Centre dedocumentation
scientifique

Robust unsupervised small area change detection from SAR imagery using deep learning / Xinzheng Zhang in ISPRS Journal of photogrammetry and remote sensing, Vol 173 (March 2021)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > Vol 173 (March 2021) . - pp 79 - 94 Titre : Robust unsupervised small area change detection from SAR imagery using deep learning Type de document : Article/Communication Auteurs : Xinzheng Zhang, Auteur ; Hang Su, Auteur ; Ce Zhang, 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] Traitement d'image radar et applications [Termes descripteurs IGN] algorithme de superpixels [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] classification floue [Termes descripteurs IGN] classification non dirigée [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] détection de changement [Termes descripteurs IGN] échantillonnage [Termes descripteurs IGN] filtre de déchatoiement [Termes descripteurs IGN] image radar moirée [Termes descripteurs IGN] ondelette [Termes descripteurs IGN] reconstruction [Termes descripteurs IGN] regroupement de données Résumé : (auteur) Small area change detection using synthetic aperture radar (SAR) imagery is a highly challenging task, due to speckle noise and imbalance between classes (changed and unchanged). In this paper, a robust unsupervised approach is proposed for small area change detection using deep learning techniques. First, a multi-scale superpixel reconstruction method is developed to generate a difference image (DI), which can suppress the speckle noise effectively and enhance edges by exploiting local, spatially homogeneous information. Second, a two-stage centre-constrained fuzzy c-means clustering algorithm is proposed to divide the pixels of the DI into changed, unchanged and intermediate classes with a parallel clustering strategy. Image patches belonging to the first two classes are then constructed as pseudo-label training samples, and image patches of the intermediate class are treated as testing samples. Finally, a convolutional wavelet neural network (CWNN) is designed and trained to classify testing samples into changed or unchanged classes, coupled with a deep convolutional generative adversarial network (DCGAN) to increase the number of changed class within the pseudo-label training samples. Numerical experiments on four real SAR datasets demonstrate the validity and robustness of the proposed approach, achieving up to 99.61% accuracy for small area change detection. Numéro de notice : A2021-103 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2021.01.004 date de publication en ligne : 17/01/2021 En ligne : https://doi.org/10.1016/j.isprsjprs.2021.01.004 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96879 [article]

From local to global: A transfer learning-based approach for mapping poplar plantations at national scale using Sentinel-2 / Yousra Hamrouni in ISPRS Journal of photogrammetry and remote sensing, vol 171 (January 2021)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 171 (January 2021) . - pp 76 - 100 Titre : From local to global: A transfer learning-based approach for mapping poplar plantations at national scale using Sentinel-2 Type de document : Article/Communication Auteurs : Yousra Hamrouni, Auteur ; Eric Paillassa, Auteur ; Véronique Chéret, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 76 - 100 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes descripteurs IGN] apprentissage automatique [Termes descripteurs IGN] base de données forestières [Termes descripteurs IGN] carte de la végétation [Termes descripteurs IGN] classification par forêts aléatoires [Termes descripteurs IGN] couvert forestier [Termes descripteurs IGN] échantillonnage [Termes descripteurs IGN] France (administrative) [Termes descripteurs IGN] image Sentinel-MSI [Termes descripteurs IGN] mise à jour de base de données [Termes descripteurs IGN] populus (genre) [Termes descripteurs IGN] série temporelle Résumé : (auteur) Reliable estimates of poplar plantations area are not available at the French national scale due to the unsuitability and low update rate of existing forest databases for this short-rotation species. While supervised classification methods have been shown to be highly accurate in mapping forest cover from remotely sensed images, their performance depends to a great extent on the labelled samples used to build the models. In addition to their high acquisition cost, such samples are often scarce and not fully representative of the variability in class distributions. Consequently, when classification models are applied to large areas with high intra-class variance, they generally yield poor accuracies because of data shift issues. In this paper, we propose the use of active learning to efficiently adapt a classifier trained on a source image to spatially distinct target images with minimal labelling effort and without sacrificing the classification performance. The adaptation consists in actively adding to the initial local model new relevant training samples from other areas in a cascade that iteratively improves the generalisation capabilities of the classifier leading to a global model tailored to these different areas. This active selection relies on uncertainty sampling to directly focus on the most informative pixels for which the algorithm is the least certain of their class labels. Experiments conducted on Sentinel-2 time series revealed their high capacity to identify poplar plantations at a local scale with an average F-score ranging from 89.5% to 99.3%. For large area adaptation, the results showed that when the same number of training samples was used, active learning outperformed random sampling by up to 5% of the overall accuracy and up to 12% of the class F-score. Additionally, and depending on the class considered, the random sampling model required up to 50% more samples to achieve the same performance of an active learning-based model. Moreover, the results demonstrate the suitability of the derived global model to accurately map poplar plantations among other tree species with overall accuracy values up to 14% higher than those obtained with local models. The proposed approach paves the way for a national scale mapping in an operational context. Numéro de notice : A2021-013 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2020.10.018 date de publication en ligne : 20/11/2020 En ligne : https://doi.org/10.1016/j.isprsjprs.2020.10.018 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96417 [article]

Variations in temperate forest biomass ratio along three environmental gradients are dominated by interspecific differences in wood density / Baptiste Kerfriden in Plant ecology, vol inconnu (January 2021)  

Public [article]  inPlant ecology > vol inconnu (January 2021) . - 20 p. Titre : Variations in temperate forest biomass ratio along three environmental gradients are dominated by interspecific differences in wood density Type de document : Article/Communication Auteurs : Baptiste Kerfriden, Auteur ; Jean-Daniel Bontemps , Auteur ; Jean-Michel Leban , Auteur Année de publication : 2021 Projets : XyloDensMap / Leban, Jean-Michel Article en page(s) : 20 p. Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes descripteurs IGN] biomasse forestière [Termes descripteurs IGN] capacité de rétention d'eau du sol [Termes descripteurs IGN] carbone [Termes descripteurs IGN] densité du bois [Termes descripteurs IGN] échantillonnage [Termes descripteurs IGN] forêt tempérée [Termes descripteurs IGN] humidité du sol [Termes descripteurs IGN] inventaire forestier (techniques et méthodes) [Termes descripteurs IGN] pinophyta [Vedettes matières IGN] Inventaire forestier Résumé : (auteur) Background: Biomass ratio (BR) is a forest state variable allowing the conversion of forest volume of growing stock into biomass. Despite huge intraspecific variation in wood density depending on the biotic and abiotic environments of tree growth, this variable is most often considered a tree species constant in C budgets. The aims were i) to identify variations in BR along decorrelated water, soil nutrition and elevation gradients, ii) to test for differences between broadleaved and conifer tree species in BR variations, and iii) to weight the contribution of interspecific and intraspecific diversity in BR variations. Methods: Analyses were based on massive wood density measurements performed with an X-ray medical scanner on 54,700 tree cores collected in 2016 and 2017 on the spatially systematic plot sampling design of the French national forest inventory (NFI) program. Results: BR variations along the three gradients were found significant. BR hence decreased by 73 kg.m-3 (conifers) and 126 kg.m-3 (broadleaves) along a 180 mm gradient of soil water holding capacity (SWHC). It also increased by 153 kg.m-3 on average along the full gradient of soil basicity Index (SBI). A negative trend along elevation was also identified, with an average decrease by 155 kg.m-3 from 200 to 2000 m of elevation. Species distribution was found to be the main cause of BR variations along these gradients. Conclusions: We report dependences of BR on both water (–), nutrient availability (+) and warmth (+) gradients, more acute in broadleaves than in conifers only for water availability. At the scale of the whole French forests, intraspecific variations in wood density do not affect BR estimations along these gradients. BR variations are mainly driven by the tree stand species composition along them. Numéro de notice : A2021-082 Affiliation des auteurs : LIF+Ext (2020- ) Thématique : FORET Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s11258-020-01106-0 date de publication en ligne : 03/01/2021 En ligne : https://link.springer.com/article/10.1007/s11258-020-01106-0 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96826 [article]

Is field-measured tree height as reliable as believed – Part II, A comparison study of tree height estimates from conventional field measurement and low-cost close-range remote sensing in a deciduous forest / Luka Jurjević in ISPRS Journal of photogrammetry and remote sensing, vol 169 (November 2020)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 169 (November 2020) . - pp 227 - 241 Titre : Is field-measured tree height as reliable as believed – Part II, A comparison study of tree height estimates from conventional field measurement and low-cost close-range remote sensing in a deciduous forest Type de document : Article/Communication Auteurs : Luka Jurjević, Auteur ; Xinlian Liang, Auteur ; Mateo Gašparović, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 227 - 241 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques [Termes descripteurs IGN] analyse comparative [Termes descripteurs IGN] balayage laser [Termes descripteurs IGN] corrélation [Termes descripteurs IGN] données de terrain [Termes descripteurs IGN] données lidar [Termes descripteurs IGN] échantillonnage [Termes descripteurs IGN] forêt de feuillus [Termes descripteurs IGN] hauteur des arbres [Termes descripteurs IGN] image captée par drone [Termes descripteurs IGN] modèle numérique de terrain [Termes descripteurs IGN] parcelle forestière [Termes descripteurs IGN] photogrammétrie métrologique [Termes descripteurs IGN] quercus pedunculata [Termes descripteurs IGN] semis de points Résumé : (auteur) Tree height is one of the most important tree attributes in forest inventory. However, using conventional field methods to measure tree height is a laborious and time-consuming process. Despite the great interest in the past to facilitate tree height measurements, new, upcoming solutions are not yet thoroughly investigated. In this study, we investigated the applicability of different close-range remote sensing options for tree height measurement in a complex lowland deciduous forest. Six sample plots in a pedunculate oak forest were measured in detail using conventional methods. Close-range remote sensing datasets used in this study represent solutions from low-cost sensors used for hand-held personal laser scanning (PLShh), unmanned–borne laser scanning (ULS) and unmanned aerial vehicle photogrammetry (UAVimage). Each tree in the sample plots was interactively measured directly from the point cloud, and correspondence of the field- and remote sensing measured trees was verified using tree positions collected during fieldwork. Cross-comparisons of different datasets were performed to evaluate the performances of different data sources in the tree height estimation with respect to crown class, tree height and species. All remote sensing data sources correlated well, e.g. biases between remote sensing sources were around ± 1%. The field-measured tree height in general correlated well with remote sensing data sources. The uncertainties and bias of the field measurements were dependent on the tree height and crown class. Field measurements tended to underestimate codominant and intermediate trees at the approximately 1 m magnitude, whilst remote sensing data sources were robust to crown classes. Low-cost ULS used in this study, and very likely in general, may not have enough penetration capability when measuring low and mostly occluded trees, causing missed treetops. PLShh gave tree height estimates closer to the real tree height than those derived from conventional field measurements for trees above 21 m height. Numéro de notice : A2020-641 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2020.09.014 date de publication en ligne : 03/10/2020 En ligne : https://doi.org/10.1016/j.isprsjprs.2020.09.014 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96064 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2020111	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2020113	DEP-RECP	Revue	MATIS	Dépôt en unité	Exclu du prêt
081-2020112	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

From small sets of GPS trajectories to detailed movement profiles: quantifying personalized trip-dependent movement diversity / Elham Naghizade in International journal of geographical information science IJGIS, vol 34 n° 10 (October 2020)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 34 n° 10 (October 2020) . - pp 2004 - 2029 Titre : From small sets of GPS trajectories to detailed movement profiles: quantifying personalized trip-dependent movement diversity Type de document : Article/Communication Auteurs : Elham Naghizade, Auteur ; jeffrey Chan, Auteur ; Martin Tomko, Auteur Année de publication : 2020 Article en page(s) : pp 2004 - 2029 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes descripteurs IGN] comportement [Termes descripteurs IGN] données GPS [Termes descripteurs IGN] données spatiotemporelles [Termes descripteurs IGN] échantillonnage [Termes descripteurs IGN] gestion de trafic [Termes descripteurs IGN] modélisation spatio-temporelle [Termes descripteurs IGN] mouvement [Termes descripteurs IGN] origine - destination [Termes descripteurs IGN] trajectoire [Termes descripteurs IGN] trajet [Termes descripteurs IGN] voyage Résumé : (auteur) The ubiquity of personal sensing devices has enabled the collection of large, diverse, and fine-grained spatio-temporal datasets. These datasets facilitate numerous applications from traffic monitoring and management to location-based services. Recently, there has been an increasing interest in profiling individuals' movements for personalized services based on fine-grained trajectory data. Most approaches identify the most representative paths of a user by analyzing coarse location information, e.g., frequently visited places. However, even for trips that share the same origin and destination, individuals exhibit a variety of behaviors (e.g., a school drop detour, a brief stop at a supermarket). The ability to characterize and compare the variability of individuals' fine-grained movement behavior can greatly support location-based services and smart spatial sampling strategies. We propose a TRip DIversity Measure --TRIM – that quantifies the regularity of users' path choice between an origin and destination. TRIM effectively captures the extent of the diversity of the paths that are taken between a given origin and destination pair, and identifies users with distinct movement patterns, while facilitating the comparison of the movement behavior variations between users. Our experiments using synthetic and real datasets and across geographies show the effectiveness of our method. Numéro de notice : A2020-512 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2020.1730849 date de publication en ligne : 09/03/2020 En ligne : https://doi.org/10.1080/13658816.2020.1730849 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95666 [article]

Towards an optimization of sample plot size and scanner position layout for terrestrial laser scanning in multi-scan mode / Tim Ritter in Forests, vol 11 n° 10 (October 2020)  

Permalink

Weighted spherical sampling of point clouds for forested scenes / Alex Fafard in Photogrammetric Engineering & Remote Sensing, PERS, vol 86 n° 10 (October 2020)  

Permalink

Analysis of chlorophyll concentration in potato crop by coupling continuous wavelet transform and spectral variable optimization / Ning Liu in Remote sensing, vol 12 n° 17 (September 2020)  

Permalink

Extraction of urban built-up areas from nighttime lights using artificial neural network / Tingting Xu in Geocarto international, vol 35 n° 10 ([01/08/2020])  

Permalink

Towards a semi-automated mapping of Australia native invasive alien Acacia trees using Sentinel-2 and radiative transfer models in South Africa / Cecilia Masemola in ISPRS Journal of photogrammetry and remote sensing, vol 166 (August 2020)  

Permalink

Subpixel-pixel-superpixel-based multiview active learning for hyperspectral images classification / Yu Li in IEEE Transactions on geoscience and remote sensing, vol 58 n° 7 (July 2020)  

Permalink

Footprint determination of a spectroradiometer mounted on an unmanned aircraft system / Deepak Gautam in IEEE Transactions on geoscience and remote sensing, vol 58 n° 5 (May 2020)  

Permalink

A point cloud feature regularization method by fusing judge criterion of field force / Xijiang Chen in IEEE Transactions on geoscience and remote sensing, vol 58 n° 5 (May 2020)  

Permalink

Spectral Interference of Heavy Metal Contamination on Spectral Signals of Moisture Content for Heavy Metal Contaminated Soils / Haein Shin in IEEE Transactions on geoscience and remote sensing, vol 58 n° 4 (April 2020)  

Permalink

Large-scale two-phase estimation of wood production by poplar plantations exploiting Sentinel-2 data as auxiliary information / Agnese Marcelli in Silva fennica, vol 54 n° 2 (March 2020)  

Permalink