Centre de documentation
scientifique

A high-reliability, high-resolution method for land cover classification into forest and non-forest / Roger Trias-Sanz (2005)    

Public contenu dans Image Analysis, 14th Scandinavian Conference, SCIA 2005, Joensuu, Finland, June 2005 / Heikki Kalviainen (2005)   Titre : A high-reliability, high-resolution method for land cover classification into forest and non-forest Type de document : Article/Communication Auteurs : Roger Trias-Sanz , Auteur ; Didier Boldo , Auteur Editeur : Berlin, Heidelberg, Vienne, New York, ... : Springer Année de publication : 2005 Collection : Lecture notes in Computer Science, ISSN 0302-9743 num. 3540 Conférence : SCIA 2005, 14th Scandinavian Conference on Image Analysis 19/06/2005 22/06/2005 Joensuu Finlande Proceedings Springer Importance : pp 831 - 840 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] classification basée sur les régions [Termes IGN] forêt [Termes IGN] image aérienne [Termes IGN] occupation du sol [Termes IGN] segmentation hiérarchique [Termes IGN] valeur radiométrique Résumé : (auteur) We present several methods for per-region land-cover classification based on distances on probability distributions and whole-region probabilities. We present results on using this method for locating forest areas in high-resolution aerial images with very high reliability, achieving more than 95% accuracy, using raw radiometric channels as well as derived color and texture features. Region boundaries are obtained from a multi-scale hierarchical segmentation or from a registration of cadastral maps. Numéro de notice : C2005-033 Affiliation des auteurs : MATIS (1993-2011) Thématique : FORET/IMAGERIE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.1007/11499145_84 En ligne : https://doi.org/10.1007/11499145_84 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99876

Documents numériques

peut être téléchargé Poster SCIA 2005 - image auteur Tag Image Format TIFF

Image Analysis, 14th Scandinavian Conference, SCIA 2005, Joensuu, Finland, June 2005 / Heikki Kalviainen (2005)  

Public Titre : Image Analysis, 14th Scandinavian Conference, SCIA 2005, Joensuu, Finland, June 2005 : Proceedings Type de document : Actes de congrès Auteurs : Heikki Kalviainen, Éditeur scientifique ; Jussi Parkkinen, Éditeur scientifique ; Arto Kaarna, Éditeur scientifique Editeur : Berlin, Heidelberg, Vienne, New York, ... : Springer Année de publication : 2005 Collection : Lecture notes in Computer Science, ISSN 0302-9743 num. 3540 Conférence : SCIA 2005, 14th Scandinavian Conference on Image Analysis 19/06/2005 22/06/2005 Joensuu Finlande Proceedings Springer Importance : 1270 p. Format : 15 x 24 cm ISBN/ISSN/EAN : 978-3-540-26320-3 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] classification [Termes IGN] compression d'image [Termes IGN] image en couleur [Termes IGN] patrimoine culturel [Termes IGN] reconnaissance de formes [Termes IGN] segmentation d'image [Termes IGN] texture d'image [Termes IGN] vision par ordinateur Résumé : (éditeur) This proceedings volume collects the scientific presentations of the Scandinavian Conference on Image Analysis, SCIA 2005, which was held at the University of Joensuu, Finland, June 19–22, 2005. The conference was the fourteenth in the series of biennial conferences started in 1980. The name of the series re?ects the fact that the conferences are organized in the Nordic (Scandinavian) countries, following the cycle Sweden, Finland, Denmark, and Norway. The event itself has always been international in its participants and presentations. Today there are many conferences in the ?elds related to SCIA. In this s- uation our goal is to keep up the reputation for the high quality and friendly environment of SCIA. We hope that participants feel that it’s worth attending the conference. Therefore, both the scienti?c and social program were designed to support the best features of a scienti?c meeting: to get new ideas for research and to have the possibility to exchange thoughts with fellow scientists. To ful?ll the above-mentioned goals, the conference was a single-track event. This meant that a higher percentage of the papers than in earlier SCIAs were presented as posters. We hope that this gave the participants better chances to follow the presentations that they were interested in. SCIA 2005 attracted a record number of submissions: 236 manuscripts. From these, 124 were accepted: 31 oral presentations and 93 poster presentations. This led to an acceptance rate of 53%. The program included also six plenary presentations and three tutorials. Numéro de notice : 19831 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Actes DOI : 10.1007/b137285 En ligne : https://doi.org/10.1007/b137285 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=85925

Contient

• Inferring and enforcing geometrical constraints on a 3D model for building reconstruction / Franck Taillandier (2005)  
• A high-reliability, high-resolution method for land cover classification into forest and non-forest / Roger Trias-Sanz (2005)    

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
19831-01	CG2005	Livre	Centre de documentation	Congrès	Disponible

Inferring and enforcing geometrical constraints on a 3D model for building reconstruction / Franck Taillandier (2005)  

Public contenu dans Image Analysis, 14th Scandinavian Conference, SCIA 2005, Joensuu, Finland, June 2005 / Heikki Kalviainen (2005)   Titre : Inferring and enforcing geometrical constraints on a 3D model for building reconstruction Type de document : Article/Communication Auteurs : Franck Taillandier , Auteur Editeur : Berlin, Heidelberg, Vienne, New York, ... : Springer Année de publication : 2005 Collection : Lecture notes in Computer Science, ISSN 0302-9743 num. 3540 Conférence : SCIA 2005, 14th Scandinavian Conference on Image Analysis 19/06/2005 22/06/2005 Joensuu Finlande Proceedings Springer Importance : pp 699 - 708 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] contrainte géométrique [Termes IGN] modèle numérique [Termes IGN] reconstruction 3D du bâti Résumé : (auteur) We present a method for inferring and enforcing geometrical constraints on an approximate 3D model for building reconstruction applications. Compared to previous works, this approach requires no user intervention for constraints definition, is inherently compliant with the detected constraints and handles over-constrained configurations. An iterative minimization is applied to search for the model subject to geometric constraints that minimizes the distance to the initial approximate model. Results on real data show the gain obtained by this algorithm. Numéro de notice : C2005-032 Affiliation des auteurs : MATIS (1993-2011) Thématique : IMAGERIE Nature : Poster nature-HAL : Poster-avec-CL DOI : 10.1007/11499145_71 En ligne : http://dx.doi.org/10.1007/11499145_71 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99560