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

Real-time monitoring and short-term forecasting of land surface phenology / M.A. White in Remote sensing of environment, vol 104 n° 1 (15/09/2006)  

Public [article]  inRemote sensing of environment > vol 104 n° 1 (15/09/2006) . - pp 43 - 49 Titre : Real-time monitoring and short-term forecasting of land surface phenology Type de document : Article/Communication Auteurs : M.A. White, Auteur ; Ramakrishna R. Nemani, Auteur Année de publication : 2006 Article en page(s) : pp 43 - 49 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] analyse diachronique [Termes IGN] phénologie [Termes IGN] prédiction [Termes IGN] prévision à court terme [Termes IGN] seuillage d'image [Termes IGN] surface du sol [Termes IGN] surveillance écologique [Termes IGN] temps réel Résumé : (Auteur) Land surface phenology is an important process for real-time monitoring and short-term forecasting in diverse land management, health, and hydrologic modeling applications. Yet current efforts to characterize phenological processes are limited by remote sensing challenges and lack of uncertainty estimates. Here, for a global distribution of phenologically and climatically similar phenoregions, we used the Advanced Very High Resolution Radiometer to develop a conceptually and computationally simple technique for real-time and forecast applications. Our overall approach was to analyze the phenological behavior of groups of pixels without recourse to smoothing or fitting. We used a 3-step initial process: (1) define a phenoregion specific normalized difference vegetation index threshold; (2) for all days from 1982–2003, calculate the percent of pixels above the threshold (PAT); (3) calculate daily 1982–2003 empirical distributions of PAT. For real-time monitoring, the current PAT may then be compared to the historical range of variability and visualized in relation to user-defined levels. Using similar concepts, we projected daily PAT up to one month in the future and compared predicted and actual dates at which a hypothetical PAT was reached. We found that the maximum lead-time of phenological forecasts could be analytically defined for user-specified uncertainty levels. The approach is adaptable to different remote sensing technologies and provides a foundation for ascribing a sequence of ground conditions (e.g. snowmelt, vegetative growth, pollen production, insect phenology) to remotely sensed land surface phenology observations. Copyright Elsevier Numéro de notice : A2006-393 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.rse.2006.04.014 En ligne : https://doi.org/10.1016/j.rse.2006.04.014 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=28117 [article]

Relating seasonal patterns of the AVHRR vegetation index to simulated photosynthesis and transpiration of forests in different climates / S.W. Running in Remote sensing of environment, vol 24 n° 2 (March 1988)  

Public [article]  inRemote sensing of environment > vol 24 n° 2 (March 1988) . - pp 347 - 367 Titre : Relating seasonal patterns of the AVHRR vegetation index to simulated photosynthesis and transpiration of forests in different climates Type de document : Article/Communication Auteurs : S.W. Running, Auteur ; Ramakrishna R. Nemani, Auteur Année de publication : 1988 Article en page(s) : pp 347 - 367 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] Advanced Very High Resolution Radiometer [Termes IGN] Amérique du nord [Termes IGN] climat [Termes IGN] corrélation [Termes IGN] forêt [Termes IGN] indice de végétation [Termes IGN] photosynthèse [Termes IGN] productivité Numéro de notice : A1988-125 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/0034-4257(88)90034-X En ligne : https://doi.org/10.1016/0034-4257(88)90034-X Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=24704 [article]