their topographic degradation. In Chapter 1, I first introduce the geologic background of the volcanic plains on the Moon and Mercury. Next, I will summarize all the methods that have been used to estimate the lava flow thicknesses on the Moon and Mercury, as well as the research progress on the crater topographic degradation. In Chapter 2, I present the remote sensing datasets used in this study. Then, the criteria used to identify partially buried craters are discussed. A lava flow thickness estimation method is later proposed based on the topographic degradation of partially buried craters. The best fitting lava flow thickness was then determined by minimizing the difference between the modeled final profile and the observed profile. In Chapter 3, in order to solve the topographic diffusion equation, the elevation profile of a fresh impact crater is constructed as the initial condition. For lunar fresh impact craters, we constructed a set of topographic profiles that consider both crater sizes and target types. For fresh impact craters on Mercury, we constructed topographic profiles that only include transitional and complex craters. As described in Chapter 4, the basalt thicknesses were inverted using 41 mare craters whose rims are completely exposed. The result shows that the estimated mare basalt thicknesses vary from 33 to 455 m, with a median value of 105 m. We then calculated the total volume and eruption rate of lunar mare basalts, and found that the estimated eruption rate of mare basalts peaked at 3.4 Ga and then decreased with time, indicating a progressive cooling of the lunar interior. We also found that the topographic diffusivity of lunar craters increases with diameter and is almost invariant with time. In Chapter 5, I present a similar result for Mercury. The lava flow thicknesses were inverted for 17 craters whose rims were exposed and embayed for more than 50% of its circumference. The result shows that the lava flow thicknesses vary from 7 to 419 m, with a median value of 218 m. We then calculated the total volume and eruption rate of the lava flows. Comparing the topographic diffusivity on the Moon with that on Mercury, it can be found that both values are similar to each other. As shown in Chapter 6, there are some remaining issues that need to be solved in the future. First, I employed a simple axisymmetric geometry when analytically solving the topographic diffusion equation and did not consider a fully three-dimensional topographic degradation process. Second, the inverted topographic diffusivities have a large range of uncertainty and are not well constrained. Third, complex craters usually have complicated formation mechanism and a variable geologic background and crater morphology, resulting in considerable variability and uncertainty in the crater morphometric relations
Xu, Hao. "Probabilistic atlas statistical estimation with multimodal datasets and its application to atlas based segmentation." Palaiseau, Ecole polytechnique, 2014. http://pastel.archives-ouvertes.fr/docs/00/96/91/76/PDF/Thesis.pdf.
Full textComputerized anatomical atlases play an important role in medical image analysis. While an atlas usually refers to a standard or mean image also called template, that presumably represents well a given population, it is not enough to characterize the observed population in detail. A template image should be learned jointly with the geometric variability of the shapes represented in the observations. These two quantities will in the sequel form the atlas of the corresponding population. The geometric variability is modelled as deformations of the template image so that it fits the observations. In the first part of the work, we provide a detailed analysis of a new generative statistical model based on dense deformable templates that represents several tissue types observed in medical images. Our atlas contains both an estimation of probability maps of each tissue (called class) and the deformation metric. We use a stochastic algorithm for the estimation of the probabilistic atlas given a dataset. This atlas is then used for atlas-based segmentation method to segment the new images. Experiments are shown on brain T1 MRI datasets. Traditional analyses of Functional Magnetic Resonance Imaging use little anatomical information. The registration of the images to a template is based on the individual anatomy and ignores functional information; subsequently detected activations are not confined to gray matter. In the second part of the work, we propose a statistical model to estimate a probabilistic atlas from functional and T1 MRIs that summarizes both anatomical and functional information and the geometric variability of the population. Registration and Segmentation are performed jointly along the atlas estimation and the functional activity is constrained to the gray matter, increasing the accuracy of the atlas. Inferring protein abundances from peptide intensities is the key step in quantitative proteomics. The inference is necessarily more accurate when many peptides are taken into account for a given protein. Yet, the information brought by the peptides shared by different proteins is commonly discarded. In the third part of the work, we propose a statistical framework based on a hierarchical modeling to include that information. Our methodology, based on a simultaneous analysis of all the quantified peptides, handles the biological and technical errors as well as the peptide effect. In addition, we propose a practical implementation suitable for analyzing large datasets. Compared to a method based on the analysis of one protein at a time (that does not include shared peptides), our methodology proved to be far more reliable for estimating protein abundances and testing abundance changes
Genov, Antonio. "Estimation de la consommation basée sur les modèles de performance SystemC-TLM des systèmes d'interconnexion et de mémoire des SoC." Thesis, Université Côte d'Azur, 2021. http://www.theses.fr/2021COAZ4108.
Full textThe rapid pace of development in microelectronics enables the semiconductor industry to constantly surpass itself and to offer ever more innovative and complex products and technologies. The most modern areas of development, such as 5G, the Internet of Things (IoT) and automotive, rely on complex, high¬-performance, low-¬power designs. Unfortunately, this increased complexity often leads to higher power consumption and more challenging designs. In order to solve these problems and differentiate themselves in the market, System¬-on-Chip (SoC) manufacturers and engineers are putting tremendous effort into researching new development strategies. Numerous studies have shown that one of the key steps to take is to revisit the early stages of the design flow and, in particular, to integrate simulation-based modeling and verification at a higher level of abstraction. The early stages of product development are critical to avoiding costs, delays, and other unexpected problems. As a result, Hardware/Software (HW/SW) architectural exploration has become a key component of SoC modeling. In this thesis, we address this gap and present a framework for mixed performance and power estimation/management of SoCs using high¬-level SystemC/TLM2.0 functional models. Our methodology allows us to dynamically extract performance and power, while considering functional model activity, power management and reduction strategies, and memory system consumption. In this way, we can observe the impact of power management on performance and optimize the trade¬off between the two at the very beginning of the design flow. We address this shortcoming and present our first dynamic approach for mixed power/performance estimation applied to an NXP Intellectual Property (IP) interconnection subsystem used in i.MX8 SoC series. This modeling methodology uses the PwClkARCH library, which follows UPF semantics and enables power estimation and management. Its key point is that it maintains a strong separation between the functional code and the power intent description. There is no intrusive power¬-oriented code in the functional model, which simplifies architectural exploration, allows joint and separate reuse of behavioral and power models, and leads to more complete code and easier performance estimation
Matha, Pauline. "Pression temporelle et estimation du temps." Thesis, Toulouse 2, 2015. http://www.theses.fr/2015TOU20095/document.
Full textThis doctoral thesis aims at investigating time pressure to have a better understanding of this so familiar concept and yet so little studied. On the one hand, time pressure is ubiquitous in our occidental society; on the other hand, time perception is essential in our daily activities. Then, we have consciously opted to study time pressure through its effects on time estimation. To this end, we elaborate series of experiments within two different frameworks; time estimation literature with two different tasks (verbal estimation and time production) and prospective memory literature, more precisely with time-based prospective memory tasks. Our assumption is that time pressure leads to a subjective time distortion. The results of our experiments reveal that time pressure causes a temporal distortion when participants have to estimate or produce a duration: in the condition with time pressure they overestimate durations, compared to a condition without time pressure. In contrast, no time pressure effect is revealed on the temporal component of our time-based prospective memory task; but performance on the ongoing task is affected by time pressure
Bouet, Romain. "Activations cérébrales liées à l’intégration des indices locaux lors de la perception de la transparence : investigation basée sur l’imagerie fonctionnelle cérébrale." Lyon 2, 2007. http://theses.univ-lyon2.fr/documents/lyon2/2007/bouet_r.
Full textSurface color perception requires the global intégration of local tristimulus contrasts to differentiate shadows, illuminance gradients and transparent layers from the intrinsic spectral characteristics of the surface. We exploit the phenomenon of transparency to identify cortical areas involved in the intégration of local contrasts to extract global surface characteristics. The distribution of activity observed supports a rôle for a medio-ventro-occipital network in transparency perception. Activated areas are separable from those differentially activated when subjects view color patterns. The parahippocampus links the extraction of a transparent layer with a site activated by object-related properties of an image. This suggests that the integration of local color differences involves a coding stage at which the stimulus is transformed into a representation of an object. The processes involved may be exemplary of general mechanisms used in the brain in surface perception to disambiguate material from illuminant changes
Villon, Sébastien. "Estimation automatisée sur vidéos de la biodiversité et de l’abondance des poissons coralliens." Thesis, Montpellier, 2019. http://www.theses.fr/2019MONTG058.
Full textCoral reefs are home of a great fish biodiversity (approximately 7000 species). This biodiversity is the source of many vital ecosystem services such as protein intakes for local populations, nutrients cycle or regulation of algae abundancy. However, increasing human pressure through over-fishing and global warming is destroying both fish popu-lations and their habitats. In this context, monitoring the coral reef fish biodiversity,abundancy and biomass with precision is one of the major issues for marine ecology. To face the increasing pressure and fast globals changes, such monitoring has to be done at a large sclae, temporally and spatially. Up to date, most of fish underwater census is achieved through diving, during which the diver identify fish species and count them. Such manual census induces many constraints (depth and duration of the dive) and biais due to the diver experience. These biais (mistaking fish species or over/under estimating fish populations) are not quantifiable nor correctable. Today, thanks to the improvement of high resolution, low-cost, underwater cameras, new protocoles are developed to use video census. However, there is not yet a way to automaticaly process these underwater videos.Therefore, the analysis of the videos remains a bottleneck between the data gathering through video census and the analysis of fish communities. During this thesis, we develop-ped automated methods for detection and identification of fish in underwater videos with Deep Learning based algorithm. We work on all aspects of the pipeline, from video acqui-sition, data annotation, to the models and post-processings conception, and models testing. Today, we have gather more than 380,000 images of 300 coral reef species. We developped an identification model who successfully identified 20 of the most common species onMayotte coral reefs with 94% rate of success, and post-processing methods allowing us to decrease the error rate down to 2%. We also developped a detection method allowing us to detect up to 84% of fish individuals in underwater videos
Qian, Jun. "Identification paramétrique en boucle fermée par une commande optimale basée sur l’analyse d’observabilité." Thesis, Lyon 1, 2015. http://www.theses.fr/2015LYO10113/document.
Full textFor online parameter identification, the developed methods here allow to design online and in closed loop optimal inputs that enrich the information in the current experience. These methods are based on real-time measurements of the process, on a dynamic nonlinear (or linear) multi-variable model, on a sensitivity model of measurements with respect to the parameters to be estimated and a nonlinear observer. Analysis of observability and predictive control techniques are used to define the optimal control which is determined online by constrained optimization. Stabilization aspects are also studied (by adding fictitious constraints or by a Lyapunov technique). Finally, for the particular case of a first order linear system, the explicit control law is developed. Illustrative examples are processed via the ODOE4OPE software : a bio-reactor, a continuous stirred tank reactor and a delta wing. These examples help to see that the parameter estimation can be performed with good accuracy in a single and less costly experiment
Zendjebil, Imane. "Localisation 3D basée sur une approche de suppléance multi-capteurs pour la Réalité Augmentée Mobile en Milieu Extérieur." Phd thesis, Université d'Evry-Val d'Essonne, 2010. http://tel.archives-ouvertes.fr/tell-00541366.
Full textCharron, Jacques-Olivier. "La relation entre estimation de la valeur fondamentale des sociétés cotées et évolution de leur cours : une contribution basée sur des études de cas." Phd thesis, Conservatoire national des arts et metiers - CNAM, 2010. http://tel.archives-ouvertes.fr/tel-00646347.
Full textKhelif, Racha. "Estimation du RUL par des approches basées sur l'expérience : de la donnée vers la connaissance." Thesis, Besançon, 2015. http://www.theses.fr/2015BESA2019/document.
Full textOur thesis work is concerned with the development of experience based approachesfor criticalcomponent prognostics and Remaining Useful Life (RUL) estimation. This choice allows us to avoidthe problematic issue of setting a failure threshold.Our work was based on Case Based Reasoning (CBR) to track the health status of a new componentand predict its RUL. An Instance Based Learning (IBL) approach was first developed offering twoexperience formalizations. The first is a supervised method that takes into account the status of thecomponent and produces health indicators. The second is an unsupervised method that fuses thesensory data into degradation trajectories.The approach was then evolved by integrating knowledge. Knowledge is extracted from the sensorydata and is of two types: temporal that completes the modeling of instances and frequential that,along with the similarity measure refine the retrieval phase. The latter is based on two similaritymeasures: a weighted one between fixed parallel windows and a weighted similarity with temporalprojection through sliding windows which allow actual health status identification.Another data-driven technique was tested. This one is developed from features extracted from theexperiences that can be either mono or multi-dimensional. These features are modeled by a SupportVector Regression (SVR) algorithm. The developed approaches were assessed on two types ofcritical components: turbofans and ”Li-ion” batteries. The obtained results are interesting but theydepend on the type of the treated data
Alves, da Silva Lucas. "Estimation de la consommation d'énergie et du taux d'erreur bit d'un système Bluetooth LE basée sur la modélisation hiérarchique d'un amplificateur de puissance à 2,4 GHz." Nice, 2011. http://www.theses.fr/2011NICE4103.
Full textThe different results presented in this thesis focus on considering the energy consumption, during the development of hierarchical models for the design and verification of complex electronic systems. A wireless communication system was developed, complying to the Bluetooth Low-Energy (B-LE) standard, to estimate the whole system’s energy consumption, during the development phases. Initially, the energetic behaviour of the digital segment was studied, following the virtual prototyping approach. At the network level, an analysis of the different scan and advertisement strategies could be conducted, considering the device’s average power consumption as the optimization factor. Following, the radio transceiver’s modelling, using behavioural blocks, allows the estimation of the whole system’s energy consumption, as well as its influence over the system’s bit-error rate (BER). Finally the design of a power amplifier is presented, starting with its specification, through the architectural exploration and choice, until the circuit’s design and tape-out. Two methods are then proposed for the extraction of the power consumption, leading to refined accurate behavioural models, with minimal increase in simulation times
Domenach, Anne-Marie. "Estimation de la fixation symbiotique chez des plantes herbacées et ligneuses : utilisation et validité de la méthode basée sur la mesure des abondances isotopiques naturelles de l'azote." Lyon 1, 1987. http://www.theses.fr/1987LYO10042.
Full textSabiron, Guillaume. "Synthèse d’une solution GNC basée sur des capteurs de flux optique bio-inspirés adaptés à la mesure des basses vitesses pour un atterrissage lunaire autonome en douceur." Thesis, Toulouse, ISAE, 2014. http://www.theses.fr/2014ESAE0038/document.
Full textIn this PhD thesis, the challenge of autonomous lunar landing was addressed and an innovative method was developed, which provides an alternative to the classical sensor suites based on RADAR, LIDAR and cameras, which tend to be bulky, energy consuming and expensive. The first part is devoted to the development of a sensor inspired by the fly’s visual sensitivity to optic flow (OF). The OF is an index giving the relative angular velocity of the environment sensed by the retina of a moving insect or robot. In a fixed environment (where there is no external motion), the self-motion of an airborne vehicle generates an OF containing information about its own velocity and attitude and the distance to obstacles. Based on the “Time of Travel” principle we present the results obtained for two versions of 5 LMSs based optic flow sensors. The first one is able to measure accurately the OF in two opposite directions. It was tested in the laboratory and gave satisfying results. The second optic flow sensor operates at low velocities such as those liable to occur during lunar landing was developed. After developing these sensors, their performances were characterized both indoors and outdoors, and lastly, they were tested onboard an 80-kg helicopter flying in an outdoor environment. The Guidance Navigation and Control (GNC) system was designed in the second part on the basis of several algorithms, using various tools such as optimal control, nonlinear control design and observation theory. This is a particularly innovative approach, since it makes it possible to perform soft landing on the basis of OF measurements and as less as possible on inertial sensors. The final constraints imposed by our industrial partners were met by mounting several non-gimbaled sensors oriented in different gaze directions on the lander’s structure. Information about the lander’s self-motion present in the OF measurements is extracted by navigation algorithms, which yield estimates of the ventral OF, expansion OF and pitch angle. It was also established that it is possible to bring the planetary lander gently to the ground by tracking a pre-computed optimal reference trajectory in terms of the lowest possible fuel consumption. Software-in-the-loop simulations were carried out in order to assess the potential of the proposed GNC approach by testing its performances. In these simulations, the sensor firmware was taken into account and virtual images of the lunar surface were used in order to improve the realism of the simulated landings
Ribouh, Soheyb. "Identification de l'environnement basée sur l'estimation de canal et génération de clés de sécurité pour les communications véhiculaires." Thesis, Valenciennes, Université Polytechnique Hauts-de-France, 2020. http://www.theses.fr/2020UPHF0029.
Full textAutonomous connected vehicles are expected to see prevalent usage as part ofthe next generation of transportation systems and the smart road vision Since thevehicular environment is highly mobile, the transmitted messages are affected by thewireless channel effect. This makes channel estimation one of the challenging tasksin Vehicle-To-Everything (V2X) communications. In this context, we propose a novelMultiple Sequential Constraint Removal (MSCR) algorithm of channel estimation,dedicated to OFDM systems based-V2X communications. In addition, identifyingthe environment where the vehicle is driving along is quite important in order toallow the vehicle to make the correct self- driving decisions. Thus by exploiting theestimated wireless channel characteristics, we propose a novel vehicular environmentidentification approach based on deep learning, where the estimated channel stateinformation (CSI) are used as input features for the proposed model. Besides that,as the vehicular environment is open access exchanged messages through V2X communicationare vulnerable to attacks. Therefore, we propose a novel physical layerkey generation algorithm in order to secure vehicular communications, where the CSIvalues are used as a source of randomness. Our key generation algorithm has beenimplemented on USRP Software-Defined Radios (SDR) cards and has been tested ona real-world testbed vehicular environment. The performance evaluation results of allthe proposed methods (MSCR channel estimation algorithm, environment identificationsapproach, and key generation algorithm), show that they meet the performancesrequired in a vehicular environment
Hospital, Fabien. "Conception préliminaire des actionneurs électromagnétiques basée sur les modèles : lois d'estimations et règles de conception pour la transmission de puissance mécanique." Thesis, Toulouse, INSA, 2012. http://www.theses.fr/2012ISAT0036/document.
Full textIn the continuity of work of research on embedded systems of mechanical transmission, this these has two objectives: to improve estimation models of Electromechanical Actuator (EMA) pieces and to extend the cross-cutting vision of preliminary design to the dynamic aspects. Indeed, in the preliminary design based on models, this research should allow to adapt the choice of architectures and technologies to static and dynamic performance to achieve. The models developed from the scaling laws will be extended and exploited to modelize elementary pieces of the EMA and to highlight rules of "good practices" in preliminary design. We focus in particular on the design of EMA in aeronautic field. In the first time, we developed estimations models and métamodèles of elementary components of EMA which was decomposed in housing and elementary pieces.In a second time, we established rules of good practices for actuator sizing in control position loop. Contrary to older researches, we take into account control synthesis to create these rules. From simulations models, we quantified the influence of technological defects of components (inertia and saturations, elasticity (backlash), friction) on EMA performances. Indeed, the usual command structures and the choice of the elements of control are intimately linked to the dynamic performance and these defects.Finally, to give test way to identify with accuracy a friction model in aeronautical conditions of temperature, a test bench of Harmonic Drive was create, integrated and implemented. It allows booting the validation of rules of good practices in preliminary design
Antigny, Nicolas. "Estimation continue de la pose d'un équipement tenu en main par fusion des données visio-inertielles pour les applications de navigation piétonne en milieux urbains." Thesis, Ecole centrale de Nantes, 2018. http://www.theses.fr/2018ECDN0027/document.
Full textTo support pedestrian navigation in urban and indoor spaces, an accurate pose estimate (i.e. 3Dposition and 3D orientation) of an equipment held inhand constitutes an essential point in the development of mobility assistance tools (e.g.Augmented Reality applications). On the assumption that the pedestrian is only equipped with general public devices, the pose estimation is restricted to the use of low-cost sensors embedded in the latter (i.e. an Inertial and Magnetic Measurement Unit and a monocular camera). In addition, urban and indoor spaces, comprising closely-spaced buildings and ferromagnetic elements,constitute challenging areas for localization and sensor pose estimation during large pedestrian displacements.However, the recent development and provision of data contained in 3D Geographical Information System constitutes a new wealth of data usable for localization and pose estimation.To address these challenges, this thesis proposes solutions to improve pedestrian localization and hand-held device pose estimation in urban and indoor spaces. The proposed solutions integrate inertial and magnetic-based attitude estimation, monocular Visual Odometry with pedestrian motion estimation for scale estimation, 3D GIS known object recognition-based absolute pose estimation and Pedestrian Dead-Reckoning updates. All these solutions are fused to improve accuracy and to continuously estimate a qualified pose of the handheld device. This qualification is required tovalidate an on-site augmented reality display. To assess the proposed solutions, experimental data has been collected during pedestrian walks in an urban space with sparse known objects and indoors passages
Duterme, Amandine. "Estimation de l'état d'un procédé basée sur la réconciliation de données couplée à un simulateur : application à l'aide à la conduite d'une unité de recyclage du combustible nucléaire usé." Thesis, Toulouse, INPT, 2019. http://www.theses.fr/2019INPT0122.
Full textThe process state is defined by the flux diagram that reaches the required performances, built thanks to the knowledge of the phenomenon at stake. Characteristic measurements of the process state can be highlighted and form the state indicators. The availability of a process simulatorallows the operating data and the indicator values to be linked. The process operation support uses the available measurements, such as operating parameters and state indicators. The main goal of operation is to stay as close as possible to the targeted process state, which is characterized by the key performance indicators (KPI). It is therefore essential to follow in real time the gap between the targeted and the real state. However, takinginto account the measurement uncertainties and the potential biases on the sensors, the use of raw measurements is not satisfactory and it is of first importance to filter and reconcile the measured physical values. Within the framework of online model based application and data reconciliation (DR), we focused on software sensors for state estimation and process performances. The aim is to build a smart operation support tool for complex process, based on the knowledge of the process operations and available information through reconciled measurements. The inventory and analysis of available data from the industrial units (position and type of sensors) allows, depending on the model, the process observability and redundancy evaluation. The use of the redundancy thanks to the DR increases the confidence in operational information and generates a set of consistent data, at least with mass balance and, depending on the model, with fundamental laws that govern the behavior of matter in physics and chemistry. Two formulations to solve the optimization problem are offered and compared: the first one stands on a feasible path approach, using a knowledge-based simulator for the DR and estimating the model parameters in real time in order to exploit the maximum amount of information available through the sensors ; the second one lies on a surrogate model and an unfeasible path approach in order to prevent potential numerical challenges in feasible path approach such as complex derivative evaluation, optimizing tool and simulator interface, high calculating time and need of good initialization. The two tools aim to estimate, with maximum precision, measured or nonmeasured physical quantities, state and key performance indicators, and need to be reliable, even in the case of a missing measurement and biased sensors. The knowledge of process state and performance is of valuable assistance for operations and help in the estimation of operating margins to guarantee the safety. The suggested methodology has been validated on different scenarios carried out with industrial data from La Hague Plant, managed by Orano, recycling the spent nuclear fuel. The PUREX process achieves the co-decontamination and separation of uranium and plutonium through solvent extraction and purification cycles. The CEA has developed and validated a knowledge-based model included in the PAREX simulator. It is capable of simulating the extraction and stripping operations used in the PUREX process, in steady state and transient regime. Combining DR and PAREX simulator, the tool reduces the measurement uncertainty and helps to support decision to strive towards the optimal and safest process operation
Bonavero, Yoann. "Une approche basée sur les préférences et les méta-heuristiques pour améliorer l’accessibilité des pages Web pour les personnes déficientes visuelles." Thesis, Montpellier, 2015. http://www.theses.fr/2015MONTS274/document.
Full textWhen the sight, which is the main communication way, is altered, then the information acquisition process is also modified, degraded or limited. In today's digital world, the Web is a wealth of information organized by designers and developers and available on different Websites. Many visual pathologies can lead to difficulties in accessing this information. Beyond this information, the access to the different tools and services is also affected. Difficulties in color perception, cloud-like white patches or dark areas in a visual field, or a reduced visual field are all sources of difficulties. Each person has a particular vision. Several persons with the same pathology may even have different visions. Several assistive tools have been proposed that apply visual adaptation, trying to meet the needs of people with low vision. Main limits of these tools are mainly the unability of taking into account the very specific needs of each person. These research works are focused on the real user's needs analysis and on making a new approach based on the personal user's preferences. The final target consists in automatizing the Web page transformation according to the specific preferences of a particular user. This transformation occurs along the navigation from page to page. Different algorithms have been used, especially evolutionary algorithms, in order to make tradeoffs between the user's preferences and the original appearance of the page. The thesis further develops main problems encountered by people with low vision and some notions on color models and contrast relations. After that, we present a preference modeling language based on logics, a modeling of the problem as an optimization problem, some resolution algorithms, a tool and experiments on several real Web pages
Yousef, Soleiman. "Etude d’estimations d’erreur a posteriori et d’adaptivité basée sur des critères d’arrêt et raffinement de maillages pour des problèmes d’écoulements multiphasiques et thermiques : Application aux procédés de récupération assistée d’huile." Paris 6, 2013. http://www.theses.fr/2013PA066616.
Full textThe goal of this thesis is the a posteriori error analysis and the conception of adaptive strategies based on stopping criteria and local mesh refinement. We treat a class of multi-dimensional degenerate parabolic equations which represent typical examples of industrial interest. The considered models are discretized by a finite volume scheme in space with the backward Euler temporal stepping. We prove un upper bound for a dual norm of the residual, augmented by a nonconformity evaluation term, by fully computable error estimators. These estimators include: an estimator associated to the linearization error, an estimator associated to the algebraic error, an estimator associated to the temporal error, and an estimator associated to the spatial error. Consequently, these estimators allow to formulate an adaptive resolution algorithm where the corresponding errors can be equilibrated. We also propose a strategy of local mesh reffinement. Finally, we prove the efficiency of our a posteriori estimates. A numerical test illustrates the efficiency of our estimates and the performance of the adaptive algorithm. In particular, a significant gain in terms of the number of mesh cells, the total number of the iterations of the linearization method, and the total number of algebraic solver iterations is achieved on several real-life reservoir engineering examples
Stolle, Martin Tobias. "Vers le vol à voile longue distance pour drones autonomes." Thesis, Toulouse, ISAE, 2017. http://www.theses.fr/2017ESAE0006.
Full textSmall fixed-wing Unmanned Aerial Vehicles (UAVs) provide utility to research, military, and industrial sectors at comparablyreasonable cost, but still suffer from both limited operational ranges and payload capacities. Thermal soaring flight for UAVsoffers a significant potential to reduce the energy consumption. However, without remote sensing of updrafts, a glider UAVcan only benefit from an updraft when encountering it by chance. In this thesis, a new framework for autonomous cross-country soaring is elaborated, enabling a glider UAV to visually localize sub-cumulus thermal updrafts and to efficiently gain energy from them.Relying on the Unscented Kalman Filter, a monocular vision-based method is established, for remotely estimatingsub-cumulus updraft parameters. Its capability of providing convergent and consistent state estimates is assessed relyingon Monte Carlo Simulations. Model uncertainties, image processing noise, and poor observer trajectories can degrade theestimated updraft parameters. Therefore, a second focus of this thesis is the design of a robust probabilistic path plannerfor map-based autonomous cross-country soaring. The proposed path planner balances between the flight time and theoutlanding risk by taking into account the estimation uncertainties in the decision making process. The suggested updraftestimation and path planning algorithms are jointly assessed in a 6 Degrees Of Freedom simulator, highlighting significantperformance improvements with respect to state of the art approaches in autonomous cross-country soaring while it is alsoshown that the path planner is implementable on a low-cost computer platform
Hu, Wei. "Identification de paramètre basée sur l'optimisation de l'intelligence artificielle et le contrôle de suivi distribué des systèmes multi-agents d'ordre fractionnaire." Thesis, Ecole centrale de Lille, 2019. http://www.theses.fr/2019ECLI0008/document.
Full textThis thesis deals with the parameter identification from the viewpoint of optimization and distributed tracking control of fractional-order multi-agent systems (FOMASs) considering time delays, external disturbances, inherent nonlinearity, parameters uncertainties, and heterogeneity under fixed undirected/directed communication topology. Several efficient controllers are designed to achieve the distributed tracking control of FOMASs successfully under different conditions. Several kinds of artificial intelligence optimization algorithms andtheir modified versions are applied to identify the unknown parameters of the FOMASs with high accuracy, fast convergence and strong robustness. It should be noted that this thesis provides a promising link between the artificial intelligence technique and distributed control
Bricola, Jean-Charles. "Estimation de cartes de profondeur à partir d’images stéréo et morphologie mathématique." Thesis, Paris Sciences et Lettres (ComUE), 2016. http://www.theses.fr/2016PSLEM046/document.
Full textIn this thesis, we introduce new approaches dedicated to the computation of depth maps associated with a pair of stereo images.The main difficulty of this problem resides in the establishment of correspondences between the two stereoscopic images. Indeed, it is difficult to ascertain the relevance of matches occurring in homogeneous areas, whilst matches are infeasible for pixels occluded in one of the stereo views.In order to handle these two problems, our methods are composed of two steps. First, we search for reliable depth measures, by comparing the two images of the stereo pair with the help of their associated segmentations. The analysis of image superimposition costs, on a regional basis and across multiple scales, allows us to perform relevant cost aggregations, from which we deduce accurate disparity measures. Furthermore, this analysis facilitates the detection of the reference image areas, which are potentially occluded in the other image of the stereo pair. Second, an interpolation mechanism is devoted to the estimation of depth values, where no correspondence could have been established.The manuscript is divided into two parts: the first will allow the reader to become familiar with the problems and issues frequently encountered when analysing stereo images. A brief introduction to morphological image processing is also provided. In the second part, our algorithms to the computation of depth maps are introduced, detailed and evaluated
Charfi, Imen. "Détection automatique de chutes de personnes basée sur des descripteurs spatio-temporels : définition de la méthode, évaluation des performances et implantation temps-réel." Phd thesis, Université de Bourgogne, 2013. http://tel.archives-ouvertes.fr/tel-00959850.
Full textRondon, Sallan Eduardo. "Navigation d'un véhicule aérien par flux optique." Compiègne, 2010. http://www.theses.fr/2010COMP1912.
Full textThis thesis is focused in the design of visual strategies to ensure the autonomousnavigation of a quad-rotor rotary wing UAV. The first step on thisstudy was to design a quad-rotor perfectly suited for the requirements related to the visual navigation such as fast rotational dynamics and sufficient payload capabilities. Then the stabilization and the speed regulation problem were addressed. For this purpose, we have developed a vision system which estimates the altitude, the lateral position and the forward speed of the engine during flights. We show that the visual information allows the construction of control strategies for different kinds of flying modes: hover flight, forward flight at constant speed. A hierarchical control strategy is developed and implemented. An experimental autonomous flight was successfully achieved, validating the visual algorithm and the control law. However, in order to be completely autonomous the robot must be capable to overcome all unexpected changes in its environment. To achieve the required functions, a reactive behavior has been built. The proposed approach aims to detect and avoid frontal obstacles using known properties of the optical flow and by taking advantage of the capability of stationary flight of the rotorcraft. A state machine is proposed as a solution to equip the UAV with all reactions necessary for indoor navigation. We show how smooth transitions can be achieved by decreasing the speed of the vehicle proportionally to the distance to an obstacle and by brief instants of stationary flight
Chen, Kui. "Modeling and estimation of degradation for PEM fuel cells in real conditions of use for mobile applications." Thesis, Bourgogne Franche-Comté, 2020. http://www.theses.fr/2020UBFCA022.
Full textProton Exchange Membrane Fuel Cells (PEMFC) is a clean energy source because of the merits like high energy efficiency, low noise, low operating temperature, and zero pollutants. However, the short lifetime caused by degradation has a great impact on the integration of PEMFC in the transportation systems. Prognostics and health management is an important way to improve performance and remaining useful life for PEMFC. This thesis proposes five degradation prognosis methods for PEMFC. The thesis considers the influence of main operating conditions including the load current, temperature, hydrogen pressure, and relative humidity on the degradation of PEMFC. The global degradation trend and reversible phenomena are analyzed on the basis of data from three PEMFC experiments conducted under different conditions of use (a fleet of 10 PEMFC vehicles and two laboratory test benches). First, the model-driven method based on unscented Kalman Filter algorithm and voltage degradation model is presented to predict the degradation of PEMFC in fuel cell electric vehicles. Then, the hybrid method based on the wavelet analysis, extreme learning machine and genetic algorithm is proposed to build the degradation model of PEMFC. To forecast the degradation of PEMFC with limited experimental data, the improved data-driven method based on the combination of the grey neural network model, the particle swarm optimization and the moving window methods, is used for developing the third model. The fourth contribution is an aging prognosis model of PEMFC operating in different conditions, by using the Backpropagation neural network and evolutionary algorithm. Finally, a degradation prognosis of PEMFC based on wavelet neural network and cuckoo search algorithm is proposed to predict the remaining useful life of PEMFC
Mahdoui, Chedly Nesrine. "Communicating multi-UAV system for cooperative SLAM-based exploration." Thesis, Compiègne, 2018. http://www.theses.fr/2018COMP2447/document.
Full textIn the aerial robotic community, a growing interest for Multi-Robot Systems (MRS) appeared in the last years. This is thanks to i) the technological advances, such as better onboard processing capabilities and higher communication performances, and ii) the promising results of MRS deployment, such as increased area coverage in minimum time. The development of highly efficient and affordable fleet of Unmanned Aerial Vehicles (UAVs) and Micro Aerial Vehicles (MAVs) of small size has paved the way to new large-scale applications, that demand such System of Systems (SoS) features in areas like security, disaster surveillance, inundation monitoring, search and rescue, infrastructure inspection, and so on. Such applications require the robots to identify their environment and localize themselves. These fundamental tasks can be ensured by the exploration mission. In this context, this thesis addresses the cooperative exploration of an unknown environment sensed by a team of UAVs with embedded vision. We propose a multi-robot framework where the key problem is to cooperatively choose specific regions of the environment to be simultaneously explored and mapped by each robot in an optimized manner in order to reduce exploration time and, consequently, energy consumption. Each UAV is able to performSimultaneous Localization And Mapping (SLAM) with a visual sensor as the main input sensor. To explore the unknown regions, the targets – selected from the computed frontier points lying between free and unknown areas – are assigned to robots by considering a trade-off between fast exploration and getting detailed grid maps. For the sake of decision making, UAVs usually exchange a copy of their local map; however, the novelty in this work is to exchange map frontier points instead, which allow to save communication bandwidth. One of the most challenging points in MRS is the inter-robot communication. We study this part in both topological and typological aspects. We also propose some strategies to cope with communication drop-out or failure. Validations based on extensive simulations and testbeds are presented
Nguyen, Van Toi. "Visual interpretation of hand postures for human-machine interaction." Thesis, La Rochelle, 2015. http://www.theses.fr/2015LAROS035/document.
Full textNowadays, people want to interact with machines more naturally. One of the powerful communication channels is hand gesture. Vision-based approach has involved many researchers because this approach does not require any extra device. One of the key problems we need to resolve is hand posture recognition on RGB images because it can be used directly or integrated into a multi-cues hand gesture recognition. The main challenges of this problem are illumination differences, cluttered background, background changes, high intra-class variation, and high inter-class similarity. This thesis proposes a hand posture recognition system consists two phases that are hand detection and hand posture recognition. In hand detection step, we employed Viola-Jones detector with proposed concept Internal Haar-like feature. The proposed hand detection works in real-time within frames captured from real complex environments and avoids unexpected effects of background. The proposed detector outperforms original Viola-Jones detector using traditional Haar-like feature. In hand posture recognition step, we proposed a new hand representation based on a good generic descriptor that is kernel descriptor (KDES). When applying KDES into hand posture recognition, we proposed three improvements to make it more robust that are adaptive patch, normalization of gradient orientation in patches, and hand pyramid structure. The improvements make KDES invariant to scale change, patch-level feature invariant to rotation, and final hand representation suitable to hand structure. Based on these improvements, the proposed method obtains better results than original KDES and a state of the art method
Ben, Abdallah Nadia. "Modeling sea-level rise uncertainties for coastal defence adaptation using belief functions." Thesis, Compiègne, 2014. http://www.theses.fr/2014COMP1616.
Full textCoastal adaptation is an imperative to deal with the elevation of the global sealevel caused by the ongoing global warming. However, when defining adaptationactions, coastal engineers encounter substantial uncertainties in the assessment of future hazards and risks. These uncertainties may stem from a limited knowledge (e.g., about the magnitude of the future sea-level rise) or from the natural variabilityof some quantities (e.g., extreme sea conditions). A proper consideration of these uncertainties is of principal concern for efficient design and adaptation.The objective of this work is to propose a methodology for uncertainty analysis based on the theory of belief functions – an uncertainty formalism that offers greater features to handle both aleatory and epistemic uncertainties than probabilities.In particular, it allows to represent more faithfully experts’ incomplete knowledge (quantiles, intervals, etc.) and to combine multi-sources evidence taking into account their dependences and reliabilities. Statistical evidence can be modeledby like lihood-based belief functions, which are simply the translation of some inference principles in evidential terms. By exploiting the mathematical equivalence between belief functions and random intervals, uncertainty can be propagated through models by Monte Carlo simulations. We use this method to quantify uncertainty in future projections of the elevation of the global sea level by 2100 and evaluate its impact on some coastal risk indicators used in coastal design. Sea-level rise projections are derived from physical modelling, expert elicitation, and historical sea-level measurements. Then, within a methodologically-oriented case study,we assess the impact of climate change on extreme sea conditions and evaluate there inforcement of a typical coastal defence asset so that its functional performance is maintained