Descripteur
Documents disponibles dans cette catégorie (122)
Ajouter le résultat dans votre panier
Visionner les documents numériques
Affiner la recherche Interroger des sources externes
Etendre la recherche sur niveau(x) vers le bas
Combining spectral and spatial information into hidden Markov models for unsupervised image classification / B. Tso in International Journal of Remote Sensing IJRS, vol 26 n° 10 (May 2005)
[article]
Titre : Combining spectral and spatial information into hidden Markov models for unsupervised image classification Type de document : Article/Communication Auteurs : B. Tso, Auteur ; C. Olsen, Auteur Année de publication : 2005 Article en page(s) : pp 2113 - 2133 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image
[Termes IGN] classification barycentrique
[Termes IGN] classification contextuelle
[Termes IGN] classification non dirigée
[Termes IGN] données localisées 2D
[Termes IGN] image multi sources
[Termes IGN] modèle de Markov
[Termes IGN] optimisation (mathématiques)
[Termes IGN] précision de la classification
[Termes IGN] qualité des donnéesRésumé : (Auteur) Unsupervised classification methodology applied to remote sensing image processing can provide benefits in automatically converting the raw image data into useful information so long as higher classification accuracy is achieved. The traditional k-means clustering scheme using spectral data alone does not perform well in general as far as accuracy is concerned. This is partly due to the failure to take the spatial inter-pixels dependencies (i.e. the context) into account, resulting in a 'busy' visual appearance to the output imagery. To address this, the hidden Markov models (HMM) are introduced in this study as a fundamental framework to incorporate both the spectral and contextual information in analysis. This helps generate more patch-like output imagery and produces higher classification accuracy in an unsupervised scheme. The newly developed unsupervised classification approach is based on observation-sequence and observation-density adjustments, which have been proposed for incorporating 2D spatial information into the linear HMM. For the observation-sequence adjustment methods, there are a total of five neighbourhood systems being proposed. Two neighbourhood systems were incorporated into the observation-density methods for study. The classification accuracy is then evaluated by means of confusion matrices made by randomly chosen test samples. The classification obtained by k-means clustering and the HMM with commonly seen strip-like and Hilbert-Peano sequence fitting methods were also measured. Experimental results showed that the proposed approaches for combining both the spectral and spatial information into HMM unsupervised classification mechanism present improvements in both classification accuracy and visual qualities. Numéro de notice : A2005-259 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/01431160512331337844 En ligne : https://doi.org/10.1080/01431160512331337844 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=27395
in International Journal of Remote Sensing IJRS > vol 26 n° 10 (May 2005) . - pp 2113 - 2133[article]Réservation
Réserver ce documentExemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité 080-05101 RAB Revue Centre de documentation En réserve L003 Disponible Representing and reducing error in natural-resource classification using model combination / Zhi Huang in International journal of geographical information science IJGIS, vol 19 n° 5 (may 2005)
[article]
Titre : Representing and reducing error in natural-resource classification using model combination Type de document : Article/Communication Auteurs : Zhi Huang, Auteur Année de publication : 2005 Article en page(s) : pp 603 - 621 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image
[Termes IGN] analyse comparative
[Termes IGN] classification de Dempster-Shafer
[Termes IGN] classification par arbre de décision
[Termes IGN] classification par réseau neuronal
[Termes IGN] erreur d'attribut
[Termes IGN] erreur d'échantillon
[Termes IGN] précision de la classification
[Termes IGN] propagation d'erreur
[Termes IGN] ressources naturellesRésumé : (Auteur) Artificial Intelligence (AI) models such as Artificial Neural Networks (ANNs), Decision Trees and Dempster-Shafer's Theory of Evidence have long claimed to be more error-tolerant than conventional statistical models, but the way error is propagated through these models is unclear. Two sources of error have been identified in this study: sampling error and attribute error. The results show that these errors propagate differently through the three AI models. The Decision Tree was the most affected by error, the Artificial Neural Network was less affected by error, and the Theory of Evidence model was not affected by the errors at all. The study indicates that AI models have very different modes of handling errors. In this case, the machine-learning models, including ANNs and Decision Trees, are more sensitive to input errors. Dempster-Shafer's Theory of Evidence has demonstrated better potential in dealing with input errors when multisource data sets are involved. The study suggests a strategy of combining AI models to improve classification accuracy. Several combination approaches have been applied, based on a 'majority voting system', a simple average, Dempster-Shafer's Theory of Evidence, and fuzzy-set theory. These approaches all increased classification accuracy to some extent. Two of them also demonstrated good performance in handling input errors. Second-stage combination approaches which use statistical evaluation of the initial combinations are able to further improve classification results. One of these second-stage combination approaches increased the overall classification accuracy on forest types to 54% from the original 46.5% of the Decision Tree model, and its visual appearance is also much closer to the ground data. By combining models, it becomes possible to calculate quantitative confidence measurements for the classification results, which can then serve as a better error representation. Final classification products include not only the predicted hard classes for individual cells, but also estimates of the probability and the confidence measurements of the prediction. Numéro de notice : A2005-239 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1080/13658810500032446 En ligne : https://doi.org/10.1080/13658810500032446 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=27376
in International journal of geographical information science IJGIS > vol 19 n° 5 (may 2005) . - pp 603 - 621[article]Réservation
Réserver ce documentExemplaires (2)
Code-barres Cote Support Localisation Section Disponibilité 079-05051 RAB Revue Centre de documentation En réserve L003 Disponible 079-05052 RAB Revue Centre de documentation En réserve L003 Disponible A comparison of local variance, fractal dimension, and Moran's index as aids to multispectral image classification / C.W. Emerson in International Journal of Remote Sensing IJRS, vol 26 n° 8 (April 2005)
[article]
Titre : A comparison of local variance, fractal dimension, and Moran's index as aids to multispectral image classification Type de document : Article/Communication Auteurs : C.W. Emerson, Auteur ; N. Siu-Ngan Lam, Auteur ; D.A. Quattrochi, Auteur Année de publication : 2005 Article en page(s) : pp 1575 - 1588 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] analyse comparative
[Termes IGN] Atlanta (Géorgie)
[Termes IGN] autocorrélation spatiale
[Termes IGN] classification par maximum de vraisemblance
[Termes IGN] ERDAS Imagine
[Termes IGN] image Landsat-ETM+
[Termes IGN] image multibande
[Termes IGN] milieu urbain
[Termes IGN] occupation du sol
[Termes IGN] précision de la classification
[Termes IGN] segmentation d'image
[Termes IGN] texture d'imageRésumé : (Auteur) The accuracy of traditional multispectral maximum-likelihood image classification is limited by the multi-modal statistical distributions of digital numbers from the complex, heterogenous mixture of land cover types in urban areas. This work examines the utility of local variance, fractal dimension and Moran's I index of spatial autocorrelation in segmenting multispectral satellite imagery with the goal of improving urban land cover classification accuracy. Tools available in the ERDAS Imagine™ software package and the Image Characterization and Modeling System (ICAMS) were used to analyse Landsat ETM+ imagery of Atlanta, Georgia. Images were created from the ETM+ panchromatic band using the three texture indices. These texture images were added to the stack of multispectral bands and classified using a supervised, maximum likelihood technique. Although each texture band improved the classification accuracy over a multispectral only effort, the addition of fractal dimension measures is particularly effective at resolving land cover classes within urbanized areas, as compared to per-pixel spectral classification techniques. Numéro de notice : A2005-204 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/01431160512331326765 En ligne : https://doi.org/10.1080/01431160512331326765 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=27341
in International Journal of Remote Sensing IJRS > vol 26 n° 8 (April 2005) . - pp 1575 - 1588[article]Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité 080-05081 RAB Revue Centre de documentation En réserve L003 Exclu du prêt The utility of texture analysis to improve per-pixel classification for high to very high spatial resolution imagery / Anne Puissant in International Journal of Remote Sensing IJRS, vol 26 n° 4 (February 2005)
[article]
Titre : The utility of texture analysis to improve per-pixel classification for high to very high spatial resolution imagery Type de document : Article/Communication Auteurs : Anne Puissant, Auteur ; Jacky Hirsch, Auteur ; Christiane Weber, Auteur Année de publication : 2005 Article en page(s) : pp 733 - 745 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image
[Termes IGN] analyse texturale
[Termes IGN] classification automatique
[Termes IGN] extraction automatique
[Termes IGN] image à haute résolution
[Termes IGN] image à très haute résolution
[Termes IGN] milieu urbain
[Termes IGN] précision de la classification
[Termes IGN] précision géométrique (imagerie)Résumé : (Auteur) Earth observation data are becoming available at increasingly finer resolutions. Sensors already in existence (IKONOS, Quickbird, SPOT 5, Orbview) or due to be launched in the near future will reach 1-5 m resolution. These very high resolution (VHR) data will provide more details of the urban areas, but it seems evident that they will create additional problems in terms of information extraction using automatic classification. In this framework, this paper examines the potential of the spectral/textural approach to improve the classification accuracy of intra-urban land cover types. The utility of the textural analysis was measured in comparison with multi-spectral per-pixel classifications. Haralick's second-order statistics were applied to the co-occurrence matrix. Four texture indices with six window sizes created from panchromatic images were tested on images at high to very high resolutions (10-1 m). The results show that the optimal index improving the global classification accuracy is the homogeneity measure, with a 7 x 7 window size. Moreover, for 1 m images, texture measure of homogeneity allows one to decrease the shadows. Numéro de notice : A2005-053 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/01431160512331316838 En ligne : https://doi.org/10.1080/01431160512331316838 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=27191
in International Journal of Remote Sensing IJRS > vol 26 n° 4 (February 2005) . - pp 733 - 745[article]Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité 080-05041 RAB Revue Centre de documentation En réserve L003 Exclu du prêt Segmentation and classification of airborne laser scanner data / George Sithole (2005)
Titre : Segmentation and classification of airborne laser scanner data Type de document : Monographie Auteurs : George Sithole, Auteur Editeur : Delft : Netherlands Geodetic Commission NGC Année de publication : 2005 Collection : Netherlands Geodetic Commission Publications on Geodesy, ISSN 0165-1706 num. 59 Importance : 184 p. Format : 17 x 24 cm ISBN/ISSN/EAN : 978-90-6132-292-4 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie
[Termes IGN] algorithme de filtrage
[Termes IGN] classification dirigée
[Termes IGN] données lidar
[Termes IGN] données localisées 3D
[Termes IGN] milieu urbain
[Termes IGN] précision de la classification
[Termes IGN] segmentation
[Termes IGN] semis de points
[Termes IGN] télémétrie laser aéroportéIndex. décimale : 35.20 Traitement d'image Résumé : (Auteur) Various methods have been developed to measure the physical presence of objects in a landscape with high positional accuracy, such as Airborne Laser Scanning (ALS). [...] The product of ALS is a cloud of points in 3D space. ALS is capable of delivering very dense and accurate point clouds of a landscape in a relatively short time. [...] However, the automatic detection and interpretation of individual objects remains a challenge. [...] Several algorithms have been developed to automatically detect the bare earth in ALS point clouds. An experimental study of filtering algorithms determined that in flat and uncomplicated landscapes, algorithms tend to do well. Significant differences in accuracies of filtering appear in landscapes containing steep slopes and discontinuties. These differences are a result of the ability of algorithms to preserve discontinuties while detecting large objects. A solution for this problem was determined to lie in the segmentation of ALS point clouds. If segmentation can be achieved in such a manner that all bare earth points are gathered into their own surface segments, then filtering can be done on the basis of surfaces rather than points. This should offer a more reliable classification since topological information can be used in addition to geometric information to classify surface segments. On the strenght of the study, a new segmentation based filtering algorithm was developed. [...] Numéro de notice : 13237 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Monographie Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=54926 Réservation
Réserver ce documentExemplaires (2)
Code-barres Cote Support Localisation Section Disponibilité 13237-01 35.20 Livre Centre de documentation Télédétection Disponible 13237-02 35.20 Livre Centre de documentation Télédétection Disponible Spatial data quality / P. Van Oort (2005)PermalinkThe development of superspectral approaches for the improvement of land cover classification / M. Gianinetto in IEEE Transactions on geoscience and remote sensing, vol 42 n° 11 (November 2004)PermalinkSpatial variability in classification accuracy of agricultural crops in the Dutch national land-cover database / A.J.W. Van Oort in International journal of geographical information science IJGIS, vol 18 n° 6 (october 2004)PermalinkWavelet for urban spatial feature discrimination: comparisons with fractal, spatial autocorrelation, and spatial co-occurrence approaches / Nina S.N. Lam in Photogrammetric Engineering & Remote Sensing, PERS, vol 70 n° 7 (July 2004)PermalinkExamining the effect of spatial resolution and texture window size on classification accuracy: an urban environment case / D. Chen in International Journal of Remote Sensing IJRS, vol 25 n° 11 (June 2004)PermalinkSub-pixel mapping and sub-pixel sharpening using neural network predicted wavelet coefficients / K.C. Mertens in Remote sensing of environment, vol 91 n° 2 (30/05/2004)PermalinkNonparametric weighted feature extraction for classification / D.A. Landgrebe in IEEE Transactions on geoscience and remote sensing, vol 42 n° 5 (May 2004)PermalinkThematic map comparison: evaluating the statistical significance of differences in classification accuracy / Giles M. Foody in Photogrammetric Engineering & Remote Sensing, PERS, vol 70 n° 5 (May 2004)PermalinkClassification of remotely sensed imagery stochastic gradient boosting as a refinement of classification tree analysis / R. Lawrence in Remote sensing of environment, vol 90 n° 3 (15/04/2004)PermalinkUsing quadtree segmentation to support error modelling in categorical raster data / S. De Bruin in International journal of geographical information science IJGIS, vol 18 n° 2 (march 2004)Permalink