Centre de documentation
scientifique

Hyperspectral dimensionality reduction for biophysical variable statistical retrieval / Juan Pablo Rivera-Caicedo in ISPRS Journal of photogrammetry and remote sensing, vol 132 (October 2017)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 132 (October 2017) . - pp 88 - 101 Titre : Hyperspectral dimensionality reduction for biophysical variable statistical retrieval Type de document : Article/Communication Auteurs : Juan Pablo Rivera-Caicedo, Auteur ; Jochem Verrelst, Auteur ; Jordi Munoz-Mari, Auteur ; et al., Auteur Année de publication : 2017 Article en page(s) : pp 88 - 101 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] image HYMAP [Termes IGN] image hyperspectrale [Termes IGN] Leaf Area Index [Termes IGN] régression linéaire [Termes IGN] variable biophysique (végétation) Résumé : (Auteur) Current and upcoming airborne and spaceborne imaging spectrometers lead to vast hyperspectral data streams. This scenario calls for automated and optimized spectral dimensionality reduction techniques to enable fast and efficient hyperspectral data processing, such as inferring vegetation properties. In preparation of next generation biophysical variable retrieval methods applicable to hyperspectral data, we present the evaluation of 11 dimensionality reduction (DR) methods in combination with advanced machine learning regression algorithms (MLRAs) for statistical variable retrieval. Two unique hyperspectral datasets were analyzed on the predictive power of DR + MLRA methods to retrieve leaf area index (LAI): (1) a simulated PROSAIL reflectance data (2101 bands), and (2) a field dataset from airborne HyMap data (125 bands). For the majority of MLRAs, applying first a DR method leads to superior retrieval accuracies and substantial gains in processing speed as opposed to using all bands into the regression algorithm. This was especially noticeable for the PROSAIL dataset: in the most extreme case, using the classical linear regression (LR), validation results (RMSECV) improved from 0.06 (12.23) without a DR method to 0.93 (0.53) when combining it with a best performing DR method (i.e., CCA or OPLS). However, these DR methods no longer excelled when applied to noisy or real sensor data such as HyMap. Then the combination of kernel CCA (KCCA) with LR, or a classical PCA and PLS with a MLRA showed more robust performances ( of 0.93). Gaussian processes regression (GPR) uncertainty estimates revealed that LAI maps as trained in combination with a DR method can lead to lower uncertainties, as opposed to using all HyMap bands. The obtained results demonstrated that, in general, biophysical variable retrieval from hyperspectral data can largely benefit from dimensionality reduction in both accuracy and computational efficiency. Numéro de notice : A2017-640 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2017.08.012 En ligne : https://doi.org/10.1016/j.isprsjprs.2017.08.012 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=86995 [article]

Exemplaires(3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2017101	RAB	Revue	Centre de documentation	En réserve L003	Disponible
081-2017102	DEP-EAF	Revue	Nancy	Dépôt en unité	Exclu du prêt
081-2017103	DEP-EXM	Revue	Saint-Mandé	Dépôt en unité	Exclu du prêt

Determination of robust spectral features for identification of urban surface materials in hyperspectral remote sensing data / U. Heiden in Remote sensing of environment, vol 111 n° 4 (28/12/2007)  

Public [article]  inRemote sensing of environment > vol 111 n° 4 (28/12/2007) . - pp 537 - 552 Titre : Determination of robust spectral features for identification of urban surface materials in hyperspectral remote sensing data Type de document : Article/Communication Auteurs : U. Heiden, Auteur ; Karl Segl, Auteur ; S. Roessner, Auteur ; H. Kaufmann, Auteur Année de publication : 2007 Article en page(s) : pp 537 - 552 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] Allemagne [Termes IGN] extraction automatique [Termes IGN] image HYMAP [Termes IGN] image hyperspectrale [Termes IGN] matrice de confusion [Termes IGN] méthode robuste [Termes IGN] milieu urbain [Termes IGN] surface du sol Résumé : (Auteur) Hyperspectral remote sensing data open up new opportunities for analyzing urban areas characterized by a large variety of spectrally distinct surface materials. Spectroscopic analysis using diagnostic spectral features yields the potential for automated identification and mapping of these materials. This study proposes a new approach for the determination and evaluation of such spectral features that are robust against spectral overlap between material classes and within-class variability. Analysis is based on comprehensive field and image spectral libraries of more than 21,000 spectra of surface materials widely-used in German cities. The robustness of the interactively defined spectral features is evaluated by a separability analysis. This method is performed based on confusion matrices for each material computed from classification results. For comparison this analysis is also performed for material-specific gray values of selected bands. The obtained commission and omission errors show superiority of the spectral features compared to gray values for most of the investigated materials. The results indicate that robust spectral features yield the potential for unsupervised detection of endmembers in hyperspectral image data. Copyright Elsevier Numéro de notice : A2007-521 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.rse.2007.04.008 En ligne : https://doi.org/10.1016/j.rse.2007.04.008 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=28884 [article]

Estimating spatial patterns of rainfall interception from remotely sensed vegetation indices and spectral mixture analysis / S.M. de Jong in International journal of geographical information science IJGIS, vol 21 n° 5 (may 2007)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 21 n° 5 (may 2007) . - pp 529 - 545 Titre : Estimating spatial patterns of rainfall interception from remotely sensed vegetation indices and spectral mixture analysis Type de document : Article/Communication Auteurs : S.M. de Jong, Auteur ; V.G. Jetten, Auteur Année de publication : 2007 Article en page(s) : pp 529 - 545 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] analyse des mélanges spectraux [Termes IGN] érosion hydrique [Termes IGN] évapotranspiration [Termes IGN] image HYMAP [Termes IGN] image hyperspectrale [Termes IGN] indice de végétation [Termes IGN] Leaf Area Index [Termes IGN] pluie [Termes IGN] ruissellement Résumé : (Auteur) Rainfall interception by vegetation is an important factor in the water balance. Consequently, rainfall interception should also be an important factor in models simulating processes such as evaporation, transpiration, surface runoff, soil erosion, and crop growth. In practice, however, it is difficult to make quantitative assessments of the spatial and temporal distribution of rainfall interception loss at the catchment level, for instance, and to make these values available as model input. In this paper, we present a novel method using earth observation images to estimate local quantitative values of rainfall interception loss. Leaf Area Index (LAI) and fractional vegetation cover per grid cell are important process variables for rainfall interception. These two variables are estimated from images using spectral vegetation indices and using spectral mixture analysis, respectively. Relations between canopy storage capacity and LAI exist for several plant species and vegetation types, but limited data are found on crops, and more research is needed in this field. The new method is explained and illustrated for a study area in southern France with a variety of land-cover types. It is found to be a valuable and practical approach to quantitatively assess spatial patterns of interception loss for given rainfall events. Copyright Taylor & Francis Numéro de notice : A2007-135 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1080/13658810601064884 En ligne : https://doi.org/10.1080/13658810601064884 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=28498 [article]

Exemplaires(2)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
079-07031	RAB	Revue	Centre de documentation	En réserve L003	Disponible
079-07032	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Evaluation of hyperspectral remote sensing as a means of environmental monitoring in the St Austell China clay (kaolin) region, Cornwall, UK / R.J. Ellis in Remote sensing of environment, vol 93 n° 1 (30/10/2004)  

Public [article]  inRemote sensing of environment > vol 93 n° 1 (30/10/2004) . - pp 118 - 130 Titre : Evaluation of hyperspectral remote sensing as a means of environmental monitoring in the St Austell China clay (kaolin) region, Cornwall, UK Type de document : Article/Communication Auteurs : R.J. Ellis, Auteur ; P.W. Scott, Auteur Année de publication : 2004 Article en page(s) : pp 118 - 130 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] Argile [Termes IGN] carte géologique [Termes IGN] Cornouailles [Termes IGN] éclairement lumineux [Termes IGN] étalonnage radiométrique [Termes IGN] image HYMAP [Termes IGN] image hyperspectrale [Termes IGN] minerai [Termes IGN] surveillance géologique Résumé : (Auteur) The St. Austell granite of Cornwall, UK contains internationally important deposits of kaolin (china clay), the formation of which result from the alteration of a composite pluton of mineralogically and texturally different primary granite units. To assess the applicability of hyperspectral remote sensing in the St. Austell china clay region, one line of airborne HyMap® hyperspectral data was acquired. These data were processed to correct for atmospheric and illumination effects by calibration from radiance to reflectance data, so that mineral abundance maps could be produced. Minerals associated with the primary granite and its subsequent kaolinisation were identified by image processing and used as mapping endmembers. These minerals include kaolinite, kaolinite with smectite, montmorillonite, muscovite, lepidolite (a lithium mica) and topaz. Hyperspectral data analysis allowed for the identification of the different primary granite units. The spectrally observed compositional differences of the biotite and topaz granite units of the region allowed for fingerprinting of the source of mined waste material as originating from specific pits. The majority of waste tips in the region originate from the nearest china clay workings. However, waste material used in the construction of a mica dam and also as backfill in a disused pit is successfully identified to have been transported across a mapped granite boundary for storage. The effect of mining and mineral processing on the abundance and spatial distribution of minerals in the region is also evident. Wastetips are classified as containing the greatest abundance of mica. This distribution results from the separation of kaolinite during the mineral processing stages. Kaolinite in lower abundance, however, is also identified within these waste areas and is the result of a less than 100% recovery by mining and processing. Numéro de notice : A2004-425 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.rse.2004.07.004 En ligne : https://doi.org/10.1016/j.rse.2004.07.004 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=26952 [article]

Airborne measurement of hot spot reflectance signatures / F. Camacho-De Coca in Remote sensing of environment, vol 90 n° 1 (15/03/2004)  

Public [article]  inRemote sensing of environment > vol 90 n° 1 (15/03/2004) . - pp 63 - 75 Titre : Airborne measurement of hot spot reflectance signatures Type de document : Article/Communication Auteurs : F. Camacho-De Coca, Auteur ; François-Marie Bréon, Auteur ; M. Leroy, Auteur ; F.J. Garcia-Haro, Auteur Année de publication : 2004 Article en page(s) : pp 63 - 75 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] ARAT [Termes IGN] composition colorée [Termes IGN] couvert végétal [Termes IGN] cultures [Termes IGN] distribution du coefficient de réflexion bidirectionnelle BRDF [Termes IGN] Espagne [Termes IGN] image DAIS [Termes IGN] image en couleur composée [Termes IGN] image HYMAP [Termes IGN] image POLDER [Termes IGN] Leaf Area Index [Termes IGN] réflectance végétale [Termes IGN] tâche claire [Termes IGN] transfert radiatif Résumé : (Auteur) The so-called hot spot is a fine directional signature of the surface reflectance observed for phase angles close to zero. In this paper, we analyze and discuss several such signatures acquired from the airborne POLDER and HyMap instruments during the DAISEX'99 campaign over agricultural crops. The observed signatures are very similar to those acquired from space at a resolution of several tens of kilometers [J. Geophys. Res. 107 (2002)], which provides further evidence that the hot spot is a scale-free feature. The hot spots can be fitted by a twoparameter function (amplitude and width) of the phase angle derived from canopy radiative transfer modeling. The model predicts that the amplitude is directly related to the leaf reflectance, while the width is a function of the canopy structure. The retrieved leaf reflectance values over a wide spectral range are in very good agreement with noncoincident laboratory measurement. The retrieved half widths are on the order of 1° with no significant variability between the analyzed targets. There is an apparent spectral variability in the half width, a feature in contradiction with the modeling, although the variations are not larger than the uncertainties. Numéro de notice : A2004-128 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.rse.2003.11.019 En ligne : https://doi.org/10.1016/j.rse.2003.11.019 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=26655 [article]

Integrating imaging spectroscopy and neural networks to map grass quality in the Kruger National Park, South Africa / Onisimo Mutanga in Remote sensing of environment, vol 90 n° 1 (15/03/2004)  

Permalink

A credit assignment approach to fusing classifiers of multiseason hyperspectral imagery / C. Bachmann in IEEE Transactions on geoscience and remote sensing, vol 41 n° 11 (November 2003)  

Permalink

Hyperspectral edge filtering for measuring homogeneity of surface cover types / Wim H. Bakker in ISPRS Journal of photogrammetry and remote sensing, vol 56 n° 4 (July - August 2002)  

Permalink

Etude des relations spécifiques entre végétation et roches du massif de Ronda par télédétection hyperspectrale AVIRIS (1991) et HYMAP (2000) / Guillaume Hallereau (2001)

Permalink