Centre de documentation
scientifique

Developing collaborative classifiers using an Expert-based Model / Giorgos Mountrakis in Photogrammetric Engineering & Remote Sensing, PERS, vol 75 n° 7 (July 2009)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 75 n° 7 (July 2009) . - pp 831 - 843 Titre : Developing collaborative classifiers using an Expert-based Model Type de document : Article/Communication Auteurs : Giorgos Mountrakis, Auteur ; R. Watts, Auteur ; L. Luo, Auteur ; Jing Wang, Auteur Année de publication : 2009 Article en page(s) : pp 831 - 843 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] classificateur [Termes IGN] classification à base de connaissances [Termes IGN] image Landsat [Termes IGN] Las Vegas [Termes IGN] mise à l'échelle [Termes IGN] précision de la classification [Termes IGN] surface imperméable [Termes IGN] système expert Résumé : (Auteur) This paper presents a hierarchical, multi-stage adaptive strategy for image classification. We iteratively apply various classification methods (e.g., decision trees, neural networks), identify regions of parametric and geographic space where accuracy is low, and in these regions, test and apply alternate methods repeating the process until the entire image is classified. Currently, classifiers are evaluated through human input using an expert-based system; therefore, this paper acts as the proof of concept for collaborative classifiers. Because we decompose the problem into smaller, more manageable sub-tasks, our classification exhibits increased flexibility compared to existing methods since classification methods are tailored to the idiosyncrasies of specific regions. A major benefit of our approach is its scalability and collaborative support since selected low-accuracy classifiers can be easily replaced with others without affecting classification accuracy in high accuracy areas. At each stage, we develop spatially explicit accuracy metrics that provide straightforward assessment of results by non-experts and point to areas that need algorithmic improvement or ancillary data. Our approach is demonstrated in the task of detecting impervious surface areas, an important indicator for human-induced alterations to the environment, using a 2001 Landsat scene from Las Vegas, Nevada. Copyright ASPRS Numéro de notice : A2009-263 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.14358/PERS.75.7.831 En ligne : https://doi.org/10.14358/PERS.75.7.831 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=29893 [article]