Centre dedocumentation
scientifique

Applying six classifiers to airborne hyperspectral imagery for detecting giant reed / C. Yang in Geocarto international, vol 27 n° 5 (August 2012)  

Public [article]  inGeocarto international > vol 27 n° 5 (August 2012) . - pp 413 - 424 Titre : Applying six classifiers to airborne hyperspectral imagery for detecting giant reed Type de document : Article/Communication Auteurs : C. Yang, Auteur ; J. Goolsby, Auteur ; James H. Everitt, Auteur ; Q. Du, Auteur Année de publication : 2012 Article en page(s) : pp 413 - 424 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse comparative [Termes IGN] classificateur [Termes IGN] classification barycentrique [Termes IGN] classification par la distance de Mahalanobis [Termes IGN] classification par maximum de vraisemblance [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] classification Spectral angle mapper [Termes IGN] espèce exotique envahissante [Termes IGN] Etats-Unis [Termes IGN] image aérienne [Termes IGN] image hyperspectrale [Termes IGN] macrophyte [Termes IGN] Mexique [Termes IGN] Rio Grande (fleuve) Résumé : (Auteur) This study evaluated and compared six image classifiers, including minimum distance (MD), Mahalanobis distance (MAHD), maximum likelihood (ML), spectral angle mapper (SAM), mixture tuned matched filtering (MTMF) and support vector machine (SVM), for detecting and mapping giant reed (Arundo donax L.), an invasive weed that presents a severe threat to agroecosystems throughout the southern US and northern Mexico. Airborne hyperspectral imagery was collected from a giant reed-infested site along the US-Mexican portion of the Rio Grande in 2009 and 2010. The imagery was transformed with minimum noise fraction (MFN) and the six classifiers were applied to the 30-band MNF imagery for each year. Accuracy assessment showed that SVM and ML generally performed better than the other four classifiers for overall classification and for distinguishing giant reed in both years. These results indicate that airborne hyperspectral imagery in conjunction with SVM and ML classification techniques is effective for detecting giant reed. Numéro de notice : A2012-371 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2011.643321 Date de publication en ligne : 04/01/2012 En ligne : https://doi.org/10.1080/10106049.2011.643321 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=31817 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
059-2012051	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Hyperspectral band clustering and band selection for urban land cover classification / H. Su in Geocarto international, vol 27 n° 5 (August 2012)  

Public [article]  inGeocarto international > vol 27 n° 5 (August 2012) . - pp 39 - 411 Titre : Hyperspectral band clustering and band selection for urban land cover classification Type de document : Article/Communication Auteurs : H. Su, Auteur ; Q. Du, Auteur Année de publication : 2012 Article en page(s) : pp 39 - 411 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse de groupement [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] classification semi-dirigée [Termes IGN] image hyperspectrale [Termes IGN] milieu urbain [Termes IGN] occupation du sol [Termes IGN] précision de la classification [Termes IGN] signature spectrale [Termes IGN] valeur aberrante Résumé : (Auteur) The aim of this study is to combine band clustering with band selection for dimensionality reduction of hyperspectral imagery. The performance of dimensionality reduction is evaluated through urban land cover classification accuracy with the dimensionality-reduced data. Different from unsupervised clustering using all the pixels or supervised clustering requiring labelled pixels, the discussed semi-supervised band clustering needs class spectral signatures only; band selection result is used as initial condition for band clustering; after clustering, a cluster selection step is applied to select clusters to be used in the following data analysis. In this article, we propose to conduct band selection by removing outlier bands in each cluster before finalizing cluster centres. The experimental results in urban land cover classification show that the proposed algorithm can further enhance support vector machine (SVM)-based classification accuracy. Numéro de notice : A2012-370 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2011.643322 Date de publication en ligne : 12/01/2012 En ligne : https://doi.org/10.1080/10106049.2011.643322 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=31816 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
059-2012051	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Linear mixture analysis-based compression for hyperspectral image analysis / Q. Du in IEEE Transactions on geoscience and remote sensing, vol 42 n° 4 (April 2004)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 42 n° 4 (April 2004) . - pp 875 - 891 Titre : Linear mixture analysis-based compression for hyperspectral image analysis Type de document : Article/Communication Auteurs : Q. Du, Auteur ; C.I. Chang, Auteur Année de publication : 2004 Article en page(s) : pp 875 - 891 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse d'image numérique [Termes IGN] analyse des mélanges spectraux [Termes IGN] compression de données [Termes IGN] image AVIRIS [Termes IGN] image hyperspectrale Résumé : (Auteur) Due to significantly improved spectral resolution produced by hyperspectral sensors, the hand-to-hand correlation is generally very high and can be removed without loss of crucial information. Data compression is an effective means to eliminate such redundancy resulting from high interband correlation. In hyperspectral imagery, various information comes from different signal sources, which include man-made targets, natural backgrounds, unknown clutters, interferers, unidentified anomalies, etc. In many applications, whether or not a compression technique is effective is measured by the degree of information loss rather than information recovery. For example, compression of noise or interferers is highly desirable to image analysis and interpretation. In this paper, we present an unsupervised fully constrained least squares (UFCLS) linear spectral mixture analysis (LSMA)-based compression technique for hyperspectral target detection and classification. Unlike most compression techniques, which deal directly with grayscale images, the proposed compression approach generates and encodes the fractional abundance images of targets of interest present in an image scene to achieve data compression. Since the vital information used for image analysis is generally preserved and retained in these fractional abundance images, the loss of information may have little impact on image analysis. On some occasions, it even improves performance analysis. Airborne Visible/InfraRed Imaging Spectrometer (AVIRIS) and Hyperspectral Digital Imagery Collection Experiment (HYDICE) data are used for experiments to evaluate our proposed LSMA-based compression technique used for applications in hyperspectral detection and image classification. The classification results using the original data and the UFCLS-decompressed data are shown to be very close with no visible difference. But a compression ratio for the HYDICE data with water bands removed can achieve as high as 138: 1 with peak SNR (PSNR) 33 dB, while a compression ratio of the AVIRIS scene also with water bands removed is 90: 1 with PSNR 40 dB. Numéro de notice : A2004-187 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2003.816668 En ligne : https://doi.org/10.1109/TGRS.2003.816668 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=26714 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-04041	RAB	Revue	Centre de documentation	En réserve L003	Disponible