Centre de documentation
scientifique

GTP-PNet: A residual learning network based on gradient transformation prior for pansharpening / Hao Zhang 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 223 - 239 Titre : GTP-PNet: A residual learning network based on gradient transformation prior for pansharpening Type de document : Article/Communication Auteurs : Hao Zhang, Auteur ; Jiayi Ma, Auteur Année de publication : 2021 Article en page(s) : pp 223 - 239 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] classification dirigée [Termes IGN] fusion d'images [Termes IGN] gradient [Termes IGN] image multibande [Termes IGN] image panchromatique [Termes IGN] Normalized Difference Vegetation Index [Termes IGN] pansharpening (fusion d'images) [Termes IGN] régression Résumé : (auteur) Pansharpening aims to fuse low-resolution multi-spectral image and high-resolution panchromatic (PAN) image to produce a high-resolution multi-spectral (HRMS) image. In this paper, a new residual learning network based on gradient transformation prior, termed as GTP-PNet, is proposed to generate the high-quality HRMS image with accurate spectral distribution as well as reasonable spatial structure. Different from previous deep models that only rely on supervision of the HRMS reference image, we introduce the gradient transformation prior to the deep model, so as to improve the solution accuracy. Our model consists of two networks, namely gradient transformation network (TNet) and pansharpening network (PNet). TNet is committed to seeking the nonlinear mapping between gradients of PAN and HRMS images, which is essentially a spatial relationship regression of imaging bands in different ranges. PNet is the residual learning network used to generate the HRMS image, which is not only supervised by the HRMS reference image, but also constrained by the trained TNet. As a result, the HRMS image generated by PNet not only approximates the HRMS reference image in the spectral distribution, but also conforms to the gradient transformation prior in the spatial structure. Experimental results demonstrate the significant superiority of our method over the current state-of-the-arts in terms of both subjective visual effect and quantitative metrics. We also apply our method to produce the HR normalized difference vegetation index in remote sensing, which can achieve the best performance. Moreover, our method is much competitive compared with the state-of-the-art alternatives in running efficiency. Numéro de notice : A2021-089 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2020.12.014 Date de publication en ligne : 11/01/2021 En ligne : https://doi.org/10.1016/j.isprsjprs.2020.12.014 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96859 [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

Large-scale patterns in forest growth rates are mainly driven by climatic variables and stand characteristics / Hao Zhang in Forest ecology and management, vol 435 (1 March 2019)  

Public [article]  inForest ecology and management > vol 435 (1 March 2019) . - pp 120 - 127 Titre : Large-scale patterns in forest growth rates are mainly driven by climatic variables and stand characteristics Type de document : Article/Communication Auteurs : Hao Zhang, Auteur ; Kelin Wang, Auteur ; Zhaoxia Zeng, Auteur ; et al., Auteur Année de publication : 2019 Article en page(s) : pp 120 - 127 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] biomasse [Termes IGN] changement climatique [Termes IGN] Chine [Termes IGN] croissance des arbres [Termes IGN] forêt [Termes IGN] modèle de croissance végétale [Termes IGN] plantation forestière [Termes IGN] puits de carbone [Vedettes matières IGN] Végétation et changement climatique Résumé : (Auteur) Comparing the growth rate of natural forest and plantation forest may be useful to better understand rates of carbon sequestration and carbon turnover. However, the large-scale patterns of biomass growth rates in China’s forests are still not well defined. We analyzed the growth rates of forest leaves, branches, stems, and roots across forest communities in China by using data collection, collation, and systematic analysis of published research and our unpublished data. The biomass growth rates in all forests exhibited negative latitudinal trends and negative altitudinal trends, with significant influence from climatic variables and stand characteristics. Stand characteristics explained more variation in growth rates of forest biomass than did climatic variables, and growth rates of forest leaves, branches, stems, and roots varied in relation to climate, stand characteristics, and forest origin. The cross-validated results of stepwise multiple regression (SMR) models and neural network models (NNM) indicated that the prediction accuracy of growth rate of forest biomass by NNM was better than that of the SMR models. Our results improve understanding of the environmental factors affecting Chinese forest growth and inform efforts to model dynamics of carbon accumulation in China’s forests. Numéro de notice : A2019-184 Affiliation des auteurs : non IGN Thématique : FORET/MATHEMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.foreco.2018.12.054 Date de publication en ligne : 04/01/2019 En ligne : https://doi.org/10.1016/j.foreco.2018.12.054 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92718 [article]

Estimation of higher chlorophylla concentrations using field spectral measurement and HJ-1A hyperspectral satellite data in Dianshan Lake, China / Liguo Zhou in ISPRS Journal of photogrammetry and remote sensing, vol 88 (February 2014)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 88 (February 2014) . - pp 41 - 47 Titre : Estimation of higher chlorophylla concentrations using field spectral measurement and HJ-1A hyperspectral satellite data in Dianshan Lake, China Type de document : Article/Communication Auteurs : Liguo Zhou, Auteur ; Dar A. Roberts, Auteur ; Weichun Ma, Auteur ; Hao Zhang, Auteur ; Lin Tang, Auteur Année de publication : 2014 Article en page(s) : pp 41 - 47 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] Chine [Termes IGN] chlorophylle [Termes IGN] image HJ-1A [Termes IGN] image hyperspectrale [Termes IGN] lac Résumé : (Auteur) Based on in situ water sampling and field spectral measurements in Dianshan Lake, a semi-analytical three-band algorithm was used to estimate Chlorophylla (Chla) content in case II waters. The three bands selected to estimate Chla for high concentrations included 653, 691 and 748 nm. An equation, based on the difference in reciprocal reflectance between 653 and 691 nm, multiplied by reflectance at 748 nm as [Rrs-1(653) - Rrs-1(691)] Rrs(748), explained 85.57% of variance in Chla concentration with a root mean square error (RMSE) of Numéro de notice : A2014-084 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2013.11.016 En ligne : https://doi.org/10.1016/j.isprsjprs.2013.11.016 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=32989 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2014021	RAB	Revue	Centre de documentation	En réserve L003	Disponible