Centre de documentation
scientifique

Dépouillements

Generating Sentinel-2 all-band 10-m data by sharpening 20/60-m bands: A hierarchical fusion network / Jingan Wu in ISPRS Journal of photogrammetry and remote sensing, vol 196 (February 2023)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 196 (February 2023) . - pp 16 - 31 Titre : Generating Sentinel-2 all-band 10-m data by sharpening 20/60-m bands: A hierarchical fusion network Type de document : Article/Communication Auteurs : Jingan Wu, Auteur ; Liupeng Lin, Auteur ; Chi Zhang, Auteur ; et al., Auteur Année de publication : 2023 Article en page(s) : pp 16 - 31 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] affinage d'image [Termes IGN] approche hiérarchique [Termes IGN] bande spectrale [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] filtre passe-haut [Termes IGN] fusion d'images [Termes IGN] image à haute résolution [Termes IGN] image Sentinel-MSI Résumé : (Auteur) Earth observations from the Sentinel-2 mission have been extensively accepted in a variety of land services. The thirteen spectral bands of Sentinel-2, however, are collected at three spatial resolutions of 10/20/60 m, and such a difference brings difficulties to analyze multispectral imagery at a uniform resolution. To address this problem, we developed a hierarchical fusion network (HFN) to sharpen 20/60-m bands and generate Sentinel-2 all-band 10-m data. The deep learning architecture is used to learn the complex mapping between multi-resolution input and output data. Given the deficiency of previous studies in which the spatial information is inferred only from the fine-resolution bands, the proposed hierarchical fusion framework simultaneously leverages the self-similarity information from coarse-resolution bands and the spatial structure information from fine-resolution bands, to enhance the sharpening performance. Technically, the coarse-resolution bands are super-resolved by exploiting the information from themselves and then sharpened by fusing with the fine-resolution bands. Both 20-m and 60-m bands can be sharpened via the developed approach. Experimental results regarding visual comparison and quantitative assessment demonstrate that HFN outperforms the other benchmarking models, including pan-sharpening-based, model-based, geostatistical-based, and other deep-learning-based approaches, showing remarkable performance in reproducing explicit spatial details and maintaining original spectral features. Moreover, the developed model works more effectively than the other models over the heterogeneous landscape, which is usually considered a challenging application scenario. To sum up, the fusion model can sharpen Sentinel-2 20/60-m bands, and the created all-band 10-m data allows image analysis and geoscience applications to be authentically carried out at the 10-m resolution. Numéro de notice : A2023-063 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2022.12.017 Date de publication en ligne : 01/01/2023 En ligne : https://doi.org/10.1016/j.isprsjprs.2022.12.017 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102392 [article]

PSSNet: Planarity-sensible Semantic Segmentation of large-scale urban meshes / Weixiao Gao in ISPRS Journal of photogrammetry and remote sensing, vol 196 (February 2023)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 196 (February 2023) . - pp 32 - 44 Titre : PSSNet: Planarity-sensible Semantic Segmentation of large-scale urban meshes Type de document : Article/Communication Auteurs : Weixiao Gao, Auteur ; Liangliang Nan, Auteur ; Bas Boom, Auteur ; Hugo Ledoux, Auteur Année de publication : 2023 Article en page(s) : pp 32 - 44 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] analyse de scène 3D [Termes IGN] champ aléatoire de Markov [Termes IGN] classification dirigée [Termes IGN] contour [Termes IGN] maillage [Termes IGN] Perceptron multicouche [Termes IGN] réseau neuronal de graphes [Termes IGN] scène urbaine [Termes IGN] segmentation sémantique Résumé : (Auteur) We introduce a novel deep learning-based framework to interpret 3D urban scenes represented as textured meshes. Based on the observation that object boundaries typically align with the boundaries of planar regions, our framework achieves semantic segmentation in two steps: planarity-sensible over-segmentation followed by semantic classification. The over-segmentation step generates an initial set of mesh segments that capture the planar and non-planar regions of urban scenes. In the subsequent classification step, we construct a graph that encodes the geometric and photometric features of the segments in its nodes and the multi-scale contextual features in its edges. The final semantic segmentation is obtained by classifying the segments using a graph convolutional network. Experiments and comparisons on two semantic urban mesh benchmarks demonstrate that our approach outperforms the state-of-the-art methods in terms of boundary quality, mean IoU (intersection over union), and generalization ability. We also introduce several new metrics for evaluating mesh over-segmentation methods dedicated to semantic segmentation, and our proposed over-segmentation approach outperforms state-of-the-art methods on all metrics. Our source code is available at https://github.com/WeixiaoGao/PSSNet. Numéro de notice : A2023-064 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2022.12.020 Date de publication en ligne : 02/01/2023 En ligne : https://doi.org/10.1016/j.isprsjprs.2022.12.020 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102399 [article]

Amazon forest spectral seasonality is consistent across sensor resolutions and driven by leaf demography / Nathan B. Gonçalves in ISPRS Journal of photogrammetry and remote sensing, vol 196 (February 2023)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 196 (February 2023) . - pp 93 - 104 Titre : Amazon forest spectral seasonality is consistent across sensor resolutions and driven by leaf demography Type de document : Article/Communication Auteurs : Nathan B. Gonçalves, Auteur ; Ricardo Dalagnol, Auteur ; Jin Wu, Auteur ; et al., Auteur Année de publication : 2023 Article en page(s) : pp 93 - 104 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] Amazonie [Termes IGN] distribution du coefficient de réflexion bidirectionnelle BRDF [Termes IGN] forêt tropicale [Termes IGN] image Landsat-8 [Termes IGN] image Landsat-OLI [Termes IGN] image proche infrarouge [Termes IGN] image Terra-MODIS [Termes IGN] indice de végétation [Termes IGN] Leaf Area Index [Termes IGN] réflectance spectrale [Termes IGN] sécheresse [Termes IGN] variation saisonnière Résumé : (Auteur) Controversy surrounds the reported dry season greening of the Central Amazon forests based on the Enhanced Vegetation Index (EVI) from the Moderate Resolution Imaging Spectroradiometer (MODIS). As the solar zenith angle decreases during the dry season, it affects the sub-pixel shade content and artificially increases Near-infrared (NIR) reflectance and EVI. MODIS' coarse resolution also creates a challenge for cloud and terrain filtering. To reduce these artifacts and then validate MODIS seasonal spectral patterns we use 16 years of 1 km resolution MODIS-MAIAC (Multi-Angle Implementation of Atmospheric Correction) images, corrected to a nadir view and 45° solar zenith angle, together with an improved cloud filter. Then we show that the 30 m Landsat-8 Operational Land Imager (OLI) surface reflectance over two Landsat scenes provides independent evidence supporting the MODIS-MAIAC seasonality for EVI, NIR, and GCC (an additional important vegetation index, green chromatic coordinate). Our empirical method for controlling for sun-sensor geometry effects in Landsat scenes encompasses the use of seasonally distinct images that have similar solar zenith angles and cloud-free pixels on flat uplands having the same phase angle. We extended this validation to nine Amazon sub-basins comprising ∼546 Landsat-8 images. Our study shows that the dry-season green-up pattern observed by MODIS is corroborated by Landsat-8, and is independent of satellite data artifacts. To investigate the mechanisms driving these seasonal changes we further used Central Amazon tower-mounted RGB cameras providing a 4-year record at the Amazon Tall Tower (ATTO, 2°8′36″S, 59°0′2″W) and a 7-year record at the Manaus k34 tower (2°36′33″ S, 60°12′33″W) to obtain monthly upper canopy green leaf cover (a proxy for Leaf Area Index - LAI) and monthly leaf age class abundances (based on the age since leaf flushing, by crown). These were compared to seasonal patterns of GCC and EVI in small MODIS-MAIAC windows centered on each tower. MODIS-MAIAC GCC was positively correlated with newly flushed leaves (R2 = 0.76 and 0.44 at ATTO and k34, respectively). EVI correlated strongly with the abundance of mature leaves (R2 = 0.82 and 0.80) but was poorly correlated with LAI (R2 = 0.20 and 0.41, respectively). Therefore, seasonal spectral patterns in the Central Amazon are likely controlled by leaf age variation, not quantity of leaf area. Numéro de notice : A2023-065 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2022.12.001 Date de publication en ligne : 04/01/2023 En ligne : https://doi.org/10.1016/j.isprsjprs.2022.12.001 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102423 [article]

Large-scale burn severity mapping in multispectral imagery using deep semantic segmentation models / Xikun Hu in ISPRS Journal of photogrammetry and remote sensing, vol 196 (February 2023)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 196 (February 2023) . - pp 228 - 240 Titre : Large-scale burn severity mapping in multispectral imagery using deep semantic segmentation models Type de document : Article/Communication Auteurs : Xikun Hu, Auteur ; Puzhao Zhang, Auteur ; Yifang Ban, Auteur Année de publication : 2023 Article en page(s) : pp 228 - 240 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] carte thématique [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] dommage [Termes IGN] image Landsat-ETM+ [Termes IGN] image Landsat-OLI [Termes IGN] image Landsat-TM [Termes IGN] image multibande [Termes IGN] image Sentinel-MSI [Termes IGN] incendie de forêt [Termes IGN] jeu de données localisées [Termes IGN] segmentation sémantique [Termes IGN] surveillance forestière [Termes IGN] zone sinistrée Résumé : (auteur) Nowadays Earth observation satellites provide forest fire authorities and resource managers with spatial and comprehensive information for fire stabilization and recovery. Burn severity mapping is typically performed by classifying bi-temporal indices (e.g., dNBR, and RdNBR) using thresholds derived from parametric models incorporating field-based measurements. Analysts are currently expending considerable manual effort using prior knowledge and visual inspection to determine burn severity thresholds. In this study, we aim to employ highly automated approaches to provide spatially explicit damage level estimates. We first reorganize a large-scale Landsat-based bi-temporal burn severity assessment dataset (Landsat-BSA) by visual data cleaning based on annotated MTBS data (approximately 1000 major fire events in the United States). Then we apply state-of-the-art deep learning (DL) based methods to map burn severity based on the Landsat-BSA dataset. Experimental results emphasize that multi-class semantic segmentation algorithms can approximate the threshold-based techniques used extensively for burn severity classification. UNet-like models outperform other region-based CNN and Transformer-based models and achieve accurate pixel-wise classification results. Combined with the online hard example mining algorithm to reduce class imbalance issue, Attention UNet achieves the highest mIoU (0.78) and the highest Kappa coefficient close to 0.90. The bi-temporal inputs with ancillary spectral indices work much better than the uni-temporal multispectral inputs. The restructured dataset will be publicly available and create opportunities for further advances in remote sensing and wildfire communities. Numéro de notice : A2023-122 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2022.12.026 Date de publication en ligne : 11/01/2023 En ligne : https://doi.org/10.1016/j.isprsjprs.2022.12.026 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102498 [article]