Centre dedocumentation
scientifique

A deep translation (GAN) based change detection network for optical and SAR remote sensing images / Xinghua Li in ISPRS Journal of photogrammetry and remote sensing, vol 179 (September 2021)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 179 (September 2021) . - pp 14 - 34 Titre : A deep translation (GAN) based change detection network for optical and SAR remote sensing images Type de document : Article/Communication Auteurs : Xinghua Li, Auteur ; Zhengshun Du, Auteur ; Yanyuan Huang, Auteur ; Zhenyu Tan, Auteur Année de publication : 2021 Article en page(s) : pp 14 - 34 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image mixte [Termes IGN] détection de changement [Termes IGN] image à très haute résolution [Termes IGN] image optique [Termes IGN] image radar moirée [Termes IGN] image Sentinel-SAR [Termes IGN] méthode robuste [Termes IGN] polarisation [Termes IGN] réseau antagoniste génératif [Termes IGN] réseau neuronal profond [Termes IGN] zone d'intérêt Résumé : (Editeur) With the development of space-based imaging technology, a larger and larger number of images with different modalities and resolutions are available. The optical images reflect the abundant spectral information and geometric shape of ground objects, whose qualities are degraded easily in poor atmospheric conditions. Although synthetic aperture radar (SAR) images cannot provide the spectral features of the region of interest (ROI), they can capture all-weather and all-time polarization information. In nature, optical and SAR images encapsulate lots of complementary information, which is of great significance for change detection (CD) in poor weather situations. However, due to the difference in imaging mechanisms of optical and SAR images, it is difficult to conduct their CD directly using the traditional difference or ratio algorithms. Most recent CD methods bring image translation to reduce their difference, but the results are obtained by ordinary algebraic methods and threshold segmentation with limited accuracy. Towards this end, this work proposes a deep translation based change detection network (DTCDN) for optical and SAR images. The deep translation firstly maps images from one domain (e.g., optical) to another domain (e.g., SAR) through a cyclic structure into the same feature space. With the similar characteristics after deep translation, they become comparable. Different from most previous researches, the translation results are imported to a supervised CD network that utilizes deep context features to separate the unchanged pixels and changed pixels. In the experiments, the proposed DTCDN was tested on four representative data sets from Gloucester, California, and Shuguang village. Compared with state-of-the-art methods, the effectiveness and robustness of the proposed method were confirmed. Numéro de notice : A2021-574 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2021.07.007 date de publication en ligne : 23/07/2021 En ligne : https://doi.org/10.1016/j.isprsjprs.2021.07.007 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98174 [article]

Two hidden layer neural network-based rotation forest ensemble for hyperspectral image classification / Laxmi Narayana Eeti in Geocarto international, vol 36 n° 16 ([17/08/2021])  

Public [article]  inGeocarto international > vol 36 n° 16 [17/08/2021] . - pp 1820 - 1837 Titre : Two hidden layer neural network-based rotation forest ensemble for hyperspectral image classification Type de document : Article/Communication Auteurs : Laxmi Narayana Eeti, Auteur ; Krishna Mohan Buddhiraju, Auteur Année de publication : 2021 Article en page(s) : pp 1820 - 1837 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] arbre de décision [Termes IGN] bagging [Termes IGN] classification par forêts aléatoires [Termes IGN] image AVIRIS [Termes IGN] image EO1-Hyperion [Termes IGN] image hyperspectrale [Termes IGN] image ROSIS [Termes IGN] Perceptron multicouche [Termes IGN] précision de la classification [Termes IGN] réseau neuronal profond [Termes IGN] Rotation Forest classification Résumé : (auteur) Decision tree-based Rotation Forest could generate satisfactory but lower classification accuracy for a given training sample set and image data, owing to the inherent disadvantages in decision trees, namely myopic, replication and fragmentation problem. To improve performance of Rotation Forest technique, we propose to utilize two-hidden-layered-feedforward neural network as base classifier instead of decision tree. We examine the classification performance of proposed model under two situations, namely when free network parameters are maintained the same across all ensemble components and otherwise. The proposed model, where each component is initialized with different pair of initial weights and bias, performs better than decision tree-based Rotation Forest on three different Hyperspectral sensor datasets – AVIRIS, ROSIS and Hyperion. Improvements in classification accuracy are above 2% and up to 3% depending upon dataset. Also, the proposed model achieves improvement in accuracy over Random Forest in the range 4.2–8.8%. Numéro de notice : A2021-581 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2019.1678680 date de publication en ligne : 21/10/2019 En ligne : https://doi.org/10.1080/10106049.2019.1678680 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98193 [article]

Simulating multi-exit evacuation using deep reinforcement learning / Dong Xu in Transactions in GIS, Vol 25 n° 3 (June 2021)  

Public [article]  inTransactions in GIS > Vol 25 n° 3 (June 2021) . - pp 1542-1564 Titre : Simulating multi-exit evacuation using deep reinforcement learning Type de document : Article/Communication Auteurs : Dong Xu, Auteur ; Xiao Huang, Auteur ; Joseph Mango, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 1542-1564 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] analyse comparative [Termes IGN] apprentissage par renforcement [Termes IGN] distribution spatiale [Termes IGN] itinéraire piétionnier [Termes IGN] modèle de simulation [Termes IGN] réseau neuronal profond Résumé : (Auteur) Conventional simulations on multi-exit indoor evacuation focus primarily on how to determine a reasonable exit based on numerous factors in a changing environment. Results commonly include some congested and other under-utilized exits, especially with large numbers of pedestrians. We propose a multi-exit evacuation simulation based on deep reinforcement learning (DRL), referred to as the MultiExit-DRL, which involves a deep neural network (DNN) framework to facilitate state-to-action mapping. The DNN framework applies Rainbow Deep Q-Network (DQN), a DRL algorithm that integrates several advanced DQN methods, to improve data utilization and algorithm stability and further divides the action space into eight isometric directions for possible pedestrian choices. We compare MultiExit-DRL with two conventional multi-exit evacuation simulation models in three separate scenarios: varying pedestrian distribution ratios; varying exit width ratios; and varying open schedules for an exit. The results show that MultiExit-DRL presents great learning efficiency while reducing the total number of evacuation frames in all designed experiments. In addition, the integration of DRL allows pedestrians to explore other potential exits and helps determine optimal directions, leading to a high efficiency of exit utilization. Numéro de notice : A2021-466 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/INFORMATIQUE Nature : Numéro de périodique nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/tgis.12738 date de publication en ligne : 11/03/2021 En ligne : https://doi.org/10.1111/tgis.12738 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98085 [article]

Exploration of reinforcement learning algorithms for autonomous vehicle visual perception and control / Florence Carton (2021)  

Public Titre : Exploration of reinforcement learning algorithms for autonomous vehicle visual perception and control Titre original : Exploration des algorithmes d'apprentissage par renforcement pour la perception et le controle d'un véhicule autonome par vision Type de document : Thèse/HDR Auteurs : Florence Carton, Auteur ; David Filliat, Directeur de thèse Editeur : Paris : Ecole Nationale Supérieure des Techniques Avancées ENSTA Année de publication : 2021 Importance : 173 p. Format : 21 x 30 cm Note générale : bibliographie Thèse de Doctorat de l’Institut Polytechnique de Paris, Spécialité : Informatique, Données, IA Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Intelligence artificielle [Termes IGN] apprentissage par renforcement [Termes IGN] classification dirigée [Termes IGN] instrument embarqué [Termes IGN] navigation autonome [Termes IGN] reconnaissance de formes [Termes IGN] réseau neuronal profond [Termes IGN] robot mobile [Termes IGN] segmentation sémantique [Termes IGN] vision par ordinateur Index. décimale : THESE Thèses et HDR Résumé : (auteur) Reinforcement learning is an approach to solve a sequential decision making problem. In this formalism, an autonomous agent interacts with an environment and receives rewards based on the decisions it makes. The goal of the agent is to maximize the total amount of rewards it receives. In the reinforcement learning paradigm, the agent learns by trial and error the policy (sequence of actions) that yields the best rewards.In this thesis, we focus on its application to the perception and control of an autonomous vehicle. To stay close to human driving, only the onboard camera is used as input sensor. We focus in particular on end-to-end training, i.e. a direct mapping between information from the environment and the action chosen by the agent. However, training end-to-end reinforcement learning for autonomous driving poses some challenges: the large dimensions of the state and action spaces as well as the instability and weakness of the reinforcement learning signal to train deep neural networks.The approaches we implemented are based on the use of semantic information (image segmentation). In particular, this work explores the joint training of semantic information and navigation.We show that these methods are promising and allow to overcome some limitations. On the one hand, combining segmentation supervised learning with navigation reinforcement learning improves the performance of the agent and its ability to generalize to an unknown environment. On the other hand, it enables to train an agent that will be more robust to unexpected events and able to make decisions limiting the risks.Experiments are conducted in simulation, and numerous comparisons with state of the art methods are made. Note de contenu : 1- Introduction 2- Supervised learning and reinforcement learning background 3- State of the art 4- End-to-end autonomous driving on circuit with reinforcement learning 5- From lane following to robust conditional driving 6- Exploration of methods to reduce overfit 7- Conclusion Numéro de notice : 28325 Affiliation des auteurs : non IGN Thématique : INFORMATIQUE Nature : Thèse étrangère Note de thèse : Thèse de Doctorat : Informatique, Données, IA : ENSTA : 2021 DOI : sans En ligne : https://tel.archives-ouvertes.fr/tel-03273748/document Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98363

Representing shape collections with alignment-aware linear models / Romain Loiseau (2021)  

Public Titre : Representing shape collections with alignment-aware linear models Type de document : Article/Communication Auteurs : Romain Loiseau, Auteur ; Tom Monnier, Auteur ; Loïc Landrieu , Auteur ; Mathieu Aubry, Auteur Editeur : Ithaca [New York - Etats-Unis] : ArXiv - Université Cornell Année de publication : 2021 Projets : READY3D / Landrieu, Loïc Importance : 17 p. Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] analyse de données [Termes IGN] apprentissage profond [Termes IGN] données localisées 3D [Termes IGN] modèle linéaire [Termes IGN] réseau neuronal profond [Termes IGN] segmentation [Termes IGN] semis de points [Termes IGN] transformation affine Résumé : (auteur) In this paper, we revisit the classical representation of 3D point clouds as linear shape models. Our key insight is to leverage deep learning to represent a collection of shapes as affine transformations of low-dimensional linear shape models. Each linear model is characterized by a shape prototype, a low-dimensional shape basis and two neural networks. The networks take as input a point cloud and predict the coordinates of a shape in the linear basis and the affine transformation which best approximate the input. Both linear models and neural networks are learned end-to-end using a single reconstruction loss. The main advantage of our approach is that, in contrast to many recent deep approaches which learn feature-based complex shape representations, our model is explicit and every operation occurs in 3D space. As a result, our linear shape models can be easily visualized and annotated, and failure cases can be visually understood. While our main goal is to introduce a compact and interpretable representation of shape collections, we show it leads to state of the art results for few-shot segmentation. Code and data are available at: https://romainloiseau.github.io/deep-linear-shapes Numéro de notice : P2021-005 Affiliation des auteurs : UGE-LaSTIG+Ext (2020- ) Thématique : INFORMATIQUE Nature : Preprint nature-HAL : Préprint DOI : sans date de publication en ligne : 03/09/2021 En ligne : https://arxiv.org/abs/2109.01605 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98385

A deep learning architecture for semantic address matching / Yue Lin in International journal of geographical information science IJGIS, vol 34 n° 3 (March 2020)  

Permalink

Volcano-seismic transfer learning and uncertainty quantification with bayesian neural networks / Angel Bueno in IEEE Transactions on geoscience and remote sensing, vol 58 n° 2 (February 2020)  

Permalink

Superpixel-enhanced deep neural forest for remote sensing image semantic segmentation / Li Mi in ISPRS Journal of photogrammetry and remote sensing, vol 159 (January 2020)  

Permalink

Torch-Points3D: A modular multi-task framework for reproducible deep learning on 3D point clouds / Thomas Chaton (2020)  

Permalink

Unsupervised Satellite Image Time Series Analysis using Deep Learning Techniques / Ekaterina Kalinicheva (2020)  

Permalink

Addressing overfitting on point cloud classification using Atrous XCRF / Hasan Asy’ari Arief in ISPRS Journal of photogrammetry and remote sensing, vol 155 (September 2019)  

Permalink

Application des algorithmes de Deep learning pour les images SAR / Luc Baudoux (2019) 

Permalink