Centre de documentation
scientifique

Robustness of visual SLAM techniques to light changing conditions / Xi Wang (2022)  

Public Titre : Robustness of visual SLAM techniques to light changing conditions : Influence of contrasted local features, multi-planar representations and multimodal image analysis Type de document : Thèse/HDR Auteurs : Xi Wang, Auteur ; Eric Marchand, Directeur de thèse Editeur : Rennes : Université de Rennes 1 Année de publication : 2022 Importance : 153 p. Format : 21 x 30 cm Note générale : bibliographie Thèse de Doctorat de l'Université de Rennes 1, Spécialité Informatique Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] cartographie et localisation simultanées [Termes IGN] éclairage [Termes IGN] estimation de pose [Termes IGN] information sémantique [Termes IGN] primitive géométrique [Termes IGN] programmation linéaire [Termes IGN] robotique [Termes IGN] vision par ordinateur Index. décimale : THESE Thèses et HDR Résumé : (auteur) The SLAM (Simultaneous Localization And Mapping) technique concentrates on localizing and recovering the environment in a simultaneous way and is one of the core functionalities of many industrial products such as augmented reality, where the device poses should be tracked in real-time; autonomous driving, where one needs to localize the vehicle in a pre-generated map or unknown environment; and even modern filmmaking workflow, where the relative camera position and orientation are critical for post-processing or real-time prevising for directors and actors to visualise the visual effects on the stage. Multiple difficulties in different levels can influence the final performance of robot agents’s SLAM task, as the pipeline is long and complicated from the real world physics to the required information such as agent poses and 3-D map, which help us visualize colourful graphics scenes in AR devices or make hard decisions on the highway for autonomous driving. Many solutions are proposed for addressing each problem, respectively, with the means from classic statistic probability models to the modern data-driven deep neural network. However, the quest of improving the robot’s robustness under dynamic and complicated environments perisists and becomes more and more significant and active for nowadays robotics research. The need for improving the robustness of robot agents is imminent and regarded as one of most imperative factors for deploying robots ubiquitously in our daily life. Under this context, this thesis tries to address a small drop in the ocean of the problem of SLAM robustness, yet in a very systematic view: we try to break down the SLAM system into different and inter-influential modules. Then use the concept of "divide and conquer" for answering possible questions within each module and wishing to contribute to the community and help improve the robustness of SLAM systems under complicated conditions. With the above objectives, the contributions of the thesis are stated as follows for tackling the robustness problem from multiple angles: 1) From the image feature angle, we proposed a multiple layered image structure for improving the performance of traditional local image features under extreme conditions. Furthermore, an optimization method on linear searching and mutual information assisted convex optimization are designed for tuning the optimal parameters with the proposed structure; 2) From the geometric primitive angle, we proposed a relative pose estimation and SLAM framework under the multiple planar assumption, by keypoint feature-based and template tracker based methods, respectively. We tried to achieve better performance of mapping and tracking simultaneously with the help of a more general planar assumption. 3) From the angle of relocalization of the SLAM system, the idea is to recover the already passed locations of the robot agent for lowering the overall estimation error or when the robot is in lost status. We proposed a binary graph structure for embedding spatial information and heterogeneous data formats such as depth image, semantic information etc. The proposed method enables robotics SLAM systems to relocalize themselves with a higher success rate even under different lighting, weather and seasonal conditions. Note de contenu : 1- Introduction 2- Résumé 3- Background on visual SLAM techniques 4- Related work 5- Organisation 6- Multiple layers image 7- Multi-planar relative pose estimation via superpixel 8- TT-SLAM 9- Binary graph descriptor for robust relocalization on heterogeneous data Conclusion Numéro de notice : 24074 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Thèse française Note de thèse : Thèse de Doctorat : Informatique : Rennes 1 : 2022 Organisme de stage : IRISA DOI : sans En ligne : https://www.theses.fr/2022REN1S022 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102162

LiDAR-based point clouds registration for localization in indoor environments / Ketty Favre (2021)  

Public Titre : LiDAR-based point clouds registration for localization in indoor environments Type de document : Thèse/HDR Auteurs : Ketty Favre, Auteur ; Luce Morin, Directeur de thèse ; Eric Marchand, Directeur de thèse Editeur : Rennes : Université de Rennes 1 Année de publication : 2021 Importance : 146 p. Format : 21 x 30 cm Note générale : bibliographie Thèse de Doctorat de l'Université Rennes 1, Spécialité Signal, Image, Vision Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] algorithme de Gauss-Newton [Termes IGN] appariement d'images [Termes IGN] cartographie et localisation simultanées [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] espace intérieur [Termes IGN] octree [Termes IGN] Ransac (algorithme) [Termes IGN] recalage de données localisées [Termes IGN] scène intérieure [Termes IGN] semis de points [Termes IGN] superposition de données Index. décimale : THESE Thèses et HDR Résumé : (auteur) This thesis deals with the problem of registration of 3D point clouds in indoor environments. Registration methods are proposed to obtain a compromise between time and accuracy. First, GNMR-ICP, a multi-resolution algorithm which robustly minimizes the point-to-plane distance between two point clouds using a Gauss-Newton method. The multi-resolution is done using an octree. On the ASL benchmark dataset, GNMR-ICP gives more accurate results than its equivalent using the small angle approximation (81% success rate against 43%). Computation times in structured environments are reduced (up to a factor of 2). Next we present NAP-ICP, an algorithm based on plane matching. Planes are matched using a score function based on the characteristics of pairs of planes. An additional point-to-plane registration is performed to ensure maximum accuracy. NAP-ICP registers 100% of the interior scenes of the ASL dataset and is more accurate than the evaluated state-of-the-art functions and is able to close the loops of the LOOP’IN dataset. Finally, PAR-ICP, a plane-based method where the matching is performed using a Random Forest is presented. PAR-ICP registers 100% of the interior scenes of the ASL dataset and is able to close the loops of LOOP’IN, allowing to generate incremental maps. Note de contenu : Introduction 1- Background 2- State of the art 3- Datasets 4- Multi-resolution registration of 3D point clouds 5- Plane-based registration of 3D point clouds 6- Learning-based plane matching for planet-to-plane Conclusion Numéro de notice : 28635 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse française Note de thèse : Thèse de Doctorat : Signal, Image, Vision : Rennes 1 : 2021 Organisme de stage : Institut d'Électronique et de Télécommunications DOI : sans En ligne : http://www.theses.fr/2021REN1S059 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99666