Centre dedocumentation
scientifique

Comparison of multi-seasonal Landsat 8, Sentinel-2 and hyperspectral images for mapping forest alliances in Northern California / Matthew L. Clark in ISPRS Journal of photogrammetry and remote sensing, vol 159 (January 2020)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 159 (January 2020) . - pp 26 - 40 Titre : Comparison of multi-seasonal Landsat 8, Sentinel-2 and hyperspectral images for mapping forest alliances in Northern California Type de document : Article/Communication Auteurs : Matthew L. Clark, Auteur Année de publication : 2020 Article en page(s) : pp 26 - 40 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes descripteurs IGN] analyse comparative [Termes descripteurs IGN] apprentissage automatique [Termes descripteurs IGN] Californie (Etats-Unis) [Termes descripteurs IGN] carte forestière [Termes descripteurs IGN] classification par forêts aléatoires [Termes descripteurs IGN] classification par séparateurs à vaste marge [Termes descripteurs IGN] couvert végétal [Termes descripteurs IGN] image AVIRIS [Termes descripteurs IGN] image hyperspectrale [Termes descripteurs IGN] image Landsat-8 [Termes descripteurs IGN] image Sentinel-MSI [Termes descripteurs IGN] occupation du sol [Termes descripteurs IGN] Short Waves InfraRed Résumé : (Auteur) The current era of earth observation now provides constellations of open-access, multispectral satellite imagery with medium spatial resolution, greatly increasing the frequency of cloud-free data for analysis. The Landsat satellites have a long historical record, while the newer Sentinel-2 (S2) satellites offer higher temporal, spatial and spectral resolution. The goal of this study was to evaluate the relative benefits of single- and multi-seasonal multispectral satellite data for discriminating detailed forest alliances, as defined by the U.S. National Vegetation Classification system, in a Mediterranean-climate landscape (Sonoma County, California). Results were compared to a companion analysis of simulated hyperspectral satellite data (HyspIRI) for the same study site and reference data (Clark et al., 2018). Experiments used real and simulated S2 and Landsat 8 (L8) data. Simulated S2 and L8 were from HyspIRI images, thereby focusing results on differences in spectral resolution rather than other confounding factors. The Support Vector Machine (SVM) classifier was used in a hierarchical classification of land-cover (Level 1), followed by alliances (Level 2) in forest pixels, and included summer-only and multi-seasonal sets of predictor variables (bands, indices and bands plus indices). Both real and simulated multi-seasonal multispectral variables significantly improved overall accuracy (OA) by 0.2–1.6% for Level 1 tree/no tree classifications and 3.6–25.8% for Level 2 forest alliances. Classifiers with S2 variables tended to be more accurate than L8 variables, particularly for S2, which had 0.4–2.1% and 5.1–11.8% significantly higher OA than L8 for Level 1 tree/no tree and Level 2 forest alliances, respectively. Combining multispectral bands and indices or using just bands was generally more accurate than relying on just indices for classification. Simulated HyspIRI variables from past research had significantly greater accuracy than real L8 and S2 variables, with an average OA increase of 8.2–12.6%. A final alliance-level map used for a deeper analysis used simulated multi-seasonal S2 bands and indices, which had an overall accuracy of 74.3% (Kappa = 0.70). The accuracy of this classification was only 1.6% significantly lower than the best HyspIRI-based classification, which used multi-seasonal metrics (Clark et al., 2018), and there were alliances where the S2-based classifier was more accurate. Within the context of these analyses and study area, S2 spectral-temporal data demonstrated a strong capability for mapping global forest alliances, or similar detailed floristic associations, at medium spatial resolutions (10–30 m). Numéro de notice : A2020-011 Thématique : FORET/GEOMATIQUE/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2019.11.007 date de publication en ligne : 14/11/2019 En ligne : https://doi.org/10.1016/j.isprsjprs.2019.11.007 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94399 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2020011	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2020013	DEP-RECP	Revue	MATIS	Dépôt en unité	Exclu du prêt
081-2020012	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

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)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 159 (January 2020) . - pp 140 - 152 Titre : Superpixel-enhanced deep neural forest for remote sensing image semantic segmentation Type de document : Article/Communication Auteurs : Li Mi, Auteur ; Zhenzhong Chen, Auteur Année de publication : 2020 Article en page(s) : pp 140 - 152 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes descripteurs IGN] apprentissage automatique [Termes descripteurs IGN] classification par forêts aléatoires [Termes descripteurs IGN] image à très haute résolution [Termes descripteurs IGN] processus stochastique [Termes descripteurs IGN] réseau de neurones profond [Termes descripteurs IGN] segmentation sémantique [Termes descripteurs IGN] SLIC algorithm [Termes descripteurs IGN] superpixel Résumé : (Auteur) Semantic segmentation plays an important role in remote sensing image understanding. Great progress has been made in this area with the development of Deep Convolutional Neural Networks (DCNNs). However, due to the complexity of ground objects’ spectrum, DCNNs with simple classifier have difficulties in distinguishing ground object categories even though they can represent image features effectively. Additionally, DCNN-based semantic segmentation methods learn to accumulate contextual information over large receptive fields that causes blur on object boundaries. In this work, a novel approach named Superpixel-enhanced Deep Neural Forest (SDNF) is proposed to target the aforementioned problems. To improve the classification ability, we introduce Deep Neural Forest (DNF), where the representation learning of deep neural network is conducted by a completely differentiable decision forest. Therefore, better classification accuracy is achieved by combining DCNNs with decision forests in an end-to-end manner. In addition, considering the homogeneity within superpixels and heterogeneity between superpixels, a Superpixel-enhanced Region Module (SRM) is proposed to further alleviate the noises and strengthen edges of ground objects. Experimental results on the ISPRS 2D semantic labeling benchmark demonstrate that our model significantly outperforms state-of-the-art methods thus validate the efficiency of our proposed SDNF. Numéro de notice : A2020-014 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2019.11.006 date de publication en ligne : 29/11/2019 En ligne : https://doi.org/10.1016/j.isprsjprs.2019.11.006 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94403 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2020011	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2020013	DEP-RECP	Revue	MATIS	Dépôt en unité	Exclu du prêt
081-2020012	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Combining Sentinel-1 and Sentinel-2 Satellite image time series for land cover mapping via a multi-source deep learning architecture / Dino Lenco in ISPRS Journal of photogrammetry and remote sensing, Vol 158 (December 2019)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > Vol 158 (December 2019) Titre : Combining Sentinel-1 and Sentinel-2 Satellite image time series for land cover mapping via a multi-source deep learning architecture Type de document : Article/Communication Auteurs : Dino Lenco, Auteur ; Roberto Interdonato, Auteur ; Raffaele Gaetano, Auteur ; Ho Tong Minh Dinh, Auteur Année de publication : 2019 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image mixte [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] Burkina Faso [Termes descripteurs IGN] carte de la végétation [Termes descripteurs IGN] classification par forêts aléatoires [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] fusion d'images [Termes descripteurs IGN] image à haute résolution [Termes descripteurs IGN] image multibande [Termes descripteurs IGN] image radar moirée [Termes descripteurs IGN] image Sentinel-MSI [Termes descripteurs IGN] image Sentinel-SAR [Termes descripteurs IGN] occupation du sol [Termes descripteurs IGN] Réunion, île de la [Termes descripteurs IGN] série temporelle [Termes descripteurs IGN] utilisation du sol Résumé : (auteur) The huge amount of data currently produced by modern Earth Observation (EO) missions has allowed for the design of advanced machine learning techniques able to support complex Land Use/Land Cover (LULC) mapping tasks. The Copernicus programme developed by the European Space Agency provides, with missions such as Sentinel-1 (S1) and Sentinel-2 (S2), radar and optical (multi-spectral) imagery, respectively, at 10 m spatial resolution with revisit time around 5 days. Such high temporal resolution allows to collect Satellite Image Time Series (SITS) that support a plethora of Earth surface monitoring tasks. How to effectively combine the complementary information provided by such sensors remains an open problem in the remote sensing field. In this work, we propose a deep learning architecture to combine information coming from S1 and S2 time series, namely TWINNS (TWIn Neural Networks for Sentinel data), able to discover spatial and temporal dependencies in both types of SITS. The proposed architecture is devised to boost the land cover classification task by leveraging two levels of complementarity, i.e., the interplay between radar and optical SITS as well as the synergy between spatial and temporal dependencies. Experiments carried out on two study sites characterized by different land cover characteristics (i.e., the Koumbia site in Burkina Faso and Reunion Island, a overseas department of France in the Indian Ocean), demonstrate the significance of our proposal. Numéro de notice : A2019-544 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2019.09.016 date de publication en ligne : 27/09/2019 En ligne : https://doi.org/10.1016/j.isprsjprs.2019.09.016 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94186 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2019121	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2019123	DEP-RECP	Revue	MATIS	Dépôt en unité	Exclu du prêt
081-2019122	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Deep learning for conifer/deciduous classification of airborne LiDAR 3D point clouds representing individual trees / Hamid Hamraz in ISPRS Journal of photogrammetry and remote sensing, Vol 158 (December 2019)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > Vol 158 (December 2019) . - pp 219 - 230 Titre : Deep learning for conifer/deciduous classification of airborne LiDAR 3D point clouds representing individual trees Type de document : Article/Communication Auteurs : Hamid Hamraz, Auteur ; Nathan B. Jacobs, Auteur ; Marco A. Contreras, Auteur ; Chase H. Clark, Auteur Année de publication : 2019 Article en page(s) : pp 219 - 230 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] arbre caducifolié [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] données d'apprentissage [Termes descripteurs IGN] données lidar [Termes descripteurs IGN] données localisées 3D [Termes descripteurs IGN] houppier [Termes descripteurs IGN] modèle numérique de surface [Termes descripteurs IGN] pinophyta [Termes descripteurs IGN] semis de points Résumé : (auteur) The purpose of this study was to investigate the use of deep learning for coniferous/deciduous classification of individual trees segmented from airborne LiDAR data. To enable processing by a deep convolutional neural network (CNN), we designed two discrete representations using leaf-off and leaf-on LiDAR data: a digital surface model with four channels (DSM × 4) and a set of four 2D views (4 × 2D). A training dataset of tree crowns was generated via segmentation of tree crowns, followed by co-registration with field data. Potential mislabels due to GPS error or tree leaning were corrected using a statistical ensemble filtering procedure. Because the training data was heavily unbalanced (~8% conifers), we trained an ensemble of CNNs on random balanced sub-samples. Benchmarked against multiple traditional shallow learning methods using manually designed features, the CNNs improved accuracies up to 14%. The 4 × 2D representation yielded similar classification accuracies to the DSM × 4 representation (~82% coniferous and ~90% deciduous) while converging faster. Further experimentation showed that early/late fusion of the channels in the representations did not affect the accuracies in a significant way. The data augmentation that was used for the CNN training improved the classification accuracies, but more real training instances (especially coniferous) likely results in much stronger improvements. Leaf-off LiDAR data were the primary source of useful information, which is likely due to the perennial nature of coniferous foliage. LiDAR intensity values also proved to be useful, but normalization yielded no significant improvement. As we observed, large training data may compensate for the lack of a subset of important domain data. Lastly, the classification accuracies of overstory trees (~90%) were more balanced than those of understory trees (~90% deciduous and ~65% coniferous), which is likely due to the incomplete capture of understory tree crowns via airborne LiDAR. In domains like remote sensing and biomedical imaging, where the data contain a large amount of information and are not friendly to human visual system, human-designed features may become suboptimal. As exemplified by this study, automatic, objective derivation of optimal features via deep learning can improve prediction tasks in such domains. Numéro de notice : A2019-547 Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2019.10.011 date de publication en ligne : 03/11/2019 En ligne : https://doi.org/10.1016/j.isprsjprs.2019.10.011 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94192 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2019121	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2019123	DEP-RECP	Revue	MATIS	Dépôt en unité	Exclu du prêt
081-2019122	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Matching of TerraSAR-X derived ground control points to optical image patches using deep learning / Tatjana Bürgmann in ISPRS Journal of photogrammetry and remote sensing, Vol 158 (December 2019)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > Vol 158 (December 2019) . - pp 241 - 248 Titre : Matching of TerraSAR-X derived ground control points to optical image patches using deep learning Type de document : Article/Communication Auteurs : Tatjana Bürgmann, Auteur ; Wolfgang Koppe, Auteur ; Michael Schmitt, Auteur Année de publication : 2019 Article en page(s) : pp 241 - 248 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image mixte [Termes descripteurs IGN] appariement d'images [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] géolocalisation [Termes descripteurs IGN] image multicapteur [Termes descripteurs IGN] image optique [Termes descripteurs IGN] image Pléiades [Termes descripteurs IGN] image radar moirée [Termes descripteurs IGN] image Sentinel-MSI [Termes descripteurs IGN] image Sentinel-SAR [Termes descripteurs IGN] image TerraSAR-X [Termes descripteurs IGN] point d'appui Résumé : (auteur) High resolution synthetic aperture radar (SAR) satellites like TerraSAR-X are capable of acquiring images exhibiting an absolute geolocation accuracy within a few centimeters, mainly because of the availability of precise orbit information and by compensating range delay errors due to atmospheric conditions. In contrast, satellite images from optical missions generally exhibit comparably low geolocation accuracies because of the propagation of errors in angular measurements over large distances. However, a variety of remote sensing applications, such as change detection, surface movement monitoring or ice flow measurements, require precisely geo-referenced and co-registered satellite images. By using Ground Control Points (GCPs) derived from TerraSAR-X, the absolute geolocation accuracy of optical satellite images can be improved. For this purpose, the corresponding matching points in the optical images need to be localized. In this paper, a deep learning based approach is investigated for an automated matching of SAR-derived GCPs to optical image elements. Therefore, a convolutional neural network is pretrained with medium resolution Sentinel-1 and Sentinel-2 imagery and fine-tuned on precisely co-registered TerraSAR-X and Pléiades training image pairs to learn a common descriptor representation. By using these descriptors, the similarity of SAR and optical image patches can be calculated. This similarity metric is then used in a sliding window approach to identify the matching points in the optical reference image. Subsequently, the derived points can be utilized for co-registration of the underlying images. The network is evaluated over nine study areas showing airports and their rural surroundings from several different countries around the world. The results show that based on TerraSAR-X-derived GCPs, corresponding points in the optical image can automatically and reliably be identified with a pixel-level localization accuracy. Numéro de notice : A2019-548 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2019.09.010 date de publication en ligne : 05/11/2019 En ligne : https://doi.org/10.1016/j.isprsjprs.2019.09.010 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94194 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2019121	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2019123	DEP-RECP	Revue	MATIS	Dépôt en unité	Exclu du prêt
081-2019122	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Comparison between convolutional neural networks and random forest for local climate zone classification in mega urban areas using Landsat images / Cheolhee Yoo in ISPRS Journal of photogrammetry and remote sensing, vol 157 (November 2019)  

Permalink

Context pyramidal network for stereo matching regularized by disparity gradients / Junhua Kang in ISPRS Journal of photogrammetry and remote sensing, vol 157 (November 2019)  

Permalink

Deep learning for multi-modal classification of cloud, shadow and land cover scenes in PlanetScope and Sentinel-2 imagery / Yuri Shendryk in ISPRS Journal of photogrammetry and remote sensing, vol 157 (November 2019)  

Permalink

Combining machine learning and compact polarimetry for estimating soil moisture from C-Band SAR data / Emanuele Santi in Remote sensing, Vol 11 n° 20 (2 October 2019)  

Permalink

A machine learning approach to detect crude oil contamination in a real scenario using hyperspectral remote sensing / Ran Pelta in International journal of applied Earth observation and geoinformation, vol 82 (October 2019)  

Permalink

Mapping dead forest cover using a deep convolutional neural network and digital aerial photography / Jean-Daniel Sylvain in ISPRS Journal of photogrammetry and remote sensing, vol 156 (October 2019)  

Permalink

Multi-sensor prediction of Eucalyptus stand volume: A support vector approach / Guilherme Silverio Aquino de Souza in ISPRS Journal of photogrammetry and remote sensing, vol 156 (October 2019)  

Permalink

Optimal segmentation of high spatial resolution images for the classification of buildings using random forests / James Bialas in International journal of applied Earth observation and geoinformation, vol 82 (October 2019)  

Permalink

Scene context-driven vehicle detection in high-resolution aerial images / Chao Tao in IEEE Transactions on geoscience and remote sensing, Vol 57 n° 10 (October 2019)  

Permalink

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

Permalink