Détail de l'auteur
Auteur Elisa Fromont |
Documents disponibles écrits par cet auteur (2)
![](./images/expand_all.gif)
![](./images/collapse_all.gif)
![Tris disponibles](./images/orderby_az.gif)
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 Spatio-temporal grid mining applied to image classification and cellular automata analysis / Romain Deville (2018)
![]()
Titre : Spatio-temporal grid mining applied to image classification and cellular automata analysis Type de document : Thèse/HDR Auteurs : Romain Deville, Auteur ; Christine Solnon, Directeur de thèse ; Elisa Fromont, Directeur de thèse ; Baptiste Jeudy, Directeur de thèse Editeur : Lyon : Institut National des Sciences Appliquées INSA Lyon Année de publication : 2018 Importance : 145 p. Format : 21 x 30 cm Note générale : bibliographie
Thèse de Doctorat de l'Université de Lyon opérée au sein de l’INSA de Lyon, Spécialité InformatiqueLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] automate cellulaire
[Termes IGN] classification dirigée
[Termes IGN] classification par séparateurs à vaste marge
[Termes IGN] exploration de données
[Termes IGN] grille
[Termes IGN] modèle sac-de-mots
[Termes IGN] SIFT (algorithme)Index. décimale : THESE Thèses et HDR Résumé : (auteur) During this thesis, we consider the exhaustive graph mining problem for a special kind of graphs : the grids. Theses grids can be used to model objects that present a regular structure. These structures are naturally present in multiple board games (checkers, chess or go for instance) or in ecosystems models using cellular automata. It is also possible to find this structure in a lower level in images, which are 2D grids of pixels, or even in videos, which are 2D+t spatio-temporal grids of pixels. In this thesis, we proposed a new algorithm to find frequent patterns dedicated to spatio-temporal grids, GriMA. Use of regular grids allow our algorithm to reduce the complexity of the isomorphisms test. These tests are often use by generic graph mining algorithm but because of their complexity, they are rarely used on real data. Two applications were proposed to evaluate our algorithm: image classification for 2D grids mining and prediction of cellular automata for 2D+t grids mining. Note de contenu : 1- Introduction
2- Background on graphs
3- Existing graph mining algoritms
4- Definition on grids
5- Description of GriMA
6- Application of GriMA to image classification
7- Application of GriMA to cellular automata analysis
8- ConclusionNuméro de notice : 25959 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Thèse française Note de thèse : Thèse de Doctorat : Informatique : Université de Lyon : 2018 Organisme de stage : LIRIS nature-HAL : Thèse DOI : sans En ligne : https://hal.science/tel-01865020 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96466