Centre de documentation
scientifique

A semiautomated probabilistic framework for tree-cover delineation from 1-m NAIP imagery using a high-performance computing architecture / S. Basu in IEEE Transactions on geoscience and remote sensing, vol 53 n° 10 (October 2015)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 53 n° 10 (October 2015) . - pp 5690 - 5708 Titre : A semiautomated probabilistic framework for tree-cover delineation from 1-m NAIP imagery using a high-performance computing architecture Type de document : Article/Communication Auteurs : S. Basu, Auteur ; Sangram Ganguly, Auteur ; Ramakrishna R. Nemani, Auteur ; et al., Auteur Année de publication : 2015 Article en page(s) : pp 5690 - 5708 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] analyse comparative [Termes IGN] architecture des systèmes d'information [Termes IGN] classification non dirigée [Termes IGN] couvert forestier [Termes IGN] Etats-Unis [Termes IGN] réseau neuronal artificiel [Termes IGN] segmentation d'image Résumé : (Auteur) Accurate tree-cover estimates are useful in deriving above-ground biomass density estimates from very high resolution (VHR) satellite imagery data. Numerous algorithms have been designed to perform tree-cover delineation in high-to-coarse-resolution satellite imagery, but most of them do not scale to terabytes of data, typical in these VHR data sets. In this paper, we present an automated probabilistic framework for the segmentation and classification of 1-m VHR data as obtained from the National Agriculture Imagery Program (NAIP) for deriving tree-cover estimates for the whole of Continental United States, using a high-performance computing architecture. The results from the classification and segmentation algorithms are then consolidated into a structured prediction framework using a discriminative undirected probabilistic graphical model based on conditional random field, which helps in capturing the higher order contextual dependence relations between neighboring pixels. Once the final probability maps are generated, the framework is updated and retrained by incorporating expert knowledge through the relabeling of misclassified image patches. This leads to a significant improvement in the true positive rates and reduction in false positive rates (FPRs). The tree-cover maps were generated for the state of California, which covers a total of 11 095 NAIP tiles and spans a total geographical area of 163 696 sq. miles. Our framework produced correct detection rates of around 88% for fragmented forests and 74% for urban tree-cover areas, with FPRs lower than 2% for both regions. Comparative studies with the National Land-Cover Data algorithm and the LiDAR high-resolution canopy height model showed the effectiveness of our algorithm for generating accurate high-resolution tree-cover maps. Numéro de notice : A2015-753 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2015.2428197 Date de publication en ligne : 26/05/2015 En ligne : https://doi.org/10.1109/TGRS.2015.2428197 Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=78743 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-2015101	SL	Revue	Centre de documentation	Revues en salle	Disponible