Descripteur
Documents disponibles dans cette catégorie (1700)
![](./images/expand_all.gif)
![](./images/collapse_all.gif)
Etendre la recherche sur niveau(x) vers le bas
Learning embeddings for cross-time geographic areas represented as graphs / Margarita Khokhlova (2021)
![]()
Titre : Learning embeddings for cross-time geographic areas represented as graphs Type de document : Article/Communication Auteurs : Margarita Khokhlova , Auteur ; Nathalie Abadie
, Auteur ; Valérie Gouet-Brunet
, Auteur ; Liming Chen, Auteur
Editeur : New York [Etats-Unis] : Association for computing machinery ACM Année de publication : 2021 Projets : Alegoria / Gouet-Brunet, Valérie Conférence : SAC 2021, 36th Annual ACM Symposium on Applied Computing 22/03/2021 26/03/2021 en ligne Proceedings ACM Importance : pp 559 - 568 Format : 21 x 30 cm Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] arête
[Termes IGN] classification par réseau neuronal
[Termes IGN] entité géographique
[Termes IGN] graphe flou
[Termes IGN] image aérienne à axe vertical
[Termes IGN] noeud
[Termes IGN] relation spatiale
[Termes IGN] représentation graphique
[Termes IGN] réseau neuronal de graphesRésumé : (auteur) Geographic entities from the vertical aerial images can be viewed as discrete objects and represented as nodes in a graph, linked to each other by edges capturing their spatial relationships. Over time, the natural and man made landscape may evolve and thus also their graph representations. This paper addresses the challenging problem of the retrieval and fuzzy matching of graphs to localize near-identical geographical areas across time. Several use-case scenarios are proposed for the end-to-end learning of a graph embedding using Graph Neural Networks (GNN), along with an effective baseline without learning. The results demonstrate the efficiency of our approach, that enables efficient similarity reasoning for novel hand-engineered cross-time graph data. Code and data processing scripts are available online. Numéro de notice : C2021-002 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Thématique : IMAGERIE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.1145/3412841.3441936 En ligne : https://doi.org/10.1145/3412841.3441936 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97583
Titre : Learning harmonised Pleiades and Sentinel-2 surface reflectances Type de document : Article/Communication Auteurs : J. Michel, Auteur ; Jordi Inglada, Auteur Editeur : International Society for Photogrammetry and Remote Sensing ISPRS Année de publication : 2021 Collection : International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, ISSN 1682-1750 num. 43-B2-2021 Conférence : ISPRS 2021, Commission 2, XXIV ISPRS Congress, Imaging today foreseeing tomorrow 05/07/2021 09/07/2021 Nice Virtuel France OA Archives Commission 2 Importance : pp 265 - 272 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] classification par Perceptron multicouche
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] image Pléiades
[Termes IGN] image Sentinel-MSI
[Termes IGN] réflectance de surface
[Termes IGN] régression linéaireRésumé : (auteur) In this paper, we investigate the use of machine-learning techniques in order to produce harmonised surface reflectances between Sentinel-2 and Pleiades images, and reduce the impact of the differences in sensors, view conditions, and atmospheric correction differences between them. We demonstrate that if a simple linear regression considering Sentinel-2 surface reflectances as the target domain can overcome this problem when both images are calibrated to Top of Canopy reflectances, the non-linearity brought by a simple Multi-Layer-Perceptron is already useful when Pleiades is corrected to Top of Atmosphere level and contributions of the atmosphere need to be learned. We also demonstrate that learning a Convolution Neural Network instead of a plain MLP can learn undesired spatial effects such as mis-registration or differences in spatial frequency content, that will affect the image quality of the corrected Pleiades product. We overcome this issue by proposing an adhoc input convolutional layer that will capture those effects and can later be unplugged during inference. Last, we also propose an architecture and loss function that is robust to unmasked clouds and produces a confidence prediction during inference. Numéro de notice : C2021-019 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Communication DOI : 10.5194/isprs-archives-XLIII-B3-2021-265-2021 Date de publication en ligne : 28/06/2021 En ligne : https://doi.org/10.5194/isprs-archives-XLIII-B3-2021-265-2021 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98071
Titre : Learning to map street-side objects using multiple views Type de document : Thèse/HDR Auteurs : Ahmed Samy Nassar, Auteur ; Sébastien Lefèvre, Directeur de thèse ; Jan Dirk Wegner, Directeur de thèse Editeur : Vannes : Université de Bretagne Sud Année de publication : 2021 Importance : 139 p. Format : 21 x 30 cm Note générale : bibliographie
Thèse de Doctorat de l'Université de Bretagne Sud, spécialité InformatiqueLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage profond
[Termes IGN] arbre urbain
[Termes IGN] cartographie par internet
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] détection d'objet
[Termes IGN] données multisources
[Termes IGN] estimation de pose
[Termes IGN] géolocalisation
[Termes IGN] graphe
[Termes IGN] image Streetview
[Termes IGN] inventaire
[Termes IGN] mobilier urbain
[Termes IGN] vision par ordinateurIndex. décimale : THESE Thèses et HDR Résumé : (auteur) Creating inventories of street-side objects and their monitoring in cities is a labor-intensive and costly process. Field workers are known to conduct this process on-site to record properties about the object. These properties can be the location, species, height, and health of a tree as an example. To monitor cities, gathering such information on a large scale becomes challenging. With the abundance of imagery, adequate coverage of a city is achieved from different views provided by online mapping services (e.g., Google Maps and Street View, Mapillary). The availability of such imagery allows efficient creation and updating of inventories of street-side objects status by using computer vision methods such as object detection and multiple object tracking. This thesis aims at detecting and geo-localizing street-side objects, especially trees and street signs, from multiple views using novel deep learning methods. Note de contenu : 1- Introduction
2- Background
3- Multi-view instance matching with learned geometric soft-constraints
4- Simultaneous multi-view instance detection with learned geometric softconstraints
5- GeoGraphV2: Graph-based aerial & street view multi-view object detection with geometric cues end-to-end
6- ConclusionNuméro de notice : 28674 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Thèse française Note de thèse : Thèse de Doctorat : Informatique : Université de Bretagne Sud : 2021 Organisme de stage : IRISA DOI : sans En ligne : https://hal.science/tel-03523658 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99920 Model based signal processing techniques for nonconventional optical imaging systems / Daniele Picone (2021)
![]()
Titre : Model based signal processing techniques for nonconventional optical imaging systems Type de document : Thèse/HDR Auteurs : Daniele Picone, Auteur ; Mauro Dalla Mura, Directeur de thèse Editeur : Grenoble [France] : Université Grenoble Alpes Année de publication : 2021 Importance : 364 p. Format : 21 x 30 cm Note générale : bibliographie
Thèse pour obtenir le grade de Docteur de l'Université Grenoble Alpes, spécialité : Signal Image Parole TélécomsLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] acquisition comprimée
[Termes IGN] fusion d'images
[Termes IGN] image hyperspectrale
[Termes IGN] inférence statistique
[Termes IGN] interférométrie
[Termes IGN] méthode du maximum de vraisemblance (estimation)
[Termes IGN] mosaïque d'images
[Termes IGN] pouvoir de résolution géométrique
[Termes IGN] pouvoir de résolution spectrale
[Termes IGN] problème inverse
[Termes IGN] reconstruction d'image
[Termes IGN] régression non linéaire
[Termes IGN] spectromètre imageur
[Termes IGN] traitement du signalIndex. décimale : THESE Thèses et HDR Résumé : (auteur) There is an increasing demand for images with higher spectral and spatial resolution for applications in several domains such as health, environment, quality checking and natural disasters monitoring. Hyperspectral imagery provides the necessary spectral diversity to recover the composition of materials on site for applications such as the detection of fires, anomalies, chemical agents, targets and changes in the scene.The requirement for cheaper and more compact devices (e.g. to be embarked on low cost satellites and airborne platform) which are capable of capturing this information has led to the development of nonconventional innovative design concepts to overcome the technological limitations of traditional cameras. Data acquired by such novel imaging devices following the computational imaging paradigm are typically not readily exploitable for the final application. A computational phase is hence needed for extracting useful information from the raw acquisitions.This thesis addresses this issue by setting up an inversion problem. The general approach is to characterize the data fidelity term with a physical model, describing the underlying optical transformations performed by the device. The challenge is then shifted on the regularization step to properly characterizes the features of the quantities of interest and improve the accuracy of the estimation, which can be tackled with variational techniques.The analysis is applied to two novel concepts for nonconventional optical devices. The first one is a novel compressed acquisition imaging system based on color filter arrays, which embeds information from sensors with different spatial and spectral characteristics into a single mosaiced product. As opposed to existing compressed sensing based devices, the goal is not to recover the original uncompressed multiresolution sources, but instead to directly recover a synthetic fused image with both high spatial and spectral resolution.The proposed solution relies on the total variation regularization and is the subject of a detailed analysis, comparing its compressive power with straightforward software alternatives, evaluating its performances as the amount of channels changes, and validating its efficiency in comparison to state of the art methods when applied to classical fusion or mosaicing algorithms separately.The second class of devices is based on the ImSPOC patent, a design concept for a low finesse snapshot imaging spectrometer based on the interferometry of Fabry-Pérot. Its ideal behaviour follows the principle of the Fourier Transform Spectroscopy, as its acquisition can be interpreted as a sampled version of an interferogram, arranged across different sub-images distributed on the same focal plane.After defining a physical model based on optical geometry, its validity is evaluated over real acquisitions by setting up a Bayesian inference problem to determine its parameters, with approaches based on maximum likelihood estimators, regular-grid searches and nonlinear regression.A variety of preliminary tests are then carried out on the inversion method, with approaches based on singular value decomposition and sparse-inducing regularizers, accompanied by a analysis of their robustness to model mismatches. Note de contenu : 1- Introduction
2- Inverse problems theory
3- Signal processing of multimodal data
4- Joint fusion and demosaicing of compressed multiresolution acquisitions
5- Optics foundations for the ImSPOC acquisition system
6- Data processing pipeline of ImSPOC acquisitions
7- ConclusionsNuméro de notice : 28691 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse française Note de thèse : Thèse de Doctorat : Signal Image Parole Télécoms : Grenoble : 2021 Organisme de stage : GIPSA-lab DOI : sans En ligne : https://hal.science/tel-03596486v1 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100170
Titre : Multispectral object detection Type de document : Thèse/HDR Auteurs : Heng Zhang, Auteur ; Elisa Fromont, Directeur de thèse ; Sébastien Lefèvre, Directeur de thèse Editeur : Rennes : Université de Rennes 1 Année de publication : 2021 Importance : 114 p. Format : 21 x 30 cm Note générale : Bibliographie
Thèse présentée en vue de l’obtention du grade de docteur en Informatique de l'Université de Rennes 1Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage profond
[Termes IGN] chambre de prise de vue thermique
[Termes IGN] détection d'objet
[Termes IGN] données d'entrainement sans étiquette
[Termes IGN] efficacité
[Termes IGN] fusion de données multisource
[Termes IGN] image multibande
[Termes IGN] précision de la classification
[Termes IGN] qualité du modèle
[Termes IGN] segmentation sémantiqueIndex. décimale : THESE Thèses et HDR Résumé : (Auteur) Only using RGB cameras for automatic outdoor scene analysis is challenging when, for example, facing insufficient illumination or adverse weather. To improve the recognition reliability, multispectral systems add additional cameras (e.g. infra-red) and perform object detection from multispectral data. Although multispectral scene analysis with deep learning has been shown to have a great potential, there are still many open research questions and it has not been widely deployed in industrial contexts. In this thesis, we investigated three main challenges about multispectral object detection: (1) the fast and accurate detection of objects of interest from images; (2) the dynamic and adaptive fusion of information from different modalities;(3) low-cost and low-energy multispectral object detection and the reduction of its manual annotation efforts. In terms of the first challenge, we first optimize the label assignment of the object detection training with a mutual guidance strategy between the classification and localization tasks; we then realize an efficient compression of object detection models including the teacher-student prediction disagreements in a feature-based knowledge distillation framework. With regard to the second challenge, three different multispectral feature fusion schemes are proposed to deal with the most difficult fusion cases where different cameras provide contradictory information. For the third challenge, a novel modality distillation framework is firstly presented to tackle the hardware and software constraints of current multispectral systems; then a multi-sensor-based active learning strategy is designed to reduce the labeling costs when constructing multispectral datasets. Note de contenu : 1. Introduction
1.1 Context and motivations
1.2 Thesis outline
2. Deep learning background
2.1 General object detection
2.2 Multispectral object detection
2.3 Knowledge distillation
2.4 Active learning
2.5 Datasets
3. Efficient object detection on embedded devices
3.1 Best practices for training object detection models
3.2 Mutual Guidance for Anchor Matching
3.3 Prediction Disagreement aware Feature Distillation
3.4 Experimental results
4. Information fusion from multispectral data
4.1 Multispectral Fusion with Cyclic Fuse-and-Refine
4.2 Progressive Spectral Fusion
4.3 Experimental results for CFR and PS-Fuse
4.4 Guided Attentive Feature Fusion
4.5 Experimental results for GAFF
5. Sensors and annotations: low cost multispectral data processing
5.1 Deep Active Learning from Multispectral Data
5.2 Low-cost Multispectral Scene Analysis with Modality Distillation
6. Conclusions and future works
6.1 Conclusions
6.2 Application to remote sensing data
6.3 PerspectivesNuméro de notice : 26765 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse française Note de thèse : Thèse de Doctorat : Informatique : Rennes 1 : 2021 Organisme de stage : (IRISA) INRIA nature-HAL : Thèse DOI : sans Date de publication en ligne : 17/01/2022 En ligne : https://hal.science/tel-03530257/ Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99855 PermalinkObject detection using component-graphs and ConvNets with application to astronomical images / Thanh Xuan Nguyen (2021)
PermalinkPermalinkPanoptic segmentation of satellite image time series with convolutional temporal attention networks / Vivien Sainte Fare Garnot (2021)
PermalinkPerception de scène par un système multi-capteurs, application à la navigation dans des environnements d'intérieur structuré / Marwa Chakroun (2021)
PermalinkRemotely-sensed rip current dynamics and morphological control in high-energy beach environments / Isaac Rodriguez Padilla (2021)
PermalinkPermalinkReprésentation sémantique de données géospatiales au service de l'analyse de changements / Jordan Dorne (2021)
PermalinkA review of image fusion techniques for pan-sharpening of high-resolution satellite imagery / Farzaneh Dadrass Javan in ISPRS Journal of photogrammetry and remote sensing, vol 171 (January 2021)
PermalinkPermalink