Centre de documentation
scientifique

Dépouillements

Remote sensing image segmentation by combining spectral and texture features / H. Li in IEEE Transactions on geoscience and remote sensing, vol 52 n° 1 tome 1 (January 2014)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 52 n° 1 tome 1 (January 2014) . - pp 16 - 16 Titre : Remote sensing image segmentation by combining spectral and texture features Type de document : Article/Communication Auteurs : H. Li, Auteur Année de publication : 2014 Article en page(s) : pp 16 - 16 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse combinatoire (maths) [Termes IGN] appariement d'histogramme [Termes IGN] image spectrale [Termes IGN] segmentation d'image [Termes IGN] texture d'image [Termes IGN] valeur radiométrique Résumé : (Auteur) We present a new method for remote sensing image segmentation, which utilizes both spectral and texture information. Linear filters are used to provide enhanced spatial patterns. For each pixel location, we compute combined spectral and texture features using local spectral histograms, which concatenate local histograms of all input bands. We regard each feature as a linear combination of several representative features, each of which corresponds to a segment. Segmentation is given by estimating combination weights, which indicate segment ownership of pixels. We present segmentation solutions where representative features are either known or unknown. We also show that feature dimensions can be greatly reduced via subspace projection. The scale issue is investigated, and an algorithm is presented to automatically select proper scales, which does not require segmentation at multiple-scale levels. Experimental results demonstrate the promise of the proposed method. Numéro de notice : A2014-034 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2012.2234755 En ligne : https://doi.org/10.1109/TGRS.2012.2234755 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=32939 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-2014011A	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Patch-based information reconstruction of cloud-contaminated multitemporal images / Chao-Hung Lin in IEEE Transactions on geoscience and remote sensing, vol 52 n° 1 tome 1 (January 2014)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 52 n° 1 tome 1 (January 2014) . - pp 163 - 174 Titre : Patch-based information reconstruction of cloud-contaminated multitemporal images Type de document : Article/Communication Auteurs : Chao-Hung Lin, Auteur ; Kang-Hua Lai, Auteur ; Zhi-Bin Chen, Auteur ; Jyun-Yuan Chen, Auteur Année de publication : 2014 Article en page(s) : pp 163 - 174 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] cohérence (physique) [Termes IGN] corrélation [Termes IGN] image Landsat-ETM+ [Termes IGN] image multitemporelle [Termes IGN] manteau neigeux Résumé : (Auteur) Cloud covers, which are generally present in optical remote sensing images, limit the usage of acquired images and increase the difficulty in data analysis. Thus, information reconstruction of cloud-contaminated images generally plays an important role in image analysis. This paper proposes a novel method to reconstruct cloud-contaminated information in multitemporal remote sensing images. Based on the concept of utilizing temporal correlation of multitemporal images, we propose a patch-based information reconstruction algorithm that spatiotemporally segments a sequence of images into clusters containing several spatially connected components called patches and then clones information from cloud-free and high-similarity patches to their corresponding cloud-contaminated patches. In addition, a seam that passes through homogenous regions is used in information reconstruction to reduce radiometric inconsistency, and information cloning is solved using an optimization process with the determined seam. These processes enable the proposed method to well reconstruct missing information. Qualitative analyses of image sequences acquired by a Landsat-7 Enhanced Thematic Mapper Plus (ETM+) sensor and a quantitative analysis of simulated data with various cloud contamination conditions are conducted to evaluate the proposed method. The experimental results demonstrate the superiority of the proposed method to related methods in terms of radiometric accuracy and consistency, particularly for large clouds in a heterogeneous landscape. Numéro de notice : A2014-035 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2012.2237408 En ligne : https://doi.org/10.1109/TGRS.2012.2237408 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=32940 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-2014011A	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Hyperspectral image classification using nearest feature line embedding approach / Yang-Lang Chang in IEEE Transactions on geoscience and remote sensing, vol 52 n° 1 tome 1 (January 2014)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 52 n° 1 tome 1 (January 2014) . - pp 278 - 287 Titre : Hyperspectral image classification using nearest feature line embedding approach Type de document : Article/Communication Auteurs : Yang-Lang Chang, Auteur ; Jan-Nan Liu, Auteur ; Chin-Chuan Han, Auteur ; Ying-Nong Chen, Auteur Année de publication : 2014 Article en page(s) : pp 278 - 287 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse comparative [Termes IGN] analyse discriminante [Termes IGN] classification barycentrique [Termes IGN] classification dirigée [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] image AVIRIS [Termes IGN] image hyperspectrale [Termes IGN] image MASTER [Termes IGN] Indiana (Etats-Unis) [Termes IGN] occupation du sol [Termes IGN] réduction géométrique Résumé : (Auteur) Eigenspace projection methods are widely used for feature extraction from hyperspectral images (HSI) for the classification of land cover. Projection transformation is used to reduce higher dimensional feature vectors to lower dimensional vectors for more accurate classification of land cover types. In this paper, a nearest feature line embedding (NFLE) transformation is proposed for the dimension reduction (DR) of an HSI. The NFL measurement is embedded in the transformation during the discriminant analysis phase, instead of the matching phase. Three factors, including class separability, neighborhood structure preservation, and NFL measurement, are considered simultaneously to determine an effective and discriminating transformation in the eigenspaces for land cover classification. Three state-of-the-art classifiers, the nearest-neighbor, support vector machine, and NFL classifiers, were used to classify the reduced features. The proposed NFLE transformation is compared with different feature extraction approaches and evaluated using two benchmark data sets, the MASTER set at Au-Ku and the AVIRIS set at Northwest Tippecanoe County. The experimental results demonstrate that the NFLE approach is effective for DR in land cover classification in the field of Earth remote sensing. Numéro de notice : A2014-036 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2013.2238635 En ligne : https://doi.org/10.1109/TGRS.2013.2238635 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=32941 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-2014011A	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Restoration of information obscured by mountainous shadows through Landsat TM/ETM+ images without the use of DEM data : A new method / Yuan Zhou in IEEE Transactions on geoscience and remote sensing, vol 52 n° 1 tome 1 (January 2014)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 52 n° 1 tome 1 (January 2014) . - pp 313 - 328 Titre : Restoration of information obscured by mountainous shadows through Landsat TM/ETM+ images without the use of DEM data : A new method Type de document : Article/Communication Auteurs : Yuan Zhou, Auteur ; Jin Chen, Auteur ; Qinghua Guo, Auteur ; et al., Auteur Année de publication : 2014 Article en page(s) : pp 313 - 328 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] image Landsat-ETM+ [Termes IGN] image Landsat-TM [Termes IGN] montagne [Termes IGN] ombre [Termes IGN] pixel [Termes IGN] plus proche voisin, algorithme du [Termes IGN] restauration d'image [Termes IGN] valeur radiométrique Résumé : (Auteur) Shadows in remotely sensed imagery occur when objects totally or partially occlude direct light from a source of illumination, generating great difficulty in land cover interpretation and classification because of the loss of spectral information of shaded pixels. In a mountainous environment with rough terrain, shadows are especially pronounced due to the differentiation of direct illumination between sunny and shady slopes. Topographic correction methods, which are widely used to adjust for differences in solar incidence angles, can partly alleviate the impacts of shadows. However, there are two limitations: one is that the contemporary topographic corrections have little effect on areas that have very low incidence angles and areas that are completely without direct solar illumination (cast shadow); another is that their effectiveness is restricted by the data quality and completeness, spatial resolution, and elevation accuracy of the Digital Elevation Model (DEM) data, which is not currently available in all parts of the world. Thus, noise and errors may be introduced in topographic correction during resampling and geometric registration of the target image. This paper proposes a new approach to restore the radiometric information of mountainous cast shadows using a spectral processing technique called “continuum removal” (CR) without the aid of DEM. The CR-based approach makes full use of the spectral information derived from both the shaded pixels and their neighboring nonshaded pixels of the same land cover type. Several Landsat TM images were used to assess the performance of the proposed method. Results indicated that the proposed method can effectively restore the spectral values of shaded pixels more accurately than the ATCOR_3 correction method, especially for very low incidence angle areas and cast shadows. By comparing data values of shaded pixels with nonshaded pixels (pure reference pixels) of their same class, images processed by the proposed method had the lowest average root mean square error (RMSE) between them in visible, NIR and SWIR bands, followed by the ATCOR_3 correction method and the original image. In addition, the proposed method achieved the best classification accuracy, higher than those from the original test image and the ATCOR_3 corrected image generated using 90 m or 30 m spatial resolution DEM. Therefore, the Continuum Removal method is a better alternative for restoring objects obscured by mountainous shadow when adequate DEM data are unavailable and the quality of DEM cannot satisfy the requirements of topographic correction algorithms. Numéro de notice : A2014-037 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2013.2239651 En ligne : https://doi.org/10.1109/TGRS.2013.2239651 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=32942 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-2014011A	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Collaborative sparse regression for hyperspectral unmixing / Marian-Daniel Iordache in IEEE Transactions on geoscience and remote sensing, vol 52 n° 1 tome 1 (January 2014)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 52 n° 1 tome 1 (January 2014) . - pp 341 - 354 Titre : Collaborative sparse regression for hyperspectral unmixing Type de document : Article/Communication Auteurs : Marian-Daniel Iordache, Auteur ; José Bioucas-Dias, Auteur ; Antonio J. Plaza, Auteur Année de publication : 2014 Article en page(s) : pp 341 - 354 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] accentuation d'image [Termes IGN] analyse des mélanges spectraux [Termes IGN] image hyperspectrale [Termes IGN] régression Résumé : (Auteur) Sparse unmixing has been recently introduced in hyperspectral imaging as a framework to characterize mixed pixels. It assumes that the observed image signatures can be expressed in the form of linear combinations of a number of pure spectral signatures known in advance (e.g., spectra collected on the ground by a field spectroradiometer). Unmixing then amounts to finding the optimal subset of signatures in a (potentially very large) spectral library that can best model each mixed pixel in the scene. In this paper, we present a refinement of the sparse unmixing methodology recently introduced which exploits the usual very low number of endmembers present in real images, out of a very large library. Specifically, we adopt the collaborative (also called “multitask” or “simultaneous”) sparse regression framework that improves the unmixing results by solving a joint sparse regression problem, where the sparsity is simultaneously imposed to all pixels in the data set. Our experimental results with both synthetic and real hyperspectral data sets show clearly the advantages obtained using the new joint sparse regression strategy, compared with the pixelwise independent approach. Numéro de notice : A2014-038 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2013.2240001 En ligne : https://doi.org/10.1109/TGRS.2013.2240001 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=32943 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-2014011A	RAB	Revue	Centre de documentation	En réserve L003	Disponible