Descripteur
Termes IGN > mathématiques > statistique mathématique > analyse de données > classification > classification par réseau neuronal
classification par réseau neuronalVoir aussi |
Documents disponibles dans cette catégorie (434)
Ajouter le résultat dans votre panier
Visionner les documents numériques
Affiner la recherche Interroger des sources externes
Etendre la recherche sur niveau(x) vers le bas
Titre : Foundations of deep convolutional models through kernel methods Type de document : Thèse/HDR Auteurs : Alberto Bietti, Auteur ; Julien Mairal, Directeur de thèse Editeur : Grenoble : Université de Grenoble Année de publication : 2019 Importance : 194 p. Format : 21 x 30 cm Note générale : bibliographie
Thèse pour obtenir le grade de Docteur de la Communauté Université Grenoble Alpes, Spécialité : Mathématiques AppliquéesLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Intelligence artificielle
[Termes IGN] apprentissage automatique
[Termes IGN] apprentissage profond
[Termes IGN] approche hiérarchique
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] espace de Hilbert
[Termes IGN] état de l'art
[Termes IGN] invariance
[Termes IGN] jeu de données
[Termes IGN] méthode fondée sur le noyau
[Termes IGN] optimisation (mathématiques)
[Termes IGN] Perceptron multicoucheIndex. décimale : THESE Thèses et HDR Résumé : (auteur) The increased availability of large amounts of data, from images in social networks, speech waveforms from mobile devices, and large text corpuses, to genomic and medical data, has led to a surge of machine learning techniques. Such methods exploit statistical patterns in these large datasets for making accurate predictions on new data. In recent years, deep learning systems have emerged as a remarkably successful class of machine learning algorithms, which rely on gradient-based methods for training multi-layer models that process data in a hierarchical manner. These methods have been particularly successful in tasks where the data consists of natural signals such as images or audio; this includes visual recognition, object detection or segmentation, and speech recognition.For such tasks, deep learning methods often yield the best known empirical performance; yet, the high dimensionality of the data and large number of parameters of these models make them challenging to understand theoretically. Their success is often attributed in part to their ability to exploit useful structure in natural signals, such as local stationarity or invariance, for instance through choices of network architectures with convolution and pooling operations. However, such properties are still poorly understood from a theoretical standpoint, leading to a growing gap between the theory and practice of machine learning. This thesis is aimed towards bridging this gap, by studying spaces of functions which arise from given network architectures, with a focus on the convolutional case. Our study relies on kernel methods, by considering reproducing kernel Hilbert spaces (RKHSs) associated to certain kernels that are constructed hierarchically based on a given architecture. This allows us to precisely study smoothness, invariance, stability to deformations, and approximation properties of functions in the RKHS. These representation properties are also linked with optimization questions when training deep networks with gradient methods in some over-parameterized regimes where such kernels arise. They also suggest new practical regularization strategies for obtaining better generalization performance on small datasets, and state-of-the-art performance for adversarial robustness on image tasks. Note de contenu : 1- Introduction
2- Invariance, Stability to deformations, and complexity of deep convolutional representations
3- A kernel perspective on regularization and robustness of deep neural networks
4- Links with optimization: inductive bias of neural tangent kernels
5- Invariance and stability through regularization: a stochastic optimization algorithm for data augmentation
6- Conclusion and perspectivesNuméro de notice : 25833 Affiliation des auteurs : non IGN Thématique : INFORMATIQUE/MATHEMATIQUE Nature : Thèse française Note de thèse : Thèse de Doctorat : Mathématiques Appliquées : Grenoble Alpes : 2019 nature-HAL : Thèse DOI : sans En ligne : https://hal.archives-ouvertes.fr/tel-02543073/ document Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95171 Joint analysis of SAR and optical satellite images time series for grassland event detection / Anatol Garioud (2019)
Titre : Joint analysis of SAR and optical satellite images time series for grassland event detection Type de document : Article/Communication Auteurs : Anatol Garioud , Auteur ; Silvia Valero, Auteur ; Sébastien Giordano , Auteur ; Clément Mallet , Auteur Editeur : Leibniz : Leibniz Institute of Ecological Urban and Regional Development Année de publication : 2019 Conférence : ILUS 2019, 3rd International land use symposium, Land use changes: Trends and projections 04/12/2019 06/12/2019 Paris France programme sans actes Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image mixte
[Termes IGN] analyse d'image orientée objet
[Termes IGN] classification par réseau neuronal
[Termes IGN] cohérence des données
[Termes IGN] détection d'événement
[Termes IGN] détection de changement
[Termes IGN] image optique
[Termes IGN] image radar moirée
[Termes IGN] image Sentinel-MSI
[Termes IGN] image Sentinel-SAR
[Termes IGN] Mâcon
[Termes IGN] prairie
[Termes IGN] puits de carboneRésumé : (auteur) Throughout Europe, grasslands are a major component of the landscape comprising 40% of agricultural land. Permanent Grassland (PM) means land used to grow herbaceous forage crops naturally (self-seeded) or through cultivation (sown) and that has not been included in the crop rotation of the holding for five years or more. PM are major ecosystems associated with high biodiversity which provide a wide range of ecosystem services (e.g. carbon sequestration, water quality, flood and erosion control). Grasslands have an important carbon storage capacity which is valuable for climate protection. Different studies have demonstrated that grassland managements such as grazing or mowing can cause significant effects on carbon storage in soils. Identifying and mapping grassland management practices over time can thus have important impact on climate studies. Remote sensing allows a synoptic and regular monitoring through systematic acquisitions of Earth Observation imagery. The emergence of free and easily Sentinel's satellite data provided by the European Copernicus program, offers new possibilities for grassland monitoring. Sentinel-1 (51) and Sentinel-2 (52) missions acquire radar and optical satellite image time series at high temporal resolution and fine spatial resolution. They fully match the requirements both for yearly and real-time monitoring. In this work, we target to jointly exploit both data sources to dynamically detect mowing events (MowEve) on permanent grasslands. Thematic related analysis of the datasets will highlight strengths and weaknesses of both optical and radar imagery. (i) 52 appears efficient for MowEve detection, with significant variations in the vegetation status that can be easily detected in the spectral signal extracted from the time series of images. But the temporal revisit of 52 although nominally 5 days is often reduced even by half due to the frequent cloud cover (ii) SAR images acquisitions being independent of illumination conditions or cloud cover allows for systematic acquisitions and revisit rate of 6 days. Data consistency makes S1 data essential during fast phenomena such as MowEve. Yet, radar data appears very sensitive to soil moisture, precipitations and geometrical properties making interpretation of their time series more challenging. MowEve detection being weakly supervised, the proposed methodology relies on applying traditional change detection strategies on a low-level fused 51 and S2 data representation. Recurrent Neural Networks will be trained to derive yearly or real-time synthetic 52 vegetation indices from both 52 and S1 observations. Furthermore, through attention mechanisms, our proposed RNN architecture will be able to take into account external data (climate, clouds, topography, etc.) so as to dynamically weight at parcel-level the contribution of optical and radar images. Such method will contribute to obtain dense temporal optical profiles without missing data and compatible with MowEve detection. An experimental evaluation will be carried out on a test site covering an area of 110x110 Km in France (Macon region). Object-oriented analysis will be presented based on permanent grasslands derived from the Land Parcel Identification System. The proposed approach will be compared with traditional MowEve methods essentially based on thresholding independently the different modalities. Numéro de notice : C2019-067 Affiliation des auteurs : LASTIG MATIS+Ext (2012-2019) Thématique : IMAGERIE Nature : Communication nature-HAL : ComSansActesPubliés-Unpublished DOI : sans Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97022
Titre : Perspective-n-learned-point: pose estimation from relative depth Type de document : Article/Communication Auteurs : Nathan Piasco , Auteur ; Désiré Sidibé, Auteur ; Cédric Demonceaux, Auteur ; Valérie Gouet-Brunet , Auteur Editeur : Saint-Mandé : Institut national de l'information géographique et forestière - IGN (2012-) Année de publication : 2019 Projets : PLaTINUM / Gouet-Brunet, Valérie Conférence : BMVC 2019, British Machine Vision Conference 09/09/2019 12/09/2019 Cardiff Royaume-Uni OA Proceedings Importance : 15 p. Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] carte de profondeur
[Termes IGN] classification par réseau neuronal
[Termes IGN] estimation de pose
[Termes IGN] géométrie de l'image
[Termes IGN] recherche d'image basée sur le contenuRésumé : (Auteur) In this paper we present an online camera pose estimation method that combines Content-Based Image Retrieval (CBIR) and pose refinement based on a learned representation of the scene geometry extracted from monocular images. Our pose estimation method is two-step, we first retrieve an initial 6 Degrees of Freedom (DoF) location of an unknown-pose query by retrieving the most similar candidate in a pool of geo-referenced images. In a second time, we refine the query pose with a Perspective-n-Point (PnP) algorithm where the 3D points are obtained thanks to a generated depth map from the retrieved image candidate. We make our method fast and lightweight by using a common neural network architecture to generate the image descriptor for image indexing and the depth map used to create the 3D points required in the PnP pose refinement step. We demonstrate the effectiveness of our proposal through extensive experimentation on both indoor and outdoor scenes, as well as generalisation capability of our method to unknown environment. Finally, we show how to deploy our system even if geometric information is missing to train our monocular-image-to-depth neural networks. Numéro de notice : C2019-025 Affiliation des auteurs : LASTIG MATIS+Ext (2012-2019) Autre URL associée : vers HAL Thématique : IMAGERIE/INFORMATIQUE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : sans Date de publication en ligne : 12/11/2019 En ligne : https://bmvc2019.org/wp-content/uploads/papers/0981-paper.pdf Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94320 Documents numériques
en open access
Perspective-n-learned-point ... - pdf auteurAdobe Acrobat PDF Time-space tradeoff in deep learning models for crop classification on satellite multi-spectral image time series / Vivien Sainte Fare Garnot (2019)
Titre : Time-space tradeoff in deep learning models for crop classification on satellite multi-spectral image time series Type de document : Article/Communication Auteurs : Vivien Sainte Fare Garnot , Auteur ; Loïc Landrieu , Auteur ; Sébastien Giordano , Auteur ; Nesrine Chehata , Auteur Editeur : New York : Institute of Electrical and Electronics Engineers IEEE Année de publication : 2019 Projets : 1-Pas de projet / Gouet-Brunet, Valérie Conférence : IGARSS 2019, IEEE International Geoscience And Remote Sensing Symposium 28/07/2019 02/08/2019 Yokohama Japon Proceedings IEEE Importance : 4 p. Format : 21 x 30 cm Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage profond
[Termes IGN] classification par réseau neuronal
[Termes IGN] cultures
[Termes IGN] image Sentinel-MSI
[Termes IGN] série temporelleRésumé : (auteur) In this article, we investigate several structured deep learning models for crop type classification on multi-spectral time series. In particular, our aim is to assess the respective importance of spatial and temporal structures in such data. With this objective, we consider several designs of convolutional, recurrent, and hybrid neural networks, and assess their performance on a large dataset of freely available Sentinel-2 imagery. We find that the best-performing approaches are hybrid configurations for which most of the parameters (up to 90%) are allocated to modeling the temporal structure of the data. Our results thus constitute a set of guidelines for the design of bespoke deep learning models for crop type classification. Numéro de notice : C2019-018 Affiliation des auteurs : LASTIG MATIS+Ext (2012-2019) Autre URL associée : URL ArXiv Thématique : IMAGERIE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.1109/IGARSS.2019.8900517 Date de publication en ligne : 14/11/2019 En ligne : https://doi.org/10.1109/IGARSS.2019.8900517 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93352 Towards visual urban scene understanding for autonomous vehicle path tracking using GPS positioning data / Citlalli Gamez Serna (2019)
Titre : Towards visual urban scene understanding for autonomous vehicle path tracking using GPS positioning data Type de document : Thèse/HDR Auteurs : Citlalli Gamez Serna, Auteur ; Yassine Ruichek, Directeur de thèse Editeur : Dijon : Université Bourgogne Franche-Comté UBFC Année de publication : 2019 Importance : 178 p. Format : 21 x 30 cm Note générale : bibliographie
Thèse de Doctorat de l'Université Bourgogne Franche-Comté préparée à l'Université de Technologie de Belfort-Montbéliard, InformatiqueLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image
[Termes IGN] apprentissage profond
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] compréhension de l'image
[Termes IGN] instance
[Termes IGN] milieu urbain
[Termes IGN] navigation autonome
[Termes IGN] récepteur GPS
[Termes IGN] scène urbaine
[Termes IGN] segmentation sémantique
[Termes IGN] signalisation routière
[Termes IGN] système de transport intelligent
[Termes IGN] trajectoire (véhicule non spatial)
[Termes IGN] véhicule sans pilote
[Termes IGN] vision par ordinateur
[Termes IGN] vision stéréoscopique
[Termes IGN] vitesseMots-clés libres : suivi d'itinéraire Index. décimale : THESE Thèses et HDR Résumé : (auteur) This PhD thesis focuses on developing a path tracking approach based on visual perception and localization in urban environments. The proposed approach comprises two systems. The first one concerns environment perception. This task is carried out using deep learning techniques to automatically extract 2D visual features and use them to learn in order to distinguish the different objects in the driving scenarios. Three deep learning techniques are adopted: semantic segmentation to assign each image pixel to a class, instance segmentation to identify separated instances of the same class and, image classification to further recognize the specific labels of the instances. Here our system segments 15 object classes and performs traffic sign recognition. The second system refers to path tracking. In order to follow a path, the equipped vehicle first travels and records the route with a stereo vision system and a GPS receiver (learning step). The proposed system analyses off-line the GPS path and identifies exactly the locations of dangerous (sharp) curves and speed limits. Later after the vehicle is able to localize itself, the vehicle control module together with our speed negotiation algorithm, takes into account the information extracted and computes the ideal speed to execute. Through experimental results of both systems, we prove that, the first one is capable to detect and recognize precisely objects of interest in urban scenarios, while the path tracking one reduces significantly the lateral errors between the learned and traveled path. We argue that the fusion of both systems will ameliorate the tracking approach for preventing accidents or implementing autonomous driving. Note de contenu : I- Context and problems
1- Introduction
II- Contribution
2- Proposed datasets
3- Traffic sign classification
4- Visual perception system for urban environments
5- Dynamic speed adaptation system for path tracking based on curvature
information and speed limits
III- Conclusions and future works
6- Conclusions and future worksNuméro de notice : 25967 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Thèse française Note de thèse : Thèse de Doctorat : Informatique : UBFC : 2019 Organisme de stage : CIAD Dijon nature-HAL : Thèse DOI : sans En ligne : https://tel.archives-ouvertes.fr/tel-02160966/document Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96587 Vision-based localization with discriminative features from heterogeneous visual data / Nathan Piasco (2019)PermalinkRemote sensing scene classification using multilayer stacked covariance pooling / Nanjun He in IEEE Transactions on geoscience and remote sensing, vol 56 n° 12 (December 2018)PermalinkScene classification based on multiscale convolutional neural network / Yanfei Liu in IEEE Transactions on geoscience and remote sensing, vol 56 n° 12 (December 2018)PermalinkA new deep convolutional neural network for fast hyperspectral image classification / Mercedes Eugenia Paoletti in ISPRS Journal of photogrammetry and remote sensing, vol 145 - part A (November 2018)PermalinkPan-sharpening via deep metric learning / Yinghui Xing in ISPRS Journal of photogrammetry and remote sensing, vol 145 - part A (November 2018)PermalinkA 3D convolutional neural network method for land cover classification using LiDAR and multi-temporal Landsat imagery / Zewei Xu in ISPRS Journal of photogrammetry and remote sensing, vol 144 (October 2018)PermalinkEstimation of forest above-ground biomass by geographically weighted regression and machine learning with Sentinel imagery / Lin Chen in Forests, vol 9 n° 10 (October 2018)PermalinkFine-grained prediction of urban population using mobile phone location data / Jie Chen in International journal of geographical information science IJGIS, vol 32 n° 9-10 (September - October 2018)PermalinkA deep neural network with spatial pooling (DNNSP) for 3-D point cloud classification / Zhen Wang in IEEE Transactions on geoscience and remote sensing, vol 56 n° 8 (August 2018)PermalinkApplication of deep learning for object detection / Ajeet Ram Pathak in Procedia Computer Science, vol 132 (2018)PermalinkClassification à très large échelle d’images satellites à très haute résolution spatiale par réseaux de neurones convolutifs / Tristan Postadjian in Revue Française de Photogrammétrie et de Télédétection, n° 217-218 (juin - septembre 2018)PermalinkFusion tardive d’images SPOT 6/7 et de données multitemporelles Sentinel-2 pour la détection de la tache urbaine / Cyril Wendl in Revue Française de Photogrammétrie et de Télédétection, n° 217-218 (juin - septembre 2018)PermalinkMapping hourly dynamics of urban population using trajectories reconstructed from mobile phone records / Zhang Liu in Transactions in GIS, vol 22 n° 2 (April 2018)PermalinkExtraction of pluvial flood relevant volunteered geographic information (VGI) by deep learning from user generated texts and photos / Yu Feng in ISPRS International journal of geo-information, vol 7 n° 2 (February 2018)PermalinkLarge-scale remote sensing image retrieval by deep hashing neural networks / Yansheng Li in IEEE Transactions on geoscience and remote sensing, vol 56 n° 2 (February 2018)PermalinkMultisource remote sensing data classification based on convolutional neural network / Xiaodong Xu in IEEE Transactions on geoscience and remote sensing, vol 56 n° 2 (February 2018)PermalinkPermalinkClassification à très haute résolution (THR) spatiale et fusion d'occupation des sols (OCS) / Tristan Postadjian (2018)PermalinkClassification à très large échelle d'images satellite à très haute résolution spatiale par réseaux de neurones convolutifs / Tristan Postadjian (2018)PermalinkComparative study of visual saliency maps in the problem of classification of architectural images with Deep CNNs / Abraham Montoya Obeso (2018)Permalink