Centre dedocumentation
scientifique

Classification of hyperspectral and LiDAR data using coupled CNNs / Renlong Hang in IEEE Transactions on geoscience and remote sensing, vol 58 n° 7 (July 2020)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 58 n° 7 (July 2020) . - pp 4939 - 4950 Titre : Classification of hyperspectral and LiDAR data using coupled CNNs Type de document : Article/Communication Auteurs : Renlong Hang, Auteur ; Zhu Li, Auteur ; Pedram Ghamisi, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 4939 - 4950 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] données hétérogènes [Termes descripteurs IGN] données lidar [Termes descripteurs IGN] extraction de traits caractéristiques [Termes descripteurs IGN] fusion de données [Termes descripteurs IGN] Houston (Texas) [Termes descripteurs IGN] image hyperspectrale [Termes descripteurs IGN] occupation du sol [Termes descripteurs IGN] Perceptron multicouche [Termes descripteurs IGN] précision de la classification [Termes descripteurs IGN] semis de points [Termes descripteurs IGN] Trente [Termes descripteurs IGN] utilisation du sol Résumé : (auteur) In this article, we propose an efficient and effective framework to fuse hyperspectral and light detection and ranging (LiDAR) data using two coupled convolutional neural networks (CNNs). One CNN is designed to learn spectral–spatial features from hyperspectral data, and the other one is used to capture the elevation information from LiDAR data. Both of them consist of three convolutional layers, and the last two convolutional layers are coupled together via a parameter-sharing strategy. In the fusion phase, feature-level and decision-level fusion methods are simultaneously used to integrate these heterogeneous features sufficiently. For the feature-level fusion, three different fusion strategies are evaluated, including the concatenation strategy, the maximization strategy, and the summation strategy. For the decision-level fusion, a weighted summation strategy is adopted, where the weights are determined by the classification accuracy of each output. The proposed model is evaluated on an urban data set acquired over Houston, USA, and a rural one captured over Trento, Italy. On the Houston data, our model can achieve a new record overall accuracy (OA) of 96.03%. On the Trento data, it achieves an OA of 99.12%. These results sufficiently certify the effectiveness of our proposed model. Numéro de notice : A2020-391 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2020.2969024 date de publication en ligne : 06/02/2020 En ligne : https://doi.org/10.1109/TGRS.2020.2969024 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95374 [article]

Comparison of spatial modelling approaches to simulate urban growth: a case study on Udaipur city, India / Biswajit Mondal in Geocarto international, vol 35 n° 4 ([15/03/2020])  

Public [article]  inGeocarto international > vol 35 n° 4 [15/03/2020] . - pp 411 - 433 Titre : Comparison of spatial modelling approaches to simulate urban growth: a case study on Udaipur city, India Type de document : Article/Communication Auteurs : Biswajit Mondal, Auteur ; Suman Chakraborti, Auteur ; Dipendra Nath Das, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 411 - 433 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes descripteurs IGN] analyse diachronique [Termes descripteurs IGN] analyse multicritère [Termes descripteurs IGN] automate cellulaire [Termes descripteurs IGN] chaîne de Markov [Termes descripteurs IGN] croissance urbaine [Termes descripteurs IGN] étalement urbain [Termes descripteurs IGN] Inde [Termes descripteurs IGN] modèle de simulation [Termes descripteurs IGN] modélisation spatiale [Termes descripteurs IGN] pente [Termes descripteurs IGN] Perceptron multicouche [Termes descripteurs IGN] utilisation du sol Résumé : (auteur) Assessment of past and future urban growth processes helps the decision makers to evaluate and formulate the policy documents. In an attempt to make such assessments, this study compares three commonly used urban growth models: Multicriteria Cellular Automata-Markov Chain (MCCA-MC), Multi-Layer Perception Markov Chain (MLP-MC), and the Slope, Land use, Exclusion, Urban Extent, Transportation and Hillshade (SLEUTH). This study has taken into account the land use and land cover data for the years, 1977, 1992, 2000, 2008, 2016 and prepared driving variables for urban growth. The KAPPA index of agreement indicates that the MCCA-MC, MLP-MC and SLEUTH models avoid errors by 94%, 93%, and 92% respectively. Models forecast that about 156.96 km2, 157.43 km2 and 142.43 km2 built-up areas will emerge through the process of urbanization by 2031 in the city of Udaipur. However, this assessment identified that all the models are embodied with their own advantages and disadvantages while serving specific purposes. While the MCCA-MC and MLP-MC provides a good account of the urban spread, the SLEUTH identifies the new isolated growth centres more accurately. Numéro de notice : A2020-100 Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2018.1520922 date de publication en ligne : 03/01/2019 En ligne : https://doi.org/10.1080/10106049.2018.1520922 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94691 [article]

Spatially constrained regionalization with multilayer perceptron / Michael Govorov in Transactions in GIS, Vol 23 n° 5 (October 2019)  

Public [article]  inTransactions in GIS > Vol 23 n° 5 (October 2019) . - pp 1048 - 1077 Titre : Spatially constrained regionalization with multilayer perceptron Type de document : Article/Communication Auteurs : Michael Govorov, Auteur ; Giedre Beconyte, Auteur ; Gennady Gienko, Auteur ; Victor Putrenko, Auteur Année de publication : 2019 Article en page(s) : pp 1048 - 1077 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes descripteurs IGN] analyse de groupement [Termes descripteurs IGN] apprentissage automatique [Termes descripteurs IGN] classification dirigée [Termes descripteurs IGN] données géologiques [Termes descripteurs IGN] Perceptron multicouche [Termes descripteurs IGN] programmation par contraintes [Termes descripteurs IGN] régionalisation [Termes descripteurs IGN] réseau neuronal artificiel [Termes descripteurs IGN] segmentation par graphes d'adjacence de régions [Termes descripteurs IGN] Ukraine [Termes descripteurs IGN] uranium Résumé : (auteur) In this article, multilayer perceptron (MLP) network models with spatial constraints are proposed for regionalization of geostatistical point data based on multivariate homogeneity measures. The study focuses on non stationarity and autocorrelation in spatial data. Supervised MLP machine learning algorithms with spatial constraints have been implemented and tested on a point dataset. MLP spatially weighted classification models and an MLP contiguity constrained classification model are developed to conduct spatially constrained regionalization. The proposed methods have been tested with an attribute‐rich point dataset of geological surveys in Ukraine. The experiments show that consideration of the spatial effects, such as the use of spatial attributes and their respective whitening, improve the output of regionalization. It is also shown that spatial sorting used to preserve spatial contiguity leads to improved regionalization performance. Numéro de notice : A2019-552 Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/tgis.12557 date de publication en ligne : 09/07/2019 En ligne : https://doi.org/10.1111/tgis.12557 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94202 [article]

Soil roughness retrieval from TerraSar-X data using neural network and fractal method / Mohammad Maleki in Advances in space research, vol 64 n°5 (1 September 2019)  

Public [article]  inAdvances in space research > vol 64 n°5 (1 September 2019) . - pp 1117-1129 Titre : Soil roughness retrieval from TerraSar-X data using neural network and fractal method Type de document : Article/Communication Auteurs : Mohammad Maleki, Auteur ; Jalal Amini, Auteur ; Claudia Notarnicola, Auteur Année de publication : 2019 Article en page(s) : pp 1117-1129 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes descripteurs IGN] analyse fractale [Termes descripteurs IGN] bande X [Termes descripteurs IGN] équation intégrale [Termes descripteurs IGN] image TerraSAR-X [Termes descripteurs IGN] modèle d'inversion [Termes descripteurs IGN] modèle numérique de terrain [Termes descripteurs IGN] Perceptron multicouche [Termes descripteurs IGN] polarimétrie radar [Termes descripteurs IGN] rugosité du sol Résumé : (auteur) The purpose of this study is to estimate the surface roughness (rms) using TerraSar-X data in HH polarization. Simulation of data is carried out at a wide range of moisture and roughness using the Integral Equation Model (IEM). The inversion method is based on Multi-Layer Perceptron neural network. Inversion technique is performed in two steps. In the first step, the neural network is trained using synthetic data. The inputs of the first neural network are the backscattering coefficient and incidence angle, and the moisture is the output. In the next step, three neural networks are built based on a prior and without prior information on roughness. The inputs of three neural network are backscattering coefficient, estimated moisture in the first step and incidence angle and the roughness is output. The validation of the proposed methods is carried out based on synthetic and real data. Ground roughness measurements are extracted from Digital Terrain Model (DTM) using the fractal method. The accuracy of moisture from synthetic data is 6.1 vol% without prior information on moisture and roughness. The roughness (rms) accuracy of synthetic datasets is 0. 61 cm without prior information and is 0.31 cm and 0.38 cm for rms lower than 2 cm and rms between 2 and 4 cm, with prior information on roughness. The result's analysis of the simulated data showed that the prior information on roughness strongly improves the accuracy of roughness and moisture estimates. The accuracy of rms estimates for the TerraSar-X image in the HH polarization is about 0.9 cm in the case of no prior information on roughness. The accuracy improves to 0.57 cm for rms lower than 2 cm and 0.54 cm for rms between 2 and 4 cm with prior information on roughness. An overestimation of rms for rms lower than 2 cm and an underestimation of rms for rms higher than 2 cm are observed. The results of the accuracy of the synthetic and real data showed that the X band in HH polarization has a very good potential to estimate the soil roughness. Numéro de notice : A2019-411 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.asr.2019.04.019 date de publication en ligne : 24/04/2019 En ligne : https://doi.org/10.1016/j.asr.2019.04.019 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93527 [article]

Using LiDAR-modified topographic wetness index, terrain attributes with leaf area index to improve a single-tree growth model in south-eastern Finland / Cheikh Mohamedou in Forestry, an international journal of forest research, vol 92 n° 3 (July 2019)  

Public [article]  inForestry, an international journal of forest research > vol 92 n° 3 (July 2019) . - pp 253 - 263 Titre : Using LiDAR-modified topographic wetness index, terrain attributes with leaf area index to improve a single-tree growth model in south-eastern Finland Type de document : Article/Communication Auteurs : Cheikh Mohamedou, Auteur ; Lauri Korhonen, Auteur ; Kalle Eerikäinen, Auteur ; Timo Tokola, Auteur Année de publication : 2019 Article en page(s) : pp 253 - 263 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes descripteurs IGN] croissance végétale [Termes descripteurs IGN] diamètre des arbres [Termes descripteurs IGN] données lidar [Termes descripteurs IGN] données localisées 3D [Termes descripteurs IGN] erreur systématique [Termes descripteurs IGN] Finlande [Termes descripteurs IGN] humidité du sol [Termes descripteurs IGN] indice d'humidité [Termes descripteurs IGN] Leaf Area Index [Termes descripteurs IGN] modèle de croissance [Termes descripteurs IGN] Perceptron multicouche Résumé : (Auteur) Tree growth information is crucial in forest management and planning. Terrain-derived attributes such as the topographic wetness index (TWI), in addition to leaf area index (LAI) are closely related to tree growth, but are not commonly used in empirical growth models. In this study, we examined if modified TWI and LAI estimated from airborne light detection and ranging (LiDAR) data could be used to improve the predictions of a national single-tree diameter growth model. Altogether 1118 sample trees were selected within 197 subjectively placed plots in randomly selected forest stands in south-eastern Finland. Linear mixed effect (LME) and multilayer perceptron models were used to model the bias of 5-year growth predictions of the model and thus ultimately improve its predictions. The root mean square error (RMSE) of the national model was 0.604 cm. LME modelling reduced this value to 0.404 cm and MLP to 0.568 cm. The predictors included in the best-performing LME model were modified TWI, LAI estimated from LiDAR intensities, and elevation. Without an LAI estimate, the best RMSE was 0.436 cm. When applied as such, original and modified TWIs produced similar accuracy. We conclude that both TWI and LAI obtained from LiDAR data improve the diameter growth predictions of the national model. Numéro de notice : A2019-293 Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1093/forestry/cpz010 date de publication en ligne : 28/02/2019 En ligne : https://doi.org/10.1093/forestry/cpz010 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93184 [article]

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

Permalink

Challenges in grassland mowing event detection with multimodal Sentinel images / Anatol Garioud (2019)  

Permalink

Foundations of deep convolutional models through kernel methods / Alberto Bietti (2019)  

Permalink

Designing an integrated urban growth prediction model: a scenario-based approach for preserving scenic landscapes / Sepideh Saeidi in Geocarto international, vol 33 n° 12 (December 2018)  

Permalink

A 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)  

Permalink

Introduction to Deep Learning / Sandro Skansi (2018)  

Permalink

Multilayer projective dictionary pair learning and sparse autoencoder for PolSAR image classification / Yanqiao Chen in IEEE Transactions on geoscience and remote sensing, vol 55 n° 12 (December 2017)  

Permalink

Atmospheric correction over coastal waters using multilayer neural networks / Yongzhen Fan in Remote sensing of environment, vol 199 (15 September 2017)  

Permalink

A relative evaluation of random forests for land cover mapping in an urban area / Di Shi in Photogrammetric Engineering & Remote Sensing, PERS, vol 83 n° 8 (August 2017)  

Permalink

Artificial neural networks in geospatial analysis / Sucharita Gopal (2017)  

Permalink