Dissertations / Theses on the topic 'Objet déformable'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 28 dissertations / theses for your research on the topic 'Objet déformable.'
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.
Soussen, Charles. "Reconstruction 3D d'un objet compact en tomographie." Phd thesis, Université Paris Sud - Paris XI, 2000. http://tel.archives-ouvertes.fr/tel-00004126.
Giraud, Victor. "Commande robuste d'objets déformables avec des bras robotiques et application à un procédé industriel." Electronic Thesis or Diss., Université Clermont Auvergne (2021-...), 2024. http://www.theses.fr/2024UCFA0012.
Deformable objects are ubiquitous. In the form of cables, clothing, plastics, they are part ofeveryday life. These objects need to be manipulated, manufactured, and transported. Their defor-mability makes these tasks more challenging than for their rigid counterparts. The work of thisthesis focuses on solving a specific industrial case, which is unresolved and of practical interest :the assembly of heavy-duty tire treads, the part that comes into contact with the road, which isstill a manual process. This industrial process is proposed by the industrial partner Michelin wi-thin the SoftManBot consortium, a Horizon20 program of the European Union with the ambitionto automate the industrial production of deformable objects. The manipulation of deformable ob-jects raises several problems that rigid objects do not present : a modeling problem, a perceptionproblem, a shape servoing problem, and a system engineering problem to make all the precedingcomponents work together.In this thesis, we propose two major contributions. The first one, Optimal Shape Servoing, is astate feedback control based on optimal control that improves the state of the art in shape controlby adding an implicit management of the deformation trajectory - how the object reaches its finaldeformation. Furthermore, the control strategy allows for decoupling and weighting shape andposition errors. Finally, this thesis presents a demonstration-based learning of controller parametersusing a genetic algorithm to mimic the behavior of an object manipulated by a human, in orderto reproduce this deformation during manipulation tasks. Identifying these parameters throughmachine learning strategies combines the best of both worlds - both explainable operation andbehavior close to that performed by a human.Our second contribution, Holistic Architecture for Deformable Object Software, addresses thesystem engineering problem by proposing a modular software architecture that formalizes theneeds and interfaces required for deformable object manipulation problems, both in the labora-tory and in an industrial context, from user interface to gripper drivers. This architecture has beenvalidated and tested through the integration of numerous software components - models, controls,perception, user interfaces, robot controllers, camera drivers, gripper drivers. These componentsare objectively compared using industrial metrics governing the quality of a final product, allowingnot only the automation of the proposed task but also the selection of the most suitable combinationof modules for the same task
Guingo, Geoffrey. "Synthèse de texture dynamique sur objets déformables." Thesis, Université Grenoble Alpes (ComUE), 2019. http://www.theses.fr/2019GREAM053.
In virtual worlds, the objects appearance is a crucial point for users immersion. In order to approximate light-matter relationships, a common way is to use textures. To help artists during the creative process, texture synthesis and texture editing methods have emerged. These methods are differentiated by the ranges of synthesizable textures, and especially by taking into account the heterogeneous textures. These textures are composed of several regions with different contents, whose distribution is lead by a global structure. Each of the zones corresponds to a different material having a specific appearance and dynamic behavior.First, we propose an additive model of static textures, allowing on-the-fly synthesis of heterogeneous textures of arbitrary sizes from an example. This method includes a spatially varying Gaussian noise pattern, as well as a mechanism for synchronization with a structure layer. The aim is to improve the variety of synthesis while preserving plausible small details. Our method consists of an analysis phase, composed of a set of algorithms for instantiating the different layers from an example image, then a real-time synthesis step. During synthesis, the two layers are independently generated, synchronized, and added, preserving details consistency even when the structure layer is deformed to increase variety.In a second step, we propose a new approach to model and control the dynamic deformation of textures, whose implementation in the standard graphical pipeline remains simple. The deformation is modeled at pixels resolution in the form of a warping in the parametric domain. Making possible to have a different behavior for each pixel, and thus depending of texture content. The warping is locally and dynamically defined by real-time integration along the flow lines of a pre-calculated velocity field, and can be controlled by the deformation of the underlying surface geometry, by parameters of environment or through interactive editing. In addition, we propose a method to pre-compute the velocity field from a simple scalar map representing heterogeneous dynamic behaviors, as well as a solution to handle sampling problems occurring in overstretched areas at the time. deformation
Brouet, Remi. "Interactions gestuelles multi-point et géométrie déformable pour l'édition 3D sur écran tactile." Thesis, Université Grenoble Alpes (ComUE), 2015. http://www.theses.fr/2015GREAM073/document.
Multi-touch gesture interactions and deformable geometry for 3D edition on touch screen: Despite the advances made in the fields of existing objects capture and of procedural generation, creation of content for virtual worlds can not be perform without human interaction. This thesis suggests to exploit new touch devices ("multi-touch" screens) to obtain an easy, intuitive 2D interaction in order to navigate inside a virtual environment, to manipulate, position and deform 3D objects. First, we study the possibilities and limitations of the hand and finger gestures while interacting on a touch screen in order to discover which gestures are the most adapted to edit 3D scene and environment. In particular, we evaluate the effective number of degrees of freedom of the human hand when constrained on a planar surface. Meanwhile, we develop a new gesture analysis method using phases to identify key motion of the hand and fingers in real time. These results, combined to several specific user-studies, lead to a gestural design pattern which handle not only navigation (camera positioning), but also object positioning, rotation and global scaling. Then, this pattern is extended to complex deformation (such as adding and deleting material, bending or twisting part of objects, using local control). Using these results, we are able to propose and evaluate a 3D world editing interface that handle a natural touch interaction, in which mode selection (i.e. navigation, object positioning or object deformation) and task selections is automatically processed by the system, relying on the gesture and the interaction context (without any menu or button). Finally, we extend this interface to integrate more complex deformations, adapting the garment transfer from a character to any other in order to process interactive deformation of the garment while the wearing character is deformed
Duriez, Christian. "Contact frottant entre objets déformables dans des simulations temps-réels avec retour haptique." Evry-Val d'Essonne, 2004. http://www.theses.fr/2004EVRY0036.
This work aims the interactive manipulationsof virtuals objets. In interactive simulations, haptic feedback computation often comes from contact forces. Subsequentently, the fidelity of haptic feedback depends significantly on contact modeling. Contact and friction laws between deformable models are simplified. They do not allow a realistic rending of contact space physical phenomena. In this work, we use Signorini's contact law and Coulomb'sfriction law as a basis. Real-time performance is made possible thanks to the formulation of Delassus operator, and interatively solved by Gauss-Seidel type algorithm dynamica models use corotational formulation to obtain the Delassus operator in which the mass and the stiffness ratio are dissociated from the simulation time step. This global approach has been pachkaged, implemented and tested. A virtual snapin task with 6D haptic feedback illustrates the approach
Aulignac, Diego d'. "Modélisation de l'interaction avec objets déformables en temps-réel pour des simulateurs médicaux." Grenoble INPG, 2001. http://www.theses.fr/2001INPG0127.
Talbi, Nadjet. "Résolution du contact frottant entre objets déformables en temps réel et avec retour haptique." Phd thesis, Université d'Evry-Val d'Essonne, 2008. http://tel.archives-ouvertes.fr/tel-00419386.
Lombardo, Jean-Christophe. "Modélisation d'objets déformables avec un système de particules orientées." Phd thesis, Université Joseph Fourier (Grenoble), 1996. http://tel.archives-ouvertes.fr/tel-00005000.
Artinian, Azad. "Manipulation robotique d'objets déformables basée sur le modèle Cosserat." Electronic Thesis or Diss., Sorbonne université, 2024. http://www.theses.fr/2024SORUS080.
Handling deformable objects is an obvious task for human beings. We manipulate them every day, whether it's clothes, food or accessories.Even for objects we've never seen before, it's intuitive to know in advance how the object will react and deform when handled. By seeing only the geometry, appearance and texture of an object, and referring to our past experiences with other similar objects, we can very often predict in advance how the object will deform without even touching it. Furthermore, with a reduced number of interactions with a new material, it's very easy for us to extrapolate and quickly deduce the set of actions required to deform the object specifically. Robots, however, do not have this memory to help them apprehend new situations. For them, there is no obvious link between the actions they perform on an object and the shape it takes. Enabling robots to manipulate deformable objects is therefore a challenge for robotics. Behind the apparent simplicity of the task, transcribing the link we intuitively possess between the actions we perform and the shape of an object into a language that a robot can understand is a complex problem. However, many tasks involving the handling and processing of deformable objects would benefit greatly from the help of robots, whether in the industrial, public or even everyday sectors. In this thesis, we aim to advance research in this field by proposing an approach enabling a robot to manipulate deformable objects. Based on a mechanical model of the object, we first propose an off-line method for planning the robot's actions in order to perform a deformable object manipulation task, taking into account the constraints applied to the object. Secondly, we extend the previous approach to the task of detaching a deformable object attached to a flat surface. Finally, we propose an on-line shape control method, which can be used in conjunction with the planning method or independently of it
Debunne, Gilles. "Animation multirésolution d'objets déformables en temps-réel : application à la simulation chirurgicale." Phd thesis, Grenoble INPG, 2000. http://tel.archives-ouvertes.fr/tel-00006740.
El, Abed Abir. "Suivi multi-objets par filtrage particulaire dans un contexte de données incomplètes et/ou manquantes." Paris 6, 2008. http://www.theses.fr/2008PA066304.
Bonnet, Jean-François. "Segmentation, poursuite et reconnaissance automatique de cibles : Application à des objets déformables issus de séquences aériennes infrarouges." Paris 5, 2000. http://www.theses.fr/2000PA05S022.
Debunne, Gilles. "Animation multirésolution d'objets déformables en temps-réel : application à la simulation chirurgicale." Phd thesis, Grenoble INPG, 2000. http://www.theses.fr/2000INPG0138.
Animating virtual scenes in Computer Graphics is a mastered technique, widely used for special effects and video games. It is although usually restricted to the manual animation of a rigid object. This thesis will try to automatically generate the deformations of a soft object, furthermore in real-time. The goal application is the creation of a surgical simulator for minimally invasive operations aimed at surgeons training. Current methods do not allow at the same time a satisfactory visual realism and a real-time animation. In order to achieve this goal, we have used the linear elasticity laws which guarantee the realism of the simulation and ensure that the behavior of the object will be the same, whatever the discretization that we use. We propose a multiresolution simulation method which automatically adapts according to the simulation and in each region of the object the precision of the computations to obtain a trade-off between a coarse and fast simulation and on the contrary a more precise animation using more sample points. The part of the organ which is close to the tool manipulated by the user will hence be animated with a good precision, whereas distant regions, visually less important will use a coarser simulation. This research resulted in the creation of a surgical simulator prototype with a real-time animation thanks to the use of multiresolution. The realism is improved by the use of a force feedback device which simulates the organ's resistance to deformation, computed from the internal physical model
Salam, Hanan. "Modélisation Multi-Objet du visage." Phd thesis, Université Rennes 1, 2013. http://tel.archives-ouvertes.fr/tel-00957812.
Salam, Hanan. "Multi-Object modelling of the face." Thesis, Supélec, 2013. http://www.theses.fr/2013SUPL0035/document.
The work in this thesis deals with the problematic of face modeling for the purpose of facial analysis.In the first part of this thesis, we proposed the Multi-Object Facial Actions Active Appearance Model (AAM). The specificity of the proposed model is that different parts of the face are treated as separate objects and eye movements (gaze and blink) are extrinsically parameterized. This increases the generalization capabilities of classical AAM.The second part of the thesis concerns the use of face modeling in the context of expression and emotion recognition. First we have proposed a system for the recognition of facial expressions in the form of Action Units (AU). Our contribution concerned mainly the extraction of AAM features of which we have opted for the use of local models.The second system concerns multi-modal recognition of four continuously valued affective dimensions. We have proposed a system that fuses audio, context and visual features and gives as output the four emotional dimensions. We contribute to the system by finding the precise localization of the facial features. Accordingly, we propose the Multi-Local AAM. This model combines extrinsically a global model of the face and a local one of the mouth through the computation of projection errors on the same global AAM
Parisot, Pascaline. "Suivi d’objets dans des séquences d’images de scènes déformables : de l’importance des points d’intérêt et du maillage 2D." Thesis, Toulouse, INPT, 2009. http://www.theses.fr/2009INPT012H/document.
We deal with object tracking in videos of non-rigid scenes with two main purposes. We aim at determining the transformations of an object, from one frame to the next, when it may be distorted or moved and when the camera focus may change (movement, zoom...). To do this, we were inspired by the Jurie and Dhome algorithm, which enables the tracking of plane rigid objects. On the one hand, we improve its performance. On the other hand, we generalize it to non-rigid objects. The first goal consists in improving the performance of the Jurie and Dhome algorithm, in terms of accuracy and robustness. The tracking is based on a set of interest points, which has a great effect on the algorithm’s performance. These interest points come from a selection among the points extracted with some common detectors: SIFT, KLT, SUSAN, HARRIS, and MORAVEC.With various pictures classes, we have studied and implemented some selection heuristics based on statistical or algebraic approaches. We show that : • there is no universal detector, • the statistical approach is the best in all cases. The second goal is a proposal of a new tracking algorithm based on a 2D mesh of the video frames. This algorithm generalizes the Jurie and Dhome one for non-rigid scenes. It is based on : • elementary (nodal), direct or inverse, mesh transformations that we geometrically and analytically characterize, • generalized barycentric coordinates to approximate the composition of two mesh transformations. This algorithm gives similar results to the hexagonal matching algorithm of Nakaya and Harashima while being faster
Zhu, Jihong. "Vision-based robotic manipulation of deformable linear objects." Thesis, Montpellier, 2020. http://www.theses.fr/2020MONTS008.
In robotics, the area of deformable object manipulation receives far less attention than that of rigid object manipulation. However, many objects in real life are deformable. Research on deformable object manipulation is indispensable to equip robots with full manipulation dexterity. Deformable linear object (DLO) is one type of deformable objects that commonly presents in the industry and households, for instance, electrical cables for power transfer, USB cables for data transfer, or ropes for dragging and lifting equipment. In the context of H2020 VERSATILE, a project focusing on industrial automation using robots, we focus our research on DLO manipulation via visual feedback.One characteristic of deformable object manipulation is that the object shape changes while being manipulated. Consequently, a research direction is to control the shape of the object during manipulation. We tackle the shape control problem by using vision. Initially, we parameterize the shape with Fourier series, estimate and update the interaction matrix online, and finally control the DLO shape.In the subsequent research, instead of using human-defined features for parameterization, we let the robot automatically learn feature vectors from visual data. We propose a method that allows the robot to simultaneously generate a feature vector and the interaction matrix from the same data. Our approach requires minimum data for initialization. Learning and control can be done online in an adaptive manner. We can also apply the method to rigid object manipulation directly without modification.Neither of the two frameworks requires camera calibration, and both are verified with simulation and real robotic experiments.Another area of importance in deformable object manipulation is the utilization of external contacts. The object deformation is defined in a configuration space of infinite dimension. Nonetheless, the inputs from robots are limited. External contacts can and should be used for manipulating deformable objects. We take a practical scenario in the industry -- cable routing with external contacts as the process to automate with our robot. We propose a planning algorithm that allows the robot to use contacts for shaping the cable and achieving the desired cable configuration. Real robotic experiments with different contact placement scenarios further validate the algorithms
Tsogkas, Stavros. "Mid-level representations for modeling objects." Thesis, Université Paris-Saclay (ComUE), 2016. http://www.theses.fr/2016SACLC012/document.
In this thesis we propose the use of mid-level representations, and in particular i) medial axes, ii) object parts, and iii)convolutional features, for modelling objects.The first part of the thesis deals with detecting medial axes in natural RGB images. We adopt a learning approach, utilizing colour, texture and spectral clustering features, to build a classifier that produces a dense probability map for symmetry. Multiple Instance Learning (MIL) allows us to treat scale and orientation as latent variables during training, while a variation based on random forests offers significant gains in terms of running time.In the second part of the thesis we focus on object part modeling using both hand-crafted and learned feature representations. We develop a coarse-to-fine, hierarchical approach that uses probabilistic bounds for part scores to decrease the computational cost of mixture models with a large number of HOG-based templates. These efficiently computed probabilistic bounds allow us to quickly discard large parts of the image, and evaluate the exact convolution scores only at promising locations. Our approach achieves a $4times-5times$ speedup over the naive approach with minimal loss in performance.We also employ convolutional features to improve object detection. We use a popular CNN architecture to extract responses from an intermediate convolutional layer. We integrate these responses in the classic DPM pipeline, replacing hand-crafted HOG features, and observe a significant boost in detection performance (~14.5% increase in mAP).In the last part of the thesis we experiment with fully convolutional neural networks for the segmentation of object parts.We re-purpose a state-of-the-art CNN to perform fine-grained semantic segmentation of object parts and use a fully-connected CRF as a post-processing step to obtain sharp boundaries.We also inject prior shape information in our model through a Restricted Boltzmann Machine, trained on ground-truth segmentations.Finally, we train a new fully-convolutional architecture from a random initialization, to segment different parts of the human brain in magnetic resonance image data.Our methods achieve state-of-the-art results on both types of data
Baudet, Vincent. "Modélisation et simulation paramétrable d'objets déformables.Application aux traitements des cancers pulmonaires." Phd thesis, Université Claude Bernard - Lyon I, 2006. http://tel.archives-ouvertes.fr/tel-00279986.
En partenariat avec le Centre anticancéreux Léon Bérard de Lyon et dans le projet ETOILE, nous proposons de rechercher des modèles de simulations des objets déformables qui prendraient en considération, en plus de la géométrie issue directement de l'imagerie médicale, les paramètres physiologiques mesurés sur les patients afin de pouvoir garantir de meilleures marges d'erreur, dans le cas des tumeurs pulmonaires.
Dans cette thèse, nous avons choisi de modéliser les poumons avec des systèmes masses-ressorts qui sont généralement utilisés dans le monde de l'animation pour le réalisme et la rapidité.
Pour rendre le système précis et directement paramétré par les données mécaniques du patient, nous nous sommes inspirés des travaux de Van Gelder qui introduit un contrôle par les caractéristiques rhéologiques d'un matériaux "2D" linéaire élastique homogène isotrope.
Cependant, après vérification et étude théorique de ce modèle, il est apparut que celui-ci bien que donnant des animations réalistes était erroné.
Nous avons donc entrepris une étude lagrangienne qui nous a permis de rendre ce modèle 2D rectangulaire, puis 3D à base de brique élémentaire cubique, paramétrable.
Nous avons d'autre part déterminer la robustesse de notre système à l'aide de tests d'étirement, gonflement, fléchissement et cisaillement et par comparaison à des tests effectués sur des modèles éléments finis.
Cette thèse explique ainsi comment ce modèle paramétrable a été obtenu, et comment il pourra être relié avec les données physiologiques et dans quelle précision.
Ladjal, Hamid. "Développement d'un simulateur haptique pour la cacaractérisation et la microinjection cellulaires." Thesis, Orléans, 2010. http://www.theses.fr/2010ORLE2019/document.
The fundamental objective of this thesis is to develop and implementing an interactive simulation techniquesfor micromanipulation biological cells. Using this tool, the operator can form, train and improve its control bydeveloping a gesture similar to that performed in reality. The design of such a simulation environment in realtime requires a compromise between the realism of biomechanical models used the accuracy and stability ofalgorithms and solution methods used haptic rendering and computational speed. Modeling Mechanicalrestraint involves the use of hyperelastic model of St Venant-Kirchhoff formulation and explicit dynamic finiteelement-type mass tensors. The validity of this model is tested on microindentation tests by Atomic ForceMicroscopy (AFM) of mouse embryonic stem cells and microinjection of oocytes. We have developed andimplemented models of real-time interaction that revolve around the detection and management of rapidcollisions between tool / cell.The synthesis of the haptic feedback provided to the operator is also available through a virtual coupling. Foreach application, we have justified our methodological choices and Algorithms that are guided by theconstraints of realism + precision "" real time ". The various proposed models have been integrated into thesimulator SIMIC that we developed during this thesis. This is dedicated to interactive simulation to supportlearning of gesture microinjection and cell nanoindentation
Sanchez, Loza Jose Manuel. "Shape sensing of deformable objects for robot manipulation." Thesis, Université Clermont Auvergne (2017-2020), 2019. http://www.theses.fr/2019CLFAC012/document.
Deformable objects are ubiquitous in our daily lives. On a given day, we manipulate clothes into uncountable configurations to dress ourselves, tie the shoelaces on our shoes, pick up fruits and vegetables without damaging them for our consumption and fold receipts into our wallets. All these tasks involve manipulating deformable objects and can be performed by an able person without any trouble, however robots have yet to reach the same level of dexterity. Unlike rigid objects, where robots are now capable of handling objects with close to human performance in some tasks; deformable objects must be controlled not only to account for their pose but also their shape. This extra constraint, to control an object's shape, renders techniques used for rigid objects mainly inapplicable to deformable objects. Furthermore, the behavior of deformable objects widely differs among them, e.g. the shape of a cable and clothes are significantly affected by gravity while it might not affect the configuration of other deformable objects such as food products. Thus, different approaches have been designed for specific classes of deformable objects.In this thesis we seek to address these shortcomings by proposing a modular approach to sense the shape of an object while it is manipulated by a robot. The modularity of the approach is inspired by a programming paradigm that has been increasingly been applied to software development in robotics and aims to achieve more general solutions by separating functionalities into components. These components can then be interchanged based on the specific task or object at hand. This provides a modular way to sense the shape of deformable objects.To validate the proposed pipeline, we implemented three different applications. Two applications focused exclusively on estimating the object's deformation using either tactile or force data, and the third application consisted in controlling the deformation of an object. An evaluation of the pipeline, performed on a set of elastic objects for all three applications, shows promising results for an approach that makes no use of visual information and hence, it could greatly be improved by the addition of this modality
Sengupta, Agniva. "Visual tracking of deformable objects with RGB-D camera." Thesis, Rennes 1, 2020. http://www.theses.fr/2020REN1S069.
Tracking soft objects using visual information has immense applications in the field of robotics, computer graphics and automation. In this thesis, we propose multiple new approaches for tracking both rigid and non-rigid objects using a RGB-D camera. There are four main contributions of this thesis. The first contribution is a rigid object tracking method which utilizes depth and photometry based errors for tracking complex shapes using their coarse, 3D template. The second contribution is a non-rigid object tracking method which uses co-rotational FEM to track deforming objects by regulating the virtual forces acting on the surface of a physics based model of the object. The third contribution is a deformation tracking approach which minimizes a combination of geometric and photometric error while utilizing co-rotation FEM as the deformation model. The fourth contribution involves estimating the elasticity properties of a deforming object while tracking their deformation using RGB-D camera. Once the elasticity parameters have been estimated, the same methodology can be re-utilized for tracking contact forces on the surface of deforming objects
Madi, Kamel. "Inexact graph matching : application to 2D and 3D Pattern Recognition." Thesis, Lyon, 2016. http://www.theses.fr/2016LYSE1315/document.
Graphs are powerful mathematical modeling tools used in various fields of computer science, in particular, in Pattern Recognition. Graph matching is the main operation in Pattern Recognition using graph-based approach. Finding solutions to the problem of graph matching that ensure optimality in terms of accuracy and time complexity is a difficult research challenge and a topical issue. In this thesis, we investigate the resolution of this problem in two fields: 2D and 3D Pattern Recognition. Firstly, we address the problem of geometric graphs matching and its applications on 2D Pattern Recognition. Kite (archaeological structures) recognition in satellite images is the main application considered in this first part. We present a complete graph based framework for Kite recognition on satellite images. We propose mainly two contributions. The first one is an automatic process transforming Kites from real images into graphs and a process of generating randomly synthetic Kite graphs. This allowing to construct a benchmark of Kite graphs (real and synthetic) structured in different level of deformations. The second contribution in this part, is the proposition of a new graph similarity measure adapted to geometric graphs and consequently for Kite graphs. The proposed approach combines graph invariants with a geometric graph edit distance computation. Secondly, we address the problem of deformable 3D objects recognition, represented by graphs, i.e., triangular tessellations. We propose a new decomposition of triangular tessellations into a set of substructures that we call triangle-stars. Based on this new decomposition, we propose a new algorithm of graph matching to measure the distance between triangular tessellations. The proposed algorithm offers a better measure by assuring a minimum number of triangle-stars covering a larger neighbourhood, and uses a set of descriptors which are invariant or at least oblivious under most common deformations. Finally, we propose a more general graph matching approach founded on a new formalization based on the stable marriage problem. The proposed approach is optimal in term of execution time, i.e. the time complexity is quadratic O(n2) and flexible in term of applicability (2D and 3D). The analyze of the time complexity of the proposed algorithms and the extensive experiments conducted on Kite graph data sets (real and synthetic) and standard data sets (2D and 3D) attest the effectiveness, the high performance and accuracy of the proposed approaches and show that the proposed approaches are extensible and quite general
Laranjeira, Moreira Matheus. "Visual servoing on deformable objects : an application to tether shape control." Electronic Thesis or Diss., Toulon, 2019. http://www.theses.fr/2019TOUL0007.
This thesis addresses the problem of tether shape contrai for small remotely operated underwater vehicles (mini-ROVs), which are suitable, thanks to their small size and high maneuverability, for the exploration of shallow waters and cluttered spaces. The management of the tether is, however, a hard task, since these robots do not have enough propulsion power to counterbalance the drag forces acting on the tether cable. ln order to cape with this problem, we introduced the concept of a Chain of miniROVs, where several robots are linked to the tether cable and can, together, manage the external perturbations and contrai the shape of the cable. We investigated the use of the embedded cameras to regulate the shape of a portion of tether linking two successive robots, a leader and a follower. Only the follower robot deals with the tether shape regulation task. The leader is released to explore its surroundings. The tether linking bath robots is assumed to be negatively buoyant and is modeled by a catenary. The tether shape parameters are estimated in real-time by a nonlinear optimization procedure that fits the catenary model to the tether detected points in the image. The shape parameter regulation is thus achieved through a catenary-based contrai scheme relating the robot motion with the tether shape variation. The proposed visual servoing contrai scheme has proved to properly manage the tether shape in simulations and real experiments in pool
Roca, Filella Nicolas. "Contributions à la robotisation de tâches entrant dans la fabrication de pneumatiques." Electronic Thesis or Diss., Université Clermont Auvergne (2021-...), 2023. http://www.theses.fr/2023UCFA0011.
Robotics research is increasingly interested in the manipulation of soft objects: fabrics, foams or any other deformable object like rubber. The deformation of such an object is usually modeled by introducing new degrees of freedom, which makes its control more complex. In the context of the industry of the future, the Manufacture Française des Pneumatiques Michelin wishes to modernize its tire manufacturing process which consists of assembling, layer by layer, strips and plies of rubber. These tasks, which have never been robotized before this thesis, fall within the domain of robotic manipulation of deformable objects (RMDO).Through the CIFRE plan (French Industrial Research Training Convention) of the ANRT (French National Association for Technological Research), this thesis addresses this issue in an industrial application context through the design of a robotic cell by providing innovative technological solutions, especially in terms of actuation, perception, and control. However, we show that the integration of these solutions is limited by classical problems of RMDO, such as the modeling of object deformations, multimodal perception or dynamic control and generation of tasks.A first contribution is the adaptation of image processing algorithms from open-source libraries to an industrial context. These algorithms replace commercial industrial solutions and allow a greater freedom of parameterization for each function. The result is an assembly of flexible algorithmic bricks adapted to the specificities of the tire manufacturing process.This thesis also explores the use of a reduced physical model to control the tension in a suspended gum strip, one end of which is wrapped around a spool while the other is manipulated by a robot. We distinguish three contributions: vision-based estimation of the tension, a closed-loop control law to regulate the rotation speed of the reel and thus vary the length of the suspended part of the strip, and a planning algorithm to achieve the desired tension.A last contribution concerns a visual feedback control allowing to join end to end the two ends of a web wrapped around a cylindrical surface. This complex operation is based on visual perception and 3D reconstruction of the edge of the ply as well as a control law considering a weighted measure of the error.Our developments have enabled the design and production of an industrial demonstrator that is ready for deployment in a factory. This means that industrial constraints such as sizing, cycle time, available hardware and software architecture, and quality tolerances have been considered from the beginning of the scientific reflection. Experimental validations were carried out on this test bench
Le, Thanh Nam. "Graph representation and mining applied in comic images retrieval." Thesis, La Rochelle, 2019. http://www.theses.fr/2019LAROS008.
In information retrieval tasks from image databases where content representation is based on graphs, the evaluation of similarity is based both on the appearance of spatial entities and on their mutual relationships. In this thesis we present a novel scheme of Attributed Relational Adjacency Graphs representation and mining, which has been applied in content-based retrieval of comic images. The images used in this thesis are comics images, which have their inherent difficulties in applying content-based retrieval, such as their abstractness, partial occlusion, scale change and shape deformation due to viewpoint changes. We propose a graph representation that yields stable graphs and allow to retain high-level and structural information of objects of interest in comic images. Next, we extend the indexing and matching problem to graph structures representing the comic image, and apply it to the problem of retrieval. The graphs in the graph database representing the whole comic volume are then mined for frequent patterns (or frequent substructures). This step is to overcome the non-repeatability problem caused by the unavoidable errors introduced into the graph structure during the graph construction stage, which ultimately create a semantic gap between the graph and the content of the comic image. Finally, we demonstrate the effectiveness of the system with a database of annotated comic images. Experiments of performance measures is addressed to evaluate the performance of this CBIR system
Gascuel, Marie-Paule. "Modèles déformables pour l'animation : modélisation, animation et contrôle." Habilitation à diriger des recherches, 1995. http://tel.archives-ouvertes.fr/tel-00346054.
Dehaes, Mathieu. "Représentations analytiques des objets géométriques et contours actifs en imagerie." Thèse, 2004. http://hdl.handle.net/1866/14589.