Centre de documentation
scientifique

Dépouillements

Radial basis function neural networks classification using very high spatial resolution satellite imagery: an application to the habitat area of Lake Kerkini (Greece) / Iphigenia Keramitsoglou in International Journal of Remote Sensing IJRS, vol 26 n° 9 (May 2005)  

Public [article]  inInternational Journal of Remote Sensing IJRS > vol 26 n° 9 (May 2005) . - pp 1861 - 1880 Titre : Radial basis function neural networks classification using very high spatial resolution satellite imagery: an application to the habitat area of Lake Kerkini (Greece) Type de document : Article/Communication Auteurs : Iphigenia Keramitsoglou, Auteur ; H. Sarimveis, Auteur ; et al., Auteur Année de publication : 2005 Article en page(s) : pp 1861 - 1880 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] analyse texturale [Termes IGN] bande spectrale [Termes IGN] classificateur paramétrique [Termes IGN] classification par maximum de vraisemblance [Termes IGN] classification par réseau neuronal [Termes IGN] fonction de base radiale [Termes IGN] Grèce [Termes IGN] image à très haute résolution [Termes IGN] lac Résumé : (Auteur) This study investigates the potential of applying the radial basis function (RBF) neural network architecture for the classification of multispectral very high spatial resolution satellite images into 13 classes of various scales. For the development of the RBF classifiers, the innovative fuzzy means training algorithm is utilized, which is based on a fuzzy partition of the input space. The method requires only a short amount of time to select both the structure and the parameters of the RBF classifier. The new technique was applied to the area of Lake Kerkini, which is a wetland of great ecological value, located in northern Greece. Eleven experiments were carried out in total in order to investigate the performance of the classifier using different input parameters (spectral and textural) as well as different window sizes and neural network complexities. For comparison purposes the same satellite scene was classified using the maximum likelihood (MLH) classification with the same set of training samples. Overall, the neural network classifiers outperformed the MLH classification by 10-17%, reaching a maximum overall accuracy of 78%. Analysis showed that the selection of input parameters is vital for the success of the classifiers. On the other hand, the incorporation of textural analysis and/or modification of the window size do not affect the performance substantially. Numéro de notice : A2005-255 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/01431160512331326594 En ligne : https://doi.org/10.1080/01431160512331326594 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=27391 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
080-05091	RAB	Revue	Centre de documentation	En réserve L003	Exclu du prêt

Spatial accuracy of orthorectified Ikonos imagery and historical aerial photographs across five sites in China / H. Wang in International Journal of Remote Sensing IJRS, vol 26 n° 9 (May 2005)  

Public [article]  inInternational Journal of Remote Sensing IJRS > vol 26 n° 9 (May 2005) . - pp 1893 - 1911 Titre : Spatial accuracy of orthorectified Ikonos imagery and historical aerial photographs across five sites in China Type de document : Article/Communication Auteurs : H. Wang, Auteur ; E.C. Ellis, Auteur Année de publication : 2005 Article en page(s) : pp 1893 - 1911 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse diachronique [Termes IGN] analyse spatio-temporelle [Termes IGN] Chine [Termes IGN] détection de changement [Termes IGN] image à résolution métrique [Termes IGN] image Ikonos [Termes IGN] modèle par fonctions rationnelles [Termes IGN] photographie aérienne [Termes IGN] point d'appui [Termes IGN] précision géométrique (imagerie) Résumé : (Auteur) High-resolution ( 1m) satellite imagery and archival World War 2 era (WW2) aerial photographs are currently available to support high-resolution longterm change measurements at sites across China. A major limitation to these measurements is the spatial accuracy with which this imagery can be orthorectified and co-registered. We orthorectified IKONOS 1m resolution GEO-format imagery and WW2 aerial photographs across five 100km2 rural sites in China with terrain ranging from flat to hilly to mountainous. Ground control points (GCPs) were collected uniformly across 100 km2 IKONOS scenes using a differential Global Positioning Systems (GPS) field campaign. WW2 aerial photos were co-registered to orthorectified IKONOS imagery using bundle block adjustment and rational function models. GCP precision, terrain relief and the number and distribution of GCPs significantly influenced image orthorectification accuracy. Root mean square errors (RMSEs) at GCPs for IKONOS imagery were Numéro de notice : A2005-256 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/01431160512331326684 En ligne : https://doi.org/10.1080/01431160512331326684 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=27392 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
080-05091	RAB	Revue	Centre de documentation	En réserve L003	Exclu du prêt

Satellite remote sensing for detailed landslide inventories using change detection and image fusion / J. Nichol in International Journal of Remote Sensing IJRS, vol 26 n° 9 (May 2005)  

Public [article]  inInternational Journal of Remote Sensing IJRS > vol 26 n° 9 (May 2005) . - pp 1913 - 1926 Titre : Satellite remote sensing for detailed landslide inventories using change detection and image fusion Type de document : Article/Communication Auteurs : J. Nichol, Auteur ; M.S. Wong, Auteur Année de publication : 2005 Article en page(s) : pp 1913 - 1926 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] classification par maximum de vraisemblance [Termes IGN] détection de changement [Termes IGN] effondrement de terrain [Termes IGN] fusion d'images [Termes IGN] image Ikonos [Termes IGN] image multitemporelle [Termes IGN] image SPOT XS [Termes IGN] surveillance géologique Résumé : (Auteur) The availability of high spatial and spectral resolution remote sensing systems may be accompanied by changes in techniques for applying the data if appropriate data processing methodologies can be demonstrated. Landslide monitoring, which requires large areas to be surveyed at a detailed level, has previously been unsatisfactory due to its reliance on air photograph interpretation. This study demonstrates the synergistic use of medium resolution, multitemporal Satellite pour I'Observation de la Terre (SPOT) XS, and fine resolution IKONOS images for landslide inventories. The post-classification comparison method of change detection using the Maximum Likelihood classifier with SPOT XS images was able to detect approximately 70% of landslides, the main omissions being those smaller than approximately half a pixel wide. The visual quality of images obtained from Pan-sharpening of IKONOS images was comparable to that obtainable from 1:10000 scale air photographs, enabling detailed interpretation of landslides and associated environmental features. A methodology combining the two levels of survey is proposed for regional scale landslide monitoring. Numéro de notice : A2005-257 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/01431160512331314047 En ligne : https://doi.org/10.1080/01431160512331314047 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=27393 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
080-05091	RAB	Revue	Centre de documentation	En réserve L003	Exclu du prêt

A quantitative comparison of methods for classifying burned areas with LISS-3 imagery / R.M. Roman-Cuesta in International Journal of Remote Sensing IJRS, vol 26 n° 9 (May 2005)  

Public [article]  inInternational Journal of Remote Sensing IJRS > vol 26 n° 9 (May 2005) . - pp 1979 - 2003 Titre : A quantitative comparison of methods for classifying burned areas with LISS-3 imagery Type de document : Article/Communication Auteurs : R.M. Roman-Cuesta, Auteur ; J. Retana, Auteur ; et al., Auteur Année de publication : 2005 Article en page(s) : pp 1979 - 2003 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] analyse comparative [Termes IGN] analyse multibande [Termes IGN] classificateur paramétrique [Termes IGN] classification dirigée [Termes IGN] image IRS-LISS [Termes IGN] impact sur l'environnement [Termes IGN] incendie de forêt [Termes IGN] surveillance écologique Résumé : (Auteur) Environmental agencies frequently require tools for quick assessments of areas affected by large fires. Remote sensing techniques have been reported as efficient tools to evaluate the effects of fire. However, there exist few quantitative comparisons about the performance of the diverse methods. This study quantitatively evaluated the accuracy of five different techniques, a field survey and four satellite-based techniques, in order to quickly classify a large forest fire that occurred in 1998 in Solsonès (north-east Spain) by means of an IRS LISS-3 image. Three pure classes were determined: burned area, unburned vegetation, and bare soil; along with a non-pure class that we called mixed area. These selected techniques were included into a tree classifier to investigate their partial contribution to the final classification. The most accurate methods when focusing on pure classes were those directly related to the spectral characteristics of the pixel: Reflectance Data and Spectral Unmixing (82% of overall accuracy), versus the poorer performances of Vegetation Indices (70%), Textural measures (72%) and the field survey (68.6%). Since no image processing technique was applied to the Raw Reflectance Data, it can be considered the most cost-effective method, and the tree classifier reinforces its importance. The results of this study reveal that time consuming and expensive methods are not necessarily the most accurate, especially when potentially easily distinguishable classes are involved. Numéro de notice : A2005-258 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/01431160512331299315 En ligne : https://doi.org/10.1080/01431160512331299315 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=27394 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
080-05091	RAB	Revue	Centre de documentation	En réserve L003	Exclu du prêt