Centre de documentation
scientifique

Learning from multimodal and multitemporal earth observation data for building damage mapping / Bruno Adriano in ISPRS Journal of photogrammetry and remote sensing, vol 175 (May 2021)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 175 (May 2021) . - pp 132 - 143 Titre : Learning from multimodal and multitemporal earth observation data for building damage mapping Type de document : Article/Communication Auteurs : Bruno Adriano, Auteur ; Naoto Yokoya, Auteur ; Junshi Xia, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 132 - 143 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] apprentissage profond [Termes IGN] cartographie des risques [Termes IGN] catastrophe naturelle [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] cyclone [Termes IGN] dommage [Termes IGN] données multitemporelles [Termes IGN] image à haute résolution [Termes IGN] image optique [Termes IGN] image radar moirée [Termes IGN] observation de la Terre [Termes IGN] segmentation sémantique [Termes IGN] séisme [Termes IGN] surveillance d'ouvrage [Termes IGN] tsunami Résumé : (auteur) Earth observation (EO) technologies, such as optical imaging and synthetic aperture radar (SAR), provide excellent means to continuously monitor ever-growing urban environments. Notably, in the case of large-scale disasters (e.g., tsunamis and earthquakes), in which a response is highly time-critical, images from both data modalities can complement each other to accurately convey the full damage condition in the disaster aftermath. However, due to several factors, such as weather and satellite coverage, which data modality will be the first available for rapid disaster response efforts is often uncertain. Hence, novel methodologies that can utilize all accessible EO datasets are essential for disaster management. In this study, we developed a global multimodal and multitemporal dataset for building damage mapping. We included building damage characteristics from three disaster types, namely, earthquakes, tsunamis, and typhoons, and considered three building damage categories. The global dataset contains high-resolution (HR) optical imagery and high-to-moderate-resolution SAR data acquired before and after each disaster. Using this comprehensive dataset, we analyzed five data modality scenarios for damage mapping: single-mode (optical and SAR datasets), cross-modal (pre-disaster optical and post-disaster SAR datasets), and mode fusion scenarios. We defined a damage mapping framework for semantic segmentation of damaged buildings based on a deep convolutional neural network (CNN) algorithm. We also compared our approach to another state-of-the-art model for damage mapping. The results indicated that our dataset, together with a deep learning network, enabled acceptable predictions for all the data modality scenarios. We also found that the results from cross-modal mapping were comparable to the results obtained from a fusion sensor and optical mode analysis. Numéro de notice : A2021-272 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2021.02.016 Date de publication en ligne : 17/03/2021 En ligne : https://doi.org/10.1016/j.isprsjprs.2021.02.016 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97343 [article]

Exemplaires(3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2021051	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2021052	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt
081-2021053	DEP-RECP	Revue	Saint-Mandé	Dépôt en unité	Exclu du prêt

Tropical forest canopy height estimation from combined polarimetric SAR and LiDAR using machine-learning / Maryam Pourshamsi in ISPRS Journal of photogrammetry and remote sensing, vol 172 (February 2021)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 172 (February 2021) . - pp 79 - 94 Titre : Tropical forest canopy height estimation from combined polarimetric SAR and LiDAR using machine-learning Type de document : Article/Communication Auteurs : Maryam Pourshamsi, Auteur ; Junshi Xia, Auteur ; Naoto Yokoya, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 79 - 94 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] apprentissage automatique [Termes IGN] bande L [Termes IGN] canopée [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] données lidar [Termes IGN] données polarimétriques [Termes IGN] forêt tropicale [Termes IGN] Gabon [Termes IGN] hauteur des arbres [Termes IGN] image captée par drone [Termes IGN] image radar moirée [Termes IGN] Rotation Forest classification [Termes IGN] semis de points Résumé : (auteur) Forest height is an important forest biophysical parameter which is used to derive important information about forest ecosystems, such as forest above ground biomass. In this paper, the potential of combining Polarimetric Synthetic Aperture Radar (PolSAR) variables with LiDAR measurements for forest height estimation is investigated. This will be conducted using different machine learning algorithms including Random Forest (RFs), Rotation Forest (RoFs), Canonical Correlation Forest (CCFs) and Support Vector Machine (SVMs). Various PolSAR parameters are required as input variables to ensure a successful height retrieval across different forest heights ranges. The algorithms are trained with 5000 LiDAR samples (less than 1% of the full scene) and different polarimetric variables. To examine the dependency of the algorithm on input training samples, three different subsets are identified which each includes different features: subset 1 is quiet diverse and includes non-vegetated region, short/sparse vegetation (0–20 m), vegetation with mid-range height (20–40 m) to tall/dense ones (40–60 m); subset 2 covers mostly the dense vegetated area with height ranges 40–60 m; and subset 3 mostly covers the non-vegetated to short/sparse vegetation (0–20 m) .The trained algorithms were used to estimate the height for the areas outside the identified subset. The results were validated with independent samples of LiDAR-derived height showing high accuracy (with the average R2 = 0.70 and RMSE = 10 m between all the algorithms and different training samples). The results confirm that it is possible to estimate forest canopy height using PolSAR parameters together with a small coverage of LiDAR height as training data. Numéro de notice : A2021-086 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2020.11.008 Date de publication en ligne : 19/12/2020 En ligne : https://doi.org/10.1016/j.isprsjprs.2020.11.008 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96846 [article]

Exemplaires(2)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2021021	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2021022	DEP-RECF	Revue	Nancy	Bibliothèque Nancy IFN	Exclu du prêt

Hyperspectral image classification with canonical correlation forests / Junshi Xia in IEEE Transactions on geoscience and remote sensing, vol 55 n° 1 (January 2017)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 55 n° 1 (January 2017) . - pp 421 - 431 Titre : Hyperspectral image classification with canonical correlation forests Type de document : Article/Communication Auteurs : Junshi Xia, Auteur ; Naoto Yokoya, Auteur ; Akira Iwasaki, Auteur Année de publication : 2017 Article en page(s) : pp 421 - 431 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse canonique [Termes IGN] analyse en composantes indépendantes [Termes IGN] champ aléatoire de Markov [Termes IGN] classificateur [Termes IGN] classification [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] image hyperspectrale [Termes IGN] Rotation Forest classification Résumé : (Auteur) Multiple classifier systems or ensemble learning is an effective tool for providing accurate classification results of hyperspectral remote sensing images. Two well-known ensemble learning classifiers for hyperspectral data are random forest (RF) and rotation forest (RoF). In this paper, we proposed to use a novel decision tree (DT) ensemble method, namely, canonical correlation forest (CCF). More specifically, several individual canonical correlation trees (CCTs) that are binary DTs, which use canonical correlation components for the hyperplane splitting, are used to construct the CCF. Additionally, we adopt the projection bootstrap technique in CCF, in which the full spectral bands are retained for split selection in the projected space. The techniques aforementioned allow the CCF to improve the accuracy of member classifiers and diversity within the ensemble. Furthermore, the CCF is extended to the spectral-spatial frameworks that incorporate Markov random fields, extended multiattribute profiles (EMAPs), and the ensemble of independent component analysis and rolling guidance filter (E-ICA-RGF). Experimental results on six hyperspectral data sets are used to indicate the comparative effectiveness of the proposed method, in terms of accuracy and computational complexity, compared with RF and RoF, and it turns out that CCF is a promising approach for hyperspectral image classification not only with spectral information but also in the spectral-spatial frameworks. Numéro de notice : A2017-021 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2016.2607755 En ligne : https://doi.org/10.1109/TGRS.2016.2607755 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=83953 [article]

Spectral–spatial classification for hyperspectral data using rotation forests with local feature extraction and markov random fields / Junshi Xia in IEEE Transactions on geoscience and remote sensing, vol 53 n° 5 (mai 2015)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 53 n° 5 (mai 2015) . - pp 2532 - 2546 Titre : Spectral–spatial classification for hyperspectral data using rotation forests with local feature extraction and markov random fields Type de document : Article/Communication Auteurs : Junshi Xia, Auteur ; Jocelyn Chanussot, Auteur ; Peijun Du, Auteur ; et al., Auteur Année de publication : 2015 Article en page(s) : pp 2532 - 2546 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse comparative [Termes IGN] analyse en composantes principales [Termes IGN] champ aléatoire de Markov [Termes IGN] classification et arbre de régression [Termes IGN] extraction de traits caractéristiques [Termes IGN] image hyperspectrale [Termes IGN] performance [Termes IGN] Rotation Forest classification Résumé : (Auteur) In this paper, we propose a new spectral-spatial classification strategy to enhance the classification performances obtained on hyperspectral images by integrating rotation forests and Markov random fields (MRFs). First, rotation forests are performed to obtain the class probabilities based on spectral information. Rotation forests create diverse base learners using feature extraction and subset features. The feature set is randomly divided into several disjoint subsets; then, feature extraction is performed separately on each subset, and a new set of linear extracted features is obtained. The base learner is trained with this set. An ensemble of classifiers is constructed by repeating these steps several times. The weak classifier of hyperspectral data, classification and regression tree (CART), is selected as the base classifier because it is unstable, fast, and sensitive to rotations of the axes. In this case, small changes in the training data of CART lead to a large change in the results, generating high diversity within the ensemble. Four feature extraction methods, including principal component analysis (PCA), neighborhood preserving embedding (NPE), linear local tangent space alignment (LLTSA), and linearity preserving projection (LPP), are used in rotation forests. Second, spatial contextual information, which is modeled by MRF prior, is used to refine the classification results obtained from the rotation forests by solving a maximum a posteriori problem using the α-expansion graph cuts optimization method. Experimental results, conducted on three hyperspectral data with different resolutions and different contexts, reveal that rotation forest ensembles are competitive with other strong supervised classification methods, such as support vector machines. Rotation forests with local feature extraction methods, including NPE, LLTSA, and LPP, can lead to higher classification accuracies than that achieved by PCA. With the help of MRF, the proposed algorithms can improve the classification accuracies significantly, confirming the importance of spatial contextual information in hyperspectral spectral-spatial classification. Numéro de notice : A2015-519 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2014.2361618 En ligne : https://doi.org/10.1109/TGRS.2014.2361618 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=77526 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-2015051	RAB	Revue	Centre de documentation	En réserve L003	Disponible