Descripteur
Termes IGN > imagerie > image numérique > image optique > image multibande > image hyperspectrale
image hyperspectraleVoir aussi |
Documents disponibles dans cette catégorie (438)
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
Deep generative model for spatial–spectral unmixing with multiple endmember priors / Shuaikai Shi in IEEE Transactions on geoscience and remote sensing, vol 60 n° 4 (April 2022)
[article]
Titre : Deep generative model for spatial–spectral unmixing with multiple endmember priors Type de document : Article/Communication Auteurs : Shuaikai Shi, Auteur ; Lijun Zhang, Auteur ; Yoann Altmann, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 5527214 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] analyse de mélange spectral d’extrémités multiples
[Termes IGN] analyse linéaire des mélanges spectraux
[Termes IGN] apprentissage profond
[Termes IGN] attention (apprentissage automatique)
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] image hyperspectrale
[Termes IGN] réseau neuronal de graphesRésumé : (auteur) Spectral unmixing is an effective tool to mine information at the subpixel level from complex hyperspectral images. To consider the spatially correlated materials distributions in the scene, many algorithms unmix the data in a spatial–spectral fashion; however, existing models are usually unable to model spectral variability simultaneously. In this article, we present a variational autoencoder-based deep generative model for spatial–spectral unmixing (DGMSSU) with endmember variability, by linking the generated endmembers to the probability distributions of endmember bundles extracted from the hyperspectral imagery via discriminators. Besides the convolutional autoencoder-like architecture that can only model the spatial information within the regular patch inputs, DGMSSU is able to alternatively choose graph convolutional networks or self-attention mechanism modules to handle the irregular but more flexible data—superpixel. Experimental results on a simulated dataset, as well as two well-known real hyperspectral images, show the superiority of our proposed approach in comparison with other state-of-the-art spatial–spectral unmixing methods. Compared to the conventional unmixing methods that consider the endmember variability, our proposed model generates more accurate endmembers on each subimage by the adversarial training process. The codes of this work will be available at https://github.com/shuaikaishi/DGMSSU for the sake of reproducibility. Numéro de notice : A2022-380 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2022.3168712 Date de publication en ligne : 18/04/2022 En ligne : https://doi.org/10.1109/TGRS.2022.3168712 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100645
in IEEE Transactions on geoscience and remote sensing > vol 60 n° 4 (April 2022) . - n° 5527214[article]Meta-learning based hyperspectral target detection using siamese network / Yulei Wang in IEEE Transactions on geoscience and remote sensing, vol 60 n° 4 (April 2022)
[article]
Titre : Meta-learning based hyperspectral target detection using siamese network Type de document : Article/Communication Auteurs : Yulei Wang, Auteur ; Xi Chen, Auteur ; Fengchao Wang, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 5527913 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage profond
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] classification pixellaire
[Termes IGN] détection de cible
[Termes IGN] espace euclidien
[Termes IGN] filtrage numérique d'image
[Termes IGN] image hyperspectrale
[Termes IGN] réseau neuronal siamois
[Termes IGN] tripletRésumé : (auteur) When predicting data for which limited supervised information is available, hyperspectral target detection methods based on deep transfer learning expect that the network will not require considerable retraining to generalize to unfamiliar application contexts. Meta-learning is an effective and practical framework for solving this problem in deep learning. This article proposes a new meta-learning based hyperspectral target detection using Siamese network (MLSN). First, a deep residual convolution feature embedding module is designed to embed spectral vectors into the Euclidean feature space. Then, the triplet loss is used to learn the intraclass similarity and interclass dissimilarity between spectra in embedding feature space by using the known labeled source data on the designed three-channel Siamese network for meta-training. The learned meta-knowledge is updated with the prior target spectrum through a designed two-channel Siamese network to quickly adapt to the new detection task. It should be noted that the parameters and structure of the deep residual convolution embedding modules of each channel in the Siamese network are identical. Finally, the spatial information is combined, and the detection map of the two-channel Siamese network is processed by the guiding image filtering and morphological closing operation, and a final detection result is obtained. Based on the experimental analysis of six real hyperspectral image datasets, the proposed MLSN has shown its excellent comprehensive performance. Numéro de notice : A2022-381 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2022.3169970 Date de publication en ligne : 22/04/2022 En ligne : https://doi.org/10.1109/TGRS.2022.3169970 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100649
in IEEE Transactions on geoscience and remote sensing > vol 60 n° 4 (April 2022) . - n° 5527913[article]Aboveground biomass of salt-marsh vegetation in coastal wetlands: Sample expansion of in situ hyperspectral and Sentinel-2 data using a generative adversarial network / Chen Chen in Remote sensing of environment, vol 270 (March 2022)
[article]
Titre : Aboveground biomass of salt-marsh vegetation in coastal wetlands: Sample expansion of in situ hyperspectral and Sentinel-2 data using a generative adversarial network Type de document : Article/Communication Auteurs : Chen Chen, Auteur ; Yi Ma, Auteur ; Guangbo Ren, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 112885 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection
[Termes IGN] biomasse aérienne
[Termes IGN] carte d'occupation du sol
[Termes IGN] carte thématique
[Termes IGN] image hyperspectrale
[Termes IGN] image Sentinel-MSI
[Termes IGN] littoral
[Termes IGN] marais salant
[Termes IGN] réseau antagoniste génératifRésumé : (auteur) Coastal wetlands are main components of the “blue carbon” ecosystems in coastal zones. Salt-marsh biomass is especially important regarding climate-change mitigation. Generating high precision biomass maps for evaluating the ecological functions of coastal wetlands is essential; however, conducting accurate biomass inversions with limited in situ observations from coastal wetlands is challenging. We propose a generative adversarial network with a constrained factor model (GAN-CF) for expanding limited in situ salt-marsh biomass observations. We used Sentinel-2 images and a deep belief network based on the conjugate gradient method (CG-DBN) for obtaining land-cover maps and the salt-marsh distribution (species: Phragmites australis, Suaeda glauca, Spartina alterniflora, and mixed species dominated by Tamarix chinensis) in the study area. This study bridges in situ hyperspectral and Sentinel-2 multispectral data by a satellite-band equivalent conversion model. The biomass and multispectral data derived from Sentinel-2 were used as input for the proposed GAN-CF model, which produced and constrained the generated samples based on the features (i.e., spectra, vegetation index, and biomass) of the in situ observations. Aboveground biomass (AGB) maps at 10-m spatial resolution were produced by constructing multiple linear regression models (MLRMs) based on the generated samples of each salt-marsh type using Sentinel-2 images. The quantity and richness of the generated samples improved the AGB estimations in the study area. The inversion accuracy of S. alterniflora was significantly improved (RMSE = 3.71 Mg/ha); the estimated AGB was strongly related to the in situ observations (R = 0.923). The estimated AGB was validated using in situ observations. The total amount of salt-marsh AGB in the study area in 2019 was estimated at 2.36 × 105 Mg, with 7.95 Mg/ha average. The salt-marsh biomass in decreasing order was as follows: P. australis (12.7 Mg/ha) > S. alterniflora (11.5 Mg/ha) > mixed species (8.97 Mg/ha) > S. glauca (2.18 Mg/ha). The salt-marsh area in decreasing order was as follows: S. glauca (10,410 ha) > P. australis (7320 ha) > mixed species (6740 ha) > S. alterniflora (5240 ha). By a feasibility analysis we estimated the biomass based on the Sentinel-2 data covering the Yellow River delta wetland in May, July, and September 2019 and the Jiaozhou Bay wetland in September 2019 by using the generated samples. The generated samples based on the 2013–2019 in situ observations constitute a salt-marsh biomass database, which can be useful for quantifying the regional carbon storage and ecological restoration monitoring. Numéro de notice : A2022-128 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.rse.2021.112885 Date de publication en ligne : 07/01/2022 En ligne : https://doi.org/10.1016/j.rse.2021.112885 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99710
in Remote sensing of environment > vol 270 (March 2022) . - n° 112885[article]Probabilistic unsupervised classification for large-scale analysis of spectral imaging data / Emmanuel Paradis in International journal of applied Earth observation and geoinformation, vol 107 (March 2022)
[article]
Titre : Probabilistic unsupervised classification for large-scale analysis of spectral imaging data Type de document : Article/Communication Auteurs : Emmanuel Paradis, Auteur Année de publication : 2022 Article en page(s) : n° 102675 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] analyse de groupement
[Termes IGN] analyse spectrale
[Termes IGN] classification barycentrique
[Termes IGN] classification ISODATA
[Termes IGN] classification non dirigée
[Termes IGN] classification par nuées dynamiques
[Termes IGN] classification par séparateurs à vaste marge
[Termes IGN] détection de changement
[Termes IGN] entropie
[Termes IGN] image hyperspectrale
[Termes IGN] image multibande
[Termes IGN] Matlab
[Termes IGN] occupation du solRésumé : (auteur) Land cover classification of remote sensing data is a fundamental tool to study changes in the environment such as deforestation or wildfires. A current challenge is to quantify land cover changes with real-time, large-scale data from modern hyper- or multispectral sensors. A range of methods are available for this task, several of them being based on the k-means classification method which is efficient when classes of land cover are well separated. Here a new algorithm, called probabilistic k-means, is presented to solve some of the limitations of the standard k-means. It is shown that the new algorithm performs better than the standard k-means when the data are noisy. If the number of land cover classes is unknown, an entropy-based criterion can be used to select the best number of classes. The proposed new algorithm is implemented in a combination of R and C computer codes which is particularly efficient with large data sets: a whole image with more than 3 million pixels and covering more than 10,000 km2 can be analysed in a few minutes. Four applications with hyperspectral and multispectral data are presented. For the data sets with ground truth data, the overall accuracy of the probabilistic k-means was substantially improved compared to the standard k-means. One of these data sets includes more than 120 million pixels, demonstrating the scalability of the proposed approach. These developments open new perspectives for the large scale analysis of remote sensing data. All computer code are available in an open-source package called sentinel. Numéro de notice : A2022-193 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.jag.2022.102675 Date de publication en ligne : 06/01/2022 En ligne : https://doi.org/10.1016/j.jag.2022.102675 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99954
in International journal of applied Earth observation and geoinformation > vol 107 (March 2022) . - n° 102675[article]Decision fusion of deep learning and shallow learning for marine oil spill detection / Junfang Yang in Remote sensing, vol 14 n° 3 (February-1 2022)
[article]
Titre : Decision fusion of deep learning and shallow learning for marine oil spill detection Type de document : Article/Communication Auteurs : Junfang Yang, Auteur ; Yi Ma, Auteur ; Yabin Hu, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 666 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] algorithme de fusion
[Termes IGN] analyse multiéchelle
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] classification par séparateurs à vaste marge
[Termes IGN] hydrocarbure
[Termes IGN] image hyperspectrale
[Termes IGN] marée noire
[Termes IGN] milieu marin
[Termes IGN] pollution des mers
[Termes IGN] précision de la classification
[Termes IGN] sous ensemble flou
[Termes IGN] surveillance écologique
[Termes IGN] transformation en ondelettesRésumé : (auteur) Marine oil spills are an emergency of great harm and have become a hot topic in marine environmental monitoring research. Optical remote sensing is an important means to monitor marine oil spills. Clouds, weather, and light control the amount of available data, which often limit feature characterization using a single classifier and therefore difficult to accurate monitoring of marine oil spills. In this paper, we develop a decision fusion algorithm to integrate deep learning methods and shallow learning methods based on multi-scale features for improving oil spill detection accuracy in the case of limited samples. Based on the multi-scale features after wavelet transform, two deep learning methods and two classical shallow learning algorithms are used to extract oil slick information from hyperspectral oil spill images. The decision fusion algorithm based on fuzzy membership degree is introduced to fuse multi-source oil spill information. The research shows that oil spill detection accuracy using the decision fusion algorithm is higher than that of the single detection algorithms. It is worth noting that oil spill detection accuracy is affected by different scale features. The decision fusion algorithm under the first-level scale features can further improve the accuracy of oil spill detection. The overall classification accuracy of the proposed method is 91.93%, which is 2.03%, 2.15%, 1.32%, and 0.43% higher than that of SVM, DBN, 1D-CNN, and MRF-CNN algorithms, respectively. Numéro de notice : A2022-125 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.3390/rs14030666 Date de publication en ligne : 30/01/2022 En ligne : https://doi.org/10.3390/rs14030666 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99688
in Remote sensing > vol 14 n° 3 (February-1 2022) . - n° 666[article]Detection and biomass estimation of phaeocystis globosa blooms off Southern China from UAV-based hyperspectral measurements / Xue Li in IEEE Transactions on geoscience and remote sensing, vol 60 n° 1 (January 2022)PermalinkPermalinkFusion de données hyperspectrales et panchromatiques dans le domaine réflectif / Yohann Constans (2022)PermalinkGlobal and climate challenges, graph-based data analysis for multisource information extraction / Morgane Batelier (2022)PermalinkA novel unmixing-based hypersharpening method via convolutional neural network / Xiaochen Lu in IEEE Transactions on geoscience and remote sensing, vol 60 n° 1 (January 2022)PermalinkPreparation of the VENµS satellite data over Israel for the input into the GRASP data treatment algorithm / Maeve Blarel (2022)PermalinkSelf-attention and generative adversarial networks for algae monitoring / Nhut Hai Huynh in European journal of remote sensing, vol 55 n° 1 (2022)PermalinkEarly detection of spruce vitality loss with hyperspectral data: Results of an experimental study in Bavaria, Germany / Kathrin Einzmann in Remote sensing of environment, vol 266 (December 2021)PermalinkFlexible Gabor-based superpixel-level unsupervised LDA for hyperspectral image classification / Sen Jia in IEEE Transactions on geoscience and remote sensing, vol 59 n° 12 (December 2021)PermalinkBagging and boosting ensemble classifiers for classification of multispectral, hyperspectral and PolSAR data: A comparative evaluation / Hamid Jafarzadeh in Remote sensing, vol 13 n° 21 (November-1 2021)Permalink