Descripteur
Documents disponibles dans cette catégorie (1677)
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
Representative multiple Kernel learning for classification in hyperspectral imagery / Y. Gu in IEEE Transactions on geoscience and remote sensing, vol 50 n° 7 Tome 2 (July 2012)
[article]
Titre : Representative multiple Kernel learning for classification in hyperspectral imagery Type de document : Article/Communication Auteurs : Y. Gu, Auteur ; C. Wang, Auteur ; D. You, Auteur ; et al., Auteur Année de publication : 2012 Article en page(s) : pp 2852 - 2865 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage automatique
[Termes IGN] image hyperspectrale
[Termes IGN] méthode fondée sur le noyauRésumé : (Auteur) Recently, multiple kernel learning (MKL) methods have been developed to improve the flexibility of kernel-based learning machine. The MKL methods generally focus on determining key kernels to be preserved and their significance in optimal kernel combination. Unfortunately, computational demand of finding the optimal combination is prohibitive when the number of training samples and kernels increase rapidly, particularly for hyperspectral remote sensing data. In this paper, we address the MKL for classification in hyperspectral images by extracting the most variation from the space spanned by multiple kernels and propose a representative MKL (RMKL) algorithm. The core idea embedded in the algorithm is to determine the kernels to be preserved and their weights according to statistical significance instead of time-consuming search for optimal kernel combination. The noticeable merits of RMKL consist that it greatly reduces the computational load for searching optimal combination of basis kernels and has no limitation from strict selection of basis kernels like most MKL algorithms do; meanwhile, RMKL keeps excellent properties of MKL in terms of both good classification accuracy and interpretability. Experiments are conducted on different real hyperspectral data, and the corresponding experimental results show that RMKL algorithm provides the best performances to date among several the state-of-the-art algorithms while demonstrating satisfactory computational efficiency. Numéro de notice : A2012-322 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2011.2176341 Date de publication en ligne : 17/01/2012 En ligne : https://doi.org/10.1109/TGRS.2011.2176341 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=31768
in IEEE Transactions on geoscience and remote sensing > vol 50 n° 7 Tome 2 (July 2012) . - pp 2852 - 2865[article]Réservation
Réserver ce documentExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 065-2012071B RAB Revue Centre de documentation En réserve L003 Disponible Tracking-Learning-Detection / Zdenek Kalal in IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI, vol 34 n° 7 (July 2012)
[article]
Titre : Tracking-Learning-Detection Type de document : Article/Communication Auteurs : Zdenek Kalal, Auteur ; Krystian Mikolajczyk, Auteur ; Jiri Matas, Auteur Année de publication : 2012 Article en page(s) : pp 1409 - 1422 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie numérique
[Termes IGN] apprentissage automatique
[Termes IGN] détection de cible
[Termes IGN] poursuite de cible
[Termes IGN] séquence d'imagesRésumé : (auteur) This paper investigates long-term tracking of unknown objects in a video stream. The object is defined by its location and extent in a single frame. In every frame that follows, the task is to determine the object's location and extent or indicate that the object is not present. We propose a novel tracking framework (TLD) that explicitly decomposes the long-term tracking task into tracking, learning, and detection. The tracker follows the object from frame to frame. The detector localizes all appearances that have been observed so far and corrects the tracker if necessary. The learning estimates the detector's errors and updates it to avoid these errors in the future. We study how to identify the detector's errors and learn from them. We develop a novel learning method (P-N learning) which estimates the errors by a pair of “experts”: (1) P-expert estimates missed detections, and (2) N-expert estimates false alarms. The learning process is modeled as a discrete dynamical system and the conditions under which the learning guarantees improvement are found. We describe our real-time implementation of the TLD framework and the P-N learning. We carry out an extensive quantitative evaluation which shows a significant improvement over state-of-the-art approaches. Numéro de notice : A2012-720 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TPAMI.2011.239 En ligne : https://doi.org/10.1109/TPAMI.2011.239 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=84845
in IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI > vol 34 n° 7 (July 2012) . - pp 1409 - 1422[article]Verification of 2D building outlines using oblique airborne images / A. Nyaruhuma in ISPRS Journal of photogrammetry and remote sensing, vol 71 (July 2012)
[article]
Titre : Verification of 2D building outlines using oblique airborne images Type de document : Article/Communication Auteurs : A. Nyaruhuma, Auteur ; Markus Gerke, Auteur ; M. George Vosselman, Auteur ; E.G. Mtalo, Auteur Année de publication : 2012 Article en page(s) : pp 62 - 75 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] arbre aléatoire
[Termes IGN] base de données foncières
[Termes IGN] bâtiment
[Termes IGN] boosting adapté
[Termes IGN] classification de Dempster-Shafer
[Termes IGN] contour
[Termes IGN] image aérienne oblique
[Termes IGN] logique floueRésumé : (Auteur) Oblique airborne images are interesting not only for visualization but also for the acquisition and updating of geo-spatial vector data. This is because side views of vertical structures, such as buildings, are present in those images. In recent years, techniques for automatic verification of building outlines have been proposed. These techniques utilized color, texture and height from vertical images or range data while oblique images contain façade information that can also be used to identify buildings. This paper presents a methodology to verify 2D building outlines in a cadastral dataset by using oblique airborne images. The method searches for clues such as building edges, wall façade edges and texture. The 2D clues in images taken from different perspectives but expected to contain the same wall are transformed to 3D, combined and used for a verification of the particular wall. Unlike methods that use vertical images or LIDAR, walls are verified individually and then the results are combined for the building. We compare three methods for combining wall-based evidence. Experiments using almost 700 buildings show that best results are obtained using Adaptive Boosting where – with a bias for better identification of demolished buildings – 100% of demolished buildings are identified and 91% of existing buildings are confirmed. The other two methods are Random Trees and a variant of the Dempster–Shafer approach combined with fuzzy reasoning and they only show some minor differences to the Adaptive Boosting result. The research as presented in this paper demonstrates the potential of oblique images, but some further work has to be done, including the identification of modified buildings and the extension towards verification of 3D building models. Numéro de notice : A2012-348 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2012.04.007 En ligne : https://doi.org/10.1016/j.isprsjprs.2012.04.007 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=31794
in ISPRS Journal of photogrammetry and remote sensing > vol 71 (July 2012) . - pp 62 - 75[article]Réservation
Réserver ce documentExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 081-2012051 SL Revue Centre de documentation Revues en salle Disponible Comparison of support vector machine, neural network, and CART algorithms for the land-cover classification using limited training data points / Y. Shao in ISPRS Journal of photogrammetry and remote sensing, vol 70 (June 2012)
[article]
Titre : Comparison of support vector machine, neural network, and CART algorithms for the land-cover classification using limited training data points Type de document : Article/Communication Auteurs : Y. Shao, Auteur ; R. Lunetta, Auteur Année de publication : 2012 Article en page(s) : pp 78 - 87 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] analyse comparative
[Termes IGN] analyse diachronique
[Termes IGN] classification dirigée
[Termes IGN] classification et arbre de régression
[Termes IGN] classification par réseau neuronal
[Termes IGN] classification par séparateurs à vaste marge
[Termes IGN] image Terra-MODIS
[Termes IGN] occupation du sol
[Termes IGN] Perceptron multicouche
[Termes IGN] série temporelleRésumé : (Auteur) Support vector machine (SVM) was applied for land-cover characterization using MODIS time-series data. Classification performance was examined with respect to training sample size, sample variability, and landscape homogeneity (purity). The results were compared to two conventional nonparametric image classification algorithms: multilayer perceptron neural networks (NN) and classification and regression trees (CART). For 2001 MODIS time-series data, SVM generated overall accuracies ranging from 77% to 80% for training sample sizes from 20 to 800 pixels per class, compared to 67–76% and 62–73% for NN and CART, respectively. These results indicated that SVM’s had superior generalization capability, particularly with respect to small training sample sizes. There was also less variability of SVM performance when classification trials were repeated using different training sets. Additionally, classification accuracies were directly related to sample homogeneity/heterogeneity. The overall accuracies for the SVM algorithm were 91% (Kappa = 0.77) and 64% (Kappa = 0.34) for homogeneous and heterogeneous pixels, respectively. The inclusion of heterogeneous pixels in the training sample did not increase overall accuracies. Also, the SVM performance was examined for the classification of multiple year MODIS time-series data at annual intervals. Finally, using only the SVM output values, a method was developed to directly classify pixel purity. Approximately 65% of pixels within the Albemarle–Pamlico Basin study area were labeled as “functionally homogeneous” with an overall classification accuracy of 91% (Kappa = 0.79). The results indicated a high potential for regional scale operational land-cover characterization applications. Numéro de notice : A2012-290 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2012.04.001 En ligne : https://doi.org/10.1016/j.isprsjprs.2012.04.001 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=31736
in ISPRS Journal of photogrammetry and remote sensing > vol 70 (June 2012) . - pp 78 - 87[article]Réservation
Réserver ce documentExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 081-2012041 SL Revue Centre de documentation Revues en salle Disponible View generation for multiview maximum disagreement based active learning for hyperspectral image classification / W. Di in IEEE Transactions on geoscience and remote sensing, vol 50 n° 5 Tome 2 (May 2012)
[article]
Titre : View generation for multiview maximum disagreement based active learning for hyperspectral image classification Type de document : Article/Communication Auteurs : W. Di, Auteur ; Melba M. Crawford, Auteur Année de publication : 2012 Article en page(s) : pp 1942 - 1954 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage automatique
[Termes IGN] apprentissage dirigé
[Termes IGN] classification dirigée
[Termes IGN] image AVIRIS
[Termes IGN] image EO1-Hyperion
[Termes IGN] image hyperspectrale
[Termes IGN] regroupement de pointsRésumé : (Auteur) Active learning (AL) seeks to interactively construct a smaller training data set that is the most informative and useful for the supervised classification task. Based on the multiview Adaptive Maximum Disagreement AL method, this study investigates the principles and capability of several approaches for the view generation for hyperspectral data classification, including clustering, random selection, and uniform subset slicing methods, which are then incorporated with dynamic view updating and feature space bagging strategies. Tests on Airborne Visible/Infrared Imaging Spectrometer and Hyperion hyperspectral data sets show excellent performance as compared with random sampling and the simple version support vector machine margin sampling, a state-of-the-art AL method. Numéro de notice : A2012-189 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2011.2168566 En ligne : https://doi.org/10.1109/TGRS.2011.2168566 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=31636
in IEEE Transactions on geoscience and remote sensing > vol 50 n° 5 Tome 2 (May 2012) . - pp 1942 - 1954[article]Réservation
Réserver ce documentExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 065-2012051B RAB Revue Centre de documentation En réserve L003 Disponible An efficient point cloud management method based on a 3D R-tree / J. Gong in Photogrammetric Engineering & Remote Sensing, PERS, vol 78 n° 4 (April 2012)PermalinkAn interactive framework for spatial joins : a statistical approach to data analysis in GIS / S. Alkobaisi in Geoinformatica, vol 16 n° 2 (April 2012)PermalinkAutomatic classification of building types in 3D city models: Using SVMs for semantic enrichment of low resolution building data / A. Henn in Geoinformatica, vol 16 n° 2 (April 2012)PermalinkExploration of information: theoretic arguments for the limited amount of information in a map / J. Bjorke in Cartography and Geographic Information Science, vol 39 n° 2 (April 2012)PermalinkRobust hyperspectral vision-based classification for multi-season weed mapping / Y. Zhang in ISPRS Journal of photogrammetry and remote sensing, vol 69 (April 2012)PermalinkSpatial knowledge acquisition with mobile maps, augmented reality and voice in the context of GPS-based pedestrian navigation: results from a field test / H. Huang in Cartography and Geographic Information Science, vol 39 n° 2 (April 2012)PermalinkUne approche ontologique pour la structuration de données spatio-temporelles de trajectoires : Application à l’étude des déplacements de mammifères marins / W. Mefteh in Revue internationale de géomatique, vol 22 n° 1 (mars - mai 2012)PermalinkDes connaissances pour plus de créativité dans le choix des couleurs de la légende (outil COLorLEGend) / Sidonie Christophe in Cartes & Géomatique, n° 211 (mars 2012)PermalinkMathematical morphology-based generalization of complex 3D building models incorporating semantic relationships / J. Zhao in ISPRS Journal of photogrammetry and remote sensing, vol 68 (March 2012)PermalinkMulti-criteria diagnosis of control knowledge for cartographic generalisation / Patrick Taillandier in European journal of operational research, vol 217 n° 3 ([01/03/2012])PermalinkE.23 - Extraction et gestion des connaissances - EGC 2012, 12es Journées Internationales Francophones (Bulletin de Revue des Nouvelles Technologies de l'Information, E.23 [08/02/2012]) / Yves LechevallierPermalinkRaisonner sur une ontologie cartographique pour concevoir des légendes de cartes / Catherine Dominguès in Revue des Nouvelles Technologies de l'Information, E.23 ([08/02/2012])PermalinkPermalinkPermalinkPermalinkConstruire la légende de la carte à l'aide d'une base de connaissance en cartographie / Catherine Dominguès (2012)PermalinkExtractions de règles concernant les bâtiments d'un corpus de plans locaux d'urbanisme / Leidiana Da Silva Martins (2012)PermalinkFormalisation, acquisition et mise en œuvre de connaissances pour l’intégration virtuelle de bases de données géographiques / Nathalie Abadie (2012)PermalinkIngénierie des connaissances, 23es journées francophones IC 2012 / Sylvie Szulman (2012)PermalinkPermalink