Descripteur
Documents disponibles dans cette catégorie (33)
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
Feature extractions for small sample size classification problem / B.C. Kuo in IEEE Transactions on geoscience and remote sensing, vol 45 n° 3 (March 2007)
[article]
Titre : Feature extractions for small sample size classification problem Type de document : Article/Communication Auteurs : B.C. Kuo, Auteur ; K.Y. Chang, Auteur Année de publication : 2007 Article en page(s) : pp 756 - 764 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image
[Termes IGN] algorithme génétique
[Termes IGN] classification dirigée
[Termes IGN] décomposition du pixel
[Termes IGN] détection de contours
[Termes IGN] reconnaissance de formes
[Termes IGN] valeur propreRésumé : (Auteur) Much research has shown that the definitions of within-class and between-class scatter matrices and regularization technique are the key components to design a feature extraction for small sample size problems. In this paper, we illustrate the importance of another key component, eigenvalue decomposition method, and a new regularization technique was proposed. In the hyperspectral image experiment, the effects of these three components of feature extraction are explored on ill-posed and poorly posed conditions. The experimental results show that different regularization methods need to cooperate with different eigenvalue decomposition methods to reach the best performance, the proposed regularization method, regularized feature extraction (RFE) outperform others, and the best feature extraction for a small sample size classification problem is RFE with nonparametric weighted scatter matrices. Numéro de notice : A2007-088 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2006.885074 En ligne : https://doi.org/10.1109/TGRS.2006.885074 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=28453
in IEEE Transactions on geoscience and remote sensing > vol 45 n° 3 (March 2007) . - pp 756 - 764[article]Réservation
Réserver ce documentExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 065-07031 RAB Revue Centre de documentation En réserve L003 Disponible Detecting roads in stabilized video with the spatio-temporal structure tensor / R. Plessl in Geoinformatica, vol 10 n° 1 (March - May 2006)
[article]
Titre : Detecting roads in stabilized video with the spatio-temporal structure tensor Type de document : Article/Communication Auteurs : R. Plessl, Auteur Année de publication : 2006 Conférence : ACM GIS 2004, 12th ACM symposium on geographic information systems 12/11/2004 13/11/2004 Arlington Etats-Unis Selected papers Article en page(s) : pp 37 - 53 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image
[Termes IGN] capteur aérien
[Termes IGN] données spatiotemporelles
[Termes IGN] extraction du réseau routier
[Termes IGN] géoréférencement
[Termes IGN] image vidéo
[Termes IGN] mise à jour de base de données
[Termes IGN] temps réel
[Termes IGN] tenseur
[Termes IGN] trafic routier
[Termes IGN] valeur propreRésumé : (Auteur) Video provides strong cues for automatic road extraction that are not available in static aerial images. In video from a static camera, or stabilized (or geo-referenced) aerial video data, motion patterns within a scene enable fonction attribution of scene regions. A "road," for example, may be defined as a path of consistent motion - a definition which is valid in a large and diverse set of environments. The spatio-temporal structure tensor field is an ideal representation of the image derivative distribution at each pixel because it can be updated in real time as video is acquired. An eigen-decomposition of the structure tensor encodes both the local scene motion and the variability in the motion. Additionally, the structure tensor field can be factored into motion components, allowing explicit determination of traffic patterns in intersections. Example results of a real time system are shown for an urban scene with both well-traveled and infrequently traveled roads, indicating that both can be discovered simultaneously. The method is ideal in urban traffic scenes, which are the most difficult to analyze using static imagery. Numéro de notice : A2006-097 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1007/s10707-005-4885-x En ligne : https://doi.org/10.1007/s10707-005-4885-x Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=27824
in Geoinformatica > vol 10 n° 1 (March - May 2006) . - pp 37 - 53[article]Réservation
Réserver ce documentExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 057-06011 RAB Revue Centre de documentation En réserve L003 Disponible Neural network model for standard PCA and its variants applied to remote sensing / S. Chitroub in International Journal of Remote Sensing IJRS, vol 26 n° 10 (May 2005)
[article]
Titre : Neural network model for standard PCA and its variants applied to remote sensing Type de document : Article/Communication Auteurs : S. Chitroub, Auteur Année de publication : 2005 Article en page(s) : pp 2197 - 2218 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] analyse en composantes principales
[Termes IGN] apprentissage automatique
[Termes IGN] extraction automatique
[Termes IGN] image Landsat-TM
[Termes IGN] image multibande
[Termes IGN] matrice de covariance
[Termes IGN] modèle topologique réseau
[Termes IGN] réseau neuronal artificiel
[Termes IGN] valeur propreRésumé : (Auteur) The conventional approach for principal component analysis (PCA) and its variants applied to remote sensing involves the computation of the input data covariance/correlation matrix and/or that of noise and application of diagonalization procedures for extracting the eigenvalues and corresponding eigenvectors. When the data dimension grows significantly, the matrix computations and manipulations become practically inefficient and inaccurate due to round-off errors. In addition, all the eigenvalues and their corresponding eigenvectors have to be evaluated. These deficiencies make the conventional scheme inefficient for remote sensing applications. For that we propose here a neural network model that performs the PCA and its variants directly from the original data without any additional non-neuronal computations or preliminary matrix estimation. Since the end user is usually not a neural network specialist, the neural network model as well as its execution are carefully designed in order to be automated as much as possible. This includes both the design of the network topology and the input/output representation as well as the design of the training algorithms. The global convergence of the model is studied. Its application has been realized on Landsat Thematic Mapper (TM) multispectral data. The obtained results show that the model performs well. Numéro de notice : A2005-260 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/01431160500075899 En ligne : https://doi.org/10.1080/01431160500075899 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=27396
in International Journal of Remote Sensing IJRS > vol 26 n° 10 (May 2005) . - pp 2197 - 2218[article]Réservation
Réserver ce documentExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 080-05101 RAB Revue Centre de documentation En réserve L003 Disponible Bundle adjustment and incidence of linear features on accuracy of external calibration parameters / Franck Jung (2004)
Titre : Bundle adjustment and incidence of linear features on accuracy of external calibration parameters Type de document : Article/Communication Auteurs : Franck Jung , Auteur ; Didier Boldo , Auteur Editeur : International Society for Photogrammetry and Remote Sensing ISPRS Année de publication : 2004 Collection : International Archives of Photogrammetry and Remote Sensing, ISSN 0252-8231 num. 35-B3 Conférence : ISPRS 2004, 20th international congress of photogrammetry and remote sensing, Geo-Imagery Bridging continents 12/07/2004 23/07/2004 Istanbul Turquie OA ISPRS Archives Importance : pp 13 - 18 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie numérique
[Termes IGN] compensation par faisceaux
[Termes IGN] étalonnage de capteur (imagerie)
[Termes IGN] forme linéaire
[Termes IGN] modélisation 3D
[Termes IGN] photogrammétrie architecturale
[Termes IGN] valeur propreIndex. décimale : 33.30 Photogrammétrie numérique Résumé : (Auteur) In this paper we investigate the influence of linear features (segments) in a bundle adjustment. Bundle adjustment is the problem of refining a set of parameters (internal calibration, external calibration, 3D model). The refinement is performed by the minimization of a cost function. In usual photogrammetric applications, this cost function is based on image tie points and 3D control points. The cost function measures the distance between the observed data and the model. Linear features are especially important when dealing with architectural or terrestrial images, since they do not require segment extremity to match. So, they are easier to detect automatically within particular scenes (buildings, landscapes...). First, we present the basic concepts of bundle adjustment and the integration of linear features. Using the same concept, the linear feature model is based on the distance between the 3D line re projection in the image and the detected image segments. We describe an algorithm for the resolution of this non-linear least-square problem under constraints. Second, we study the influence of these features on two cases. The first case is a calibration polygon, with a large overlap between images. The second one is a façade of a building. We compare a statistical evaluation of the reliability of the estimated parameters to the theoretical bounds calculated with the eigenvalues and eigenvectors of the Hessian matrix associated to our problem. We stress that segments can be relevant features and can highly increase precision. Numéro de notice : 57398 Affiliation des auteurs : MATIS (1993-2011) Thématique : IMAGERIE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : sans En ligne : https://www.isprs.org/proceedings/XXXV/congress/comm3/papers/233.pdf Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=64738 Réservation
Réserver ce documentExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 57398-01 33.30 Tiré à part Centre de documentation Photogrammétrie - Lasergrammétrie Disponible Advanced polarimetric SAR data classification for cartographic information extraction / Manfred F. Buchroithner (31/05/1999)
contenu dans Remote sensing in the 21st century : economic and environmental applications / José Luis Casanova (2000)
Titre : Advanced polarimetric SAR data classification for cartographic information extraction Type de document : Article/Communication Auteurs : Manfred F. Buchroithner, Auteur ; E. Kraetzschmar, Auteur ; M. Hellmann, Auteur Editeur : Lisse et Amsterdam : Balkema (August Aimé) Année de publication : 31/05/1999 Conférence : EARSeL 1999, 19th symposium, Remote sensing in the 21st century : economic and environmental applications 31/05/1999 02/06/1999 Valladolid Espagne OA ISPRS Archives Importance : pp 533 - 539 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Acquisition d'image(s) et de donnée(s)
[Termes IGN] analyse comparative
[Termes IGN] classification
[Termes IGN] classification floue
[Termes IGN] extraction automatique
[Termes IGN] image radar
[Termes IGN] image SIR-C-X-SAR
[Termes IGN] réseau neuronal artificiel
[Termes IGN] valeur propreRésumé : (Auteur) Within the last decade several studies using polarimetric SAR data for bio-/geo-physical feature extraction have been reported and have significantly improved the understanding of polarimetric scattering mechanisms. In a comparative view, the approach presented here, which is based on Shane Cloud's Decomposition Theorem, seems to be most promising : the Entropy H and Angle Classification has been extended by using not only the parameters H and but also the first eigenvalue1. A big advantage of this approach is the high correlation between its results and the physical properties of different landsurface materials, which makes this recently adapted method well-suited for both supervised and automated landcover classification. It is also most useful for the derivation of topographic as well as thematic map information, the scale naturally depending on the sensor's spatial resolution. The well-known DLR Oberpfaffenhofen study site in southern Germany served as a testbed for the exploitation of spaceborne SIR-C/X-SAR data and of L-band data from DLR's airborne experimental ESAR. For validation purposes the classification results have been high-precision geocoded and compared to both ground truth and recent map data, also superimposing the digital national topographic geodata of Germany, ATKIS. The classification proved to be of extraordinary accuracy, as far as can be judged by visual inspection. An exact quantification is underway. The approach presented is being further developed and will - in contrast to the flat test-site used so far - be applied to data flown by a new airborne SAR sensor over mountainous terrain at the northern rim of the Bavarian Alps. First results in this respect look very promising. Numéro de notice : C1999-051 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Communication Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=65817 Verwendung und Bewertung von a-priori Information bei potentiell singulären Inversionsproblemen am Beispiel der gravimetrischen Bestimmung von Dichteverteilungen / P.L. Smilde (1998)PermalinkIntroduction to numerical analysis / J. Stoer (1993)PermalinkOptimierung geodätischer Netze mit spektralen Zielfunktionen / H. Kaltenbach (1992)PermalinkAnalyse und Optimierung geodätischer Netze nach spektralen Kriterien und mechanische Analogien / R. Jäger (1988)PermalinkGPS - network analysis / Wojciech Pachelski (1988)PermalinkNumerical recipes / William H. Press (1988)PermalinkMap distortions and singular value decomposition / P.H. Laskowski (29/03/1987)PermalinkRésolution des grands systèmes linéaires : Rapport du groupe spécial d'études 4.35 / Henri Marcel Dufour (01/08/1975)PermalinkContributions to the solution of systems of linear equations and the determination of eigenvalues / O. Taussky (1954)Permalink