Descripteur
Documents disponibles dans cette catégorie (18)
Ajouter le résultat dans votre panier Affiner la recherche Interroger des sources externes
Etendre la recherche sur niveau(x) vers le bas
A novel transductive SVM for semisupervised classification of remote-sensing images / Lorenzo Bruzzone in IEEE Transactions on geoscience and remote sensing, vol 44 n° 11 Tome 2 (November 2006)
[article]
Titre : A novel transductive SVM for semisupervised classification of remote-sensing images Type de document : Article/Communication Auteurs : Lorenzo Bruzzone, Auteur ; M. Chi, Auteur ; Mattia Marconcini, Auteur Année de publication : 2006 Article en page(s) : pp 3363 - 3373 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image
[Termes IGN] apprentissage dirigé
[Termes IGN] classification par séparateurs à vaste marge
[Termes IGN] classification semi-dirigée
[Termes IGN] reconnaissance automatiqueRésumé : (Auteur) This paper introduces a semisupervised classification method that exploits both labeled and unlabeled samples for addressing ill-posed problems with support vector machines (SVMs). The method is based on recent developments in statistical learning theory concerning transductive inference and in particular transductive SVMs (TSVMs). TSVMs exploit specific iterative algorithms which gradually search a reliable separating hyperplane (in the kernel space) with a transductive process that incorporates both labeled and unlabeled samples in the training phase. Based on an analysis of the properties of the TSVMs presented in the literature, a novel modified TSVM classifier designed for addressing ill-posed remote-sensing problems is proposed. In particular, the proposed technique: 1) is based on a novel transductive procedure that exploits a weighting strategy for unlabeled patterns, based on a time-dependent criterion; 2) is able to mitigate the effects of suboptimal model selection (which is unavoidable in the presence of small-size training sets); and 3) can address multiclass cases. Experimental results confirm the effectiveness of the proposed method on a set of ill-posed remote-sensing classification problems representing different operative conditions. Copyright IEEE Numéro de notice : A2006-527 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2006.877950 En ligne : https://doi.org/10.1109/TGRS.2006.877950 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=28250
in IEEE Transactions on geoscience and remote sensing > vol 44 n° 11 Tome 2 (November 2006) . - pp 3363 - 3373[article]Exemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 065-06111B RAB Revue Centre de documentation En réserve L003 Disponible Automatic 3D object recognition and reconstruction based on neuro-fuzzy modelling / F. Samadzadegan in ISPRS Journal of photogrammetry and remote sensing, vol 59 n° 5 (August - October 2005)
[article]
Titre : Automatic 3D object recognition and reconstruction based on neuro-fuzzy modelling Type de document : Article/Communication Auteurs : F. Samadzadegan, Auteur ; A. Azizi, Auteur ; et al., Auteur Année de publication : 2005 Article en page(s) : pp 255 - 277 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie numérique
[Termes IGN] Allemagne
[Termes IGN] image aérienne
[Termes IGN] image en couleur
[Termes IGN] milieu urbain
[Termes IGN] raisonnement flou
[Termes IGN] reconnaissance automatique
[Termes IGN] reconnaissance d'objets
[Termes IGN] reconstruction 3D
[Termes IGN] réseau neuronal artificiel
[Termes IGN] visualisation 3DRésumé : (Auteur) Three-dimensional object recognition and reconstruction (ORR) is a research area of major interest in computer vision and photogrammetry. Virtual cities, for example, is one of the exciting application fields of ORR which became very popular during the last decade. Natural and man-made objects of cities such as trees and buildings are complex structures and automatic recognition and reconstruction of these objects from digital aerial images but also other data sources is a big challenge. In this paper, a novel approach for object recognition is presented based on neuro-fuzzy modelling. Structural, textural and spectral information is extracted and integrated in a fuzzy reasoning process. The learning capability of neural networks is introduced to the fuzzy recognition process by taking adaptable parameter sets into account which leads to the neuro-fuzzy approach. Object reconstruction follows recognition seamlessly by using the recognition output and the descriptors which have been extracted for recognition. A first successful application of this new ORR approach is demonstrated for the three object classes 'buildings', 'cars' and 'trees' by using aerial colour images of an urban area of the town of Engen in Germany. Copyright ISPRS Numéro de notice : A2005-351 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2005.02.010 En ligne : https://doi.org/10.1016/j.isprsjprs.2005.02.010 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=27487
in ISPRS Journal of photogrammetry and remote sensing > vol 59 n° 5 (August - October 2005) . - pp 255 - 277[article]Exemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 081-05031 SL Revue Centre de documentation Revues en salle Disponible From mobile mapping to telegeoinformatics: paradigm shift in geospatial data acquisition, processing, and management / Dorota A. Grejner-Brzezinska in Photogrammetric Engineering & Remote Sensing, PERS, vol 70 n° 2 (February 2004)
[article]
Titre : From mobile mapping to telegeoinformatics: paradigm shift in geospatial data acquisition, processing, and management Type de document : Article/Communication Auteurs : Dorota A. Grejner-Brzezinska, Auteur ; R. Li, Auteur ; et al., Auteur Année de publication : 2004 Article en page(s) : pp 197 - 210 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Information géographique
[Termes IGN] capteur imageur
[Termes IGN] capteur multibande
[Termes IGN] chambre DTC
[Termes IGN] données lidar
[Termes IGN] géoréférencement direct
[Termes IGN] GPS-INS
[Termes IGN] image multibande
[Termes IGN] modèle 3D de l'espace urbain
[Termes IGN] reconnaissance automatique
[Termes IGN] reconnaissance d'objets
[Termes IGN] SIG nomade
[Termes IGN] système de numérisation mobile
[Termes IGN] télécommunication sans fil
[Termes IGN] télémétrie laser aéroporté
[Termes IGN] télémétrie laser terrestre
[Termes IGN] temps réelRésumé : (Auteur) Technological advances in positioning and imaging sensors, combined with the explosion in wireless mobile communication systems that occurred during the lost decade of the twentieth century, practically redefined and substantially extended the concept of mobile mapping. The advent of the first mobile mapping systems (MMS) in the early 1990s initiated the process of establishing modern, virtually ground-control-free photogrammetry and digital mapping. By the end of the last decade, mobile mapping technology had made remarkable progress, evolving from rather simple land-based systems to more sophisticated, real-time multitasking and multisensor systems, operational in land and airborne environments. New specialized systems, based on modern imaging sensors, such as CCD (charge-coupled device) cameras, lidar (Light Detection and Ranging) and hyperspectral/multispectral scanners, are being developed, aimed at automatic data acquisition for geoinformatics, thematic mapping, land classification, terrain modeling, emergency response, homeland security, etc. This paper provides an overview of the mobile mapping concept, with a special emphasis on the MMS paradigm shift from the post-mission to near-real-time systems that occurred in the past few years. A short review of the direct georeferencing concept is given, and the major techniques (sensors) used for platform georegistration, as well as the primary radiolocation techniques based on wireless networks, are presented. An overview of the major imaging sensors and the importance of multisensor system calibration are also provided. Future perspectives of mobile mapping and its extension towards telegeoinformatics are also discussed. Some examples of mobile geospatial technology used in automatic object recognition, real-time highway centerline mapping, thematic mapping, and city modeling with lidar and multispectral imagery are included. Copyright ASPRS Numéro de notice : A2004-067 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.14358/PERS.70.2.197 En ligne : http://dx.doi.org/10.14358/PERS.70.2.197 Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=26595
in Photogrammetric Engineering & Remote Sensing, PERS > vol 70 n° 2 (February 2004) . - pp 197 - 210[article]An experimental study on content-based image classication for image databases / R.D. Holowczak in IEEE Transactions on geoscience and remote sensing, vol 40 n° 6 (June 2002)
[article]
Titre : An experimental study on content-based image classication for image databases Type de document : Article/Communication Auteurs : R.D. Holowczak, Auteur ; F.J. Artigas, Auteur ; S.A. Chunfang, Auteur ; J.S. Cho, Auteur ; H.S. Stone, Auteur Année de publication : 2002 Article en page(s) : pp 1338 - 1347 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Bases de données localisées
[Termes IGN] base de données d'images
[Termes IGN] classification dirigée
[Termes IGN] image NOAA-AVHRR
[Termes IGN] nébulosité
[Termes IGN] reconnaissance automatique
[Termes IGN] zone d'intérêtRésumé : (Auteur) Current art uses metadata associated with satellite images to facilitate their retrieval from image repositories. Typical metadata are geographic location, time, and data type. Because the metadata do not indicate which regions within an image are obscured by clouds, retrieval with such metadata may produce an image within which the region of interest (ROI) for the user is not visible. We report a system that can automatically determine whether an ROI is visible in the image, and can incorporate this into the metadata for individual images to enhance searching capability. The goal is to annotate each image with metadata regarding a number of ROIs. An experiment with the system annotated 236 advanced very high resolution radiometer (AVHRR) images of the North Atlantic from a flvemonth viewing period with descriptors that expressed the visibility of an ROI centered on Long Island, NY. For ground truth, we used the classifications of three human subjects to determine visibility of the same region of interest, and labeled the ROI with the majority decision of the three subjects. Partial cloud cover made the human determination subjective, and resulted in disagreements among the subjects. Using randomly selected training subsets of the images, we found the two images whose regions were most like those in images for which the Long Island region was visible. For training subsets, the descriptors derived from the two best images produced average recall and precision retrieval results jointly in the 75% to 80% region. Descriptors derived from those same two images for the test subsets also produced average recall and precision results that jointly fell in the 75% to 80% region. Numéro de notice : A2002-191 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2002.800751 Date de publication en ligne : 02/08/2002 En ligne : https://doi.org/10.1109/TGRS.2002.800751 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=22106
in IEEE Transactions on geoscience and remote sensing > vol 40 n° 6 (June 2002) . - pp 1338 - 1347[article]Exemplaires(2)
Code-barres Cote Support Localisation Section Disponibilité 065-02061 RAB Revue Centre de documentation En réserve L003 Disponible 065-02062 RAB Revue Centre de documentation En réserve L003 Disponible A framework for automatic recognition of spatial features from mobile mapping imagery / Z. Tu in Photogrammetric Engineering & Remote Sensing, PERS, vol 68 n° 3 (March 2002)
[article]
Titre : A framework for automatic recognition of spatial features from mobile mapping imagery Type de document : Article/Communication Auteurs : Z. Tu, Auteur ; R. Li, Auteur Année de publication : 2002 Article en page(s) : pp 267 - 276 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie numérique
[Termes IGN] axiome de Bayes
[Termes IGN] chaîne de Markov
[Termes IGN] méthode de Monte-Carlo
[Termes IGN] méthode robuste
[Termes IGN] objet géographique
[Termes IGN] objet géographique 3D
[Termes IGN] point de fuite
[Termes IGN] processus stochastique
[Termes IGN] reconnaissance automatique
[Termes IGN] reconnaissance de formes
[Termes IGN] système de numérisation mobileRésumé : (Auteur) Mobile mapping is a new technology for capturing georeferenced data. It is, however, still not practical to extract spatial and attribute information of objects such as infrastructure elements fully automatically. In this article, a new framework for 3D object recognition by hypothesis-and-test techniques is proposed and developed. An example of traffic-light recognition from mobile mapping images is given in detail. The hypothesis is generated according to the viewpoint dependent theory. We formulate the hypothesis test problem based on Bayesion inference and, in particular, the MAP (Maximize A Posteriori Probability). This approach functions in two major steps: (1) generation of hot-spot maps by vanishing point detection and template matching, and (2) estimation of the parameters of 3D objects (traffic lights) by Markov Chain Monte Carlo (MCMC). The developed hot-spot map generation method is, in general, faster than general color image segmentation algorithms. For example, it can handle the recognition problem with a color image of 720 by 400 pixels within a couple of minutes rather than tens of minutes to even hours when using the segmentation algorithms. The parameter estimation method uses mcmc to simulate an ergodic stochastic process so that a robust and global optimal solution can be found. The approach shows great potential for automatic object recognition in image sequences acquired by mobile mapping systems. Numéro de notice : A2002-030 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : sans En ligne : https://www.asprs.org/wp-content/uploads/pers/2002journal/march/2002_mar_267-276 [...] Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=21947
in Photogrammetric Engineering & Remote Sensing, PERS > vol 68 n° 3 (March 2002) . - pp 267 - 276[article]Workshop 12 Knowledge discovery from temporal and spatial data / Christophe Dousson (2002)PermalinkEuroconférence GIS, SIG / Euroconference SIG (1995)PermalinkFour theses / Ulf Almroth (1991)PermalinkUne approche de la reconnaissance automatique de l'écriture manuscrite et théories cognitives de la lecture / Claude Parisse (16/11/1987)Permalink