Centre dedocumentation
scientifique

Dépouillements

Graph learning based on signal smoothness representation for homogeneous and heterogeneous change detection / David Alejandro Jimenez-Sierra in IEEE Transactions on geoscience and remote sensing, vol 60 n° 4 (April 2022)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 60 n° 4 (April 2022) . - n° 4410416 Titre : Graph learning based on signal smoothness representation for homogeneous and heterogeneous change detection Type de document : Article/Communication Auteurs : David Alejandro Jimenez-Sierra, Auteur ; David Alfredo Quintero-Olaya, Auteur ; Juan Carlos Alvear-Muñoz, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 4410416 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image mixte [Termes IGN] apprentissage non-dirigé [Termes IGN] apprentissage profond [Termes IGN] détection de changement [Termes IGN] graphe [Termes IGN] image multibande [Termes IGN] image radar moirée [Termes IGN] Kappa de Cohen [Termes IGN] lissage de données [Termes IGN] processus gaussien [Termes IGN] réseau sémantique [Termes IGN] segmentation d'image [Termes IGN] seuillage [Termes IGN] superpixel Résumé : (auteur) Graph-based methods are promising approaches for traditional and modern techniques in change detection (CD) applications. Nonetheless, some graph-based approaches omit the existence of useful priors that account for the structure of a scene, and the inter- and intra-relationships between the pixels are analyzed. To address this issue, in this article, we propose a framework for CD based on graph fusion and driven by graph signal smoothness representation. In addition to modifying the graph learning stage, in the proposed model, we apply a Gaussian mixture model for superpixel segmentation (GMMSP) as a downsampling module to reduce the computational cost required to learn the graph of the entire images. We carry out tests on 14 real cases of natural disasters, farming, and construction. The dataset contains homogeneous cases with multispectral (MS) and synthetic aperture radar (SAR) images, along with heterogeneous cases that include MS/SAR images. We compare our approach against probabilistic thresholding, unsupervised learning, deep learning, and graph-based methods. In terms of Cohen’s kappa coefficient, our proposed model based on graph signal smoothness representation outperformed state-of-the-art approaches in ten out of 14 datasets. Numéro de notice : A2022-379 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2022.3168126 Date de publication en ligne : 18/04/2022 En ligne : https://doi.org/10.1109/TGRS.2022.3168126 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100643 [article]

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)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 60 n° 4 (April 2022) . - n° 5527214 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 graphes Résumé : (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 [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)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 60 n° 4 (April 2022) . - n° 5527913 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] triplet Résumé : (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 [article]