Centre de documentation
scientifique

Dépouillements

Fuzzy image segmentation for urban land-cover classification / I. Lizarazo in Photogrammetric Engineering & Remote Sensing, PERS, vol 76 n° 2 (February 2010)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 76 n° 2 (February 2010) . - pp 151 - 162 Titre : Fuzzy image segmentation for urban land-cover classification Type de document : Article/Communication Auteurs : I. Lizarazo, Auteur ; J. Barros, Auteur Année de publication : 2010 Article en page(s) : pp 151 - 162 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] analyse d'image orientée objet [Termes IGN] classification dirigée [Termes IGN] classification orientée objet [Termes IGN] exploration de données géographiques [Termes IGN] image à haute résolution [Termes IGN] occupation du sol [Termes IGN] segmentation d'image [Termes IGN] zone urbaine Résumé : (Auteur) A main problem of hard image segmentation is that, in complex landscapes, such as urban areas, it is very hard to produce meaningful crisp image-objects. This paper proposes a fuzzy approach for image segmentation aimed to produce fuzzy image-regions expressing degrees of membership of pixels to different target classes. This approach, called Fuzzy Image-Regions Method (FIRME), is a natural way to deal with the inherent ambiguity of remotely sensed images. The FIRME approach comprises three main stages: (a) image segmenta-tion which creates fuzzy image-regions, (b) feature analysis which measures properties of fuzzy image regions, and (c) classification which produces the intended land-cover classes. The FIRME method was evaluated in a land-cover classification experiment using high spectral resolution imagery in an urban zone in Bogota, Colombia. Results suggest that in complex environments, fuzzy image segmen-tation may be a suitable alternative for GEOBIA as it produces higher thematic accuracy than the hard image segmentation and other traditional classifiers. Copyright ASPRS Numéro de notice : A2010-049 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.14358/PERS.76.2.151 En ligne : https://doi.org/10.14358/PERS.76.2.151 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=30245 [article]

Real world objects in geobia through the exploitation of existing digital cartography and image segmentation / G. Smith in Photogrammetric Engineering & Remote Sensing, PERS, vol 76 n° 2 (February 2010)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 76 n° 2 (February 2010) . - pp 163 - 171 Titre : Real world objects in geobia through the exploitation of existing digital cartography and image segmentation Type de document : Article/Communication Auteurs : G. Smith, Auteur ; D. Morton, Auteur Année de publication : 2010 Article en page(s) : pp 163 - 171 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] analyse d'image orientée objet [Termes IGN] cartographie numérique [Termes IGN] objet géographique [Termes IGN] processus [Termes IGN] réalité de terrain [Termes IGN] segmentation d'image Résumé : (Auteur) Descriptions of Geographic Object-Based Image Analysis (geobia) often identify image segmentation as the initial step. This may be reasonable in some cases, but segmentation might also be considered a "black art," due to its image dependence and the limited amount control available to users. The resulting segments reflect the spectral structure of the image rather than the physical structure of the landscape with no one-to-one relationship between real world objects and segments. Geographic analysis often begins in the context of existing mapping. In regions with high quality large scale cartography, an obvious question is why is this information not used in the GEOBIA process? It is therefore proposed that geobia be redefined to use the best existing real world feature datasets as the starting point before segmentation is considered. Such an approach would increase opportunities for integration, improve map update initiatives, and widen uptake by end user communities. Copyright ASPRS Numéro de notice : A2010-050 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.14358/PERS.76.2.151 En ligne : https://doi.org/10.14358/PERS.76.2.151 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=30246 [article]

Automated image-to-map discrepancy detection using iterative trimming / J. Radoux in Photogrammetric Engineering & Remote Sensing, PERS, vol 76 n° 2 (February 2010)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 76 n° 2 (February 2010) . - pp 173 - 181 Titre : Automated image-to-map discrepancy detection using iterative trimming Type de document : Article/Communication Auteurs : J. Radoux, Auteur ; P. Defourny, Auteur Année de publication : 2010 Article en page(s) : pp 173 - 181 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] analyse d'image orientée objet [Termes IGN] appariement de données localisées [Termes IGN] base de données vectorielles [Termes IGN] détection de changement [Termes IGN] forêt [Termes IGN] image numérique [Termes IGN] itération [Termes IGN] segmentation d'image [Termes IGN] seuillage d'image [Termes IGN] système d'information géographique Résumé : (Auteur) Keeping existing vector databases up to date is a real challenge for GIS data providers. This study directly compares a map with a more recent image in order to detect the discrepancies between them. An automatic workflow was designed to process the image based on existing information extracted from the vector database. First, geographic object-based image analysis provided automatically labeled image segments after matching the vector database to the image. Then, discrepan-cies were detected using a statistical iterative trimming, where outliers were excluded based on a likelihood threshold. Applied on forest map updating, the proposed workflow was able to detect about 75 percent of the forest regeneration, and 100 percent of the clear cuts with less than 10 percent of commission errors. This discrepancy detection approach assumes that discrepancy corresponds to small proportion of the map area and is very promising in diverse applications thanks to its flexibility. Copyright ASPRS Numéro de notice : A2010-051 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.14358/PERS.76.2.173 En ligne : https://doi.org/10.14358/PERS.76.2.173 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=30247 [article]