Centre de documentation
scientifique

Optimal segmentation of high spatial resolution images for the classification of buildings using random forests / James Bialas in International journal of applied Earth observation and geoinformation, vol 82 (October 2019)  

Public [article]  inInternational journal of applied Earth observation and geoinformation > vol 82 (October 2019) . - pp Titre : Optimal segmentation of high spatial resolution images for the classification of buildings using random forests Type de document : Article/Communication Auteurs : James Bialas, Auteur ; Thomas Oommen, Auteur ; Timothy C. Havens, Auteur Année de publication : 2019 Article en page(s) : pp Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse d'image orientée objet [Termes IGN] apprentissage automatique [Termes IGN] bâtiment [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] dommage matériel [Termes IGN] image à haute résolution [Termes IGN] image aérienne [Termes IGN] Nouvelle-Zélande [Termes IGN] précision de la classification [Termes IGN] qualité du processus [Termes IGN] segmentation d'image [Termes IGN] séisme [Termes IGN] zone urbaine Résumé : (auteur) In the application of machine learning to geographic object based image analysis, several parameters influence overall classifier performance. One of the first parameters is segmentation size—for example, how many pixels should be grouped together to form an image object. Often, trial and error methods are used to obtain segmentation parameters that best delineate the borders of real world objects. Several attempts at automated methods have produced promising results, but manual intervention is still necessary. Meanwhile, numerous measures of segmentation quality have been defined, but their relationship to classifier performance is not then directly shown. For example, as measures of segmentation quality improve, do classification results improve as well? Our work considers the problem of building classification in high resolution aerial imagery of urban areas. Based on user defined training polygons generated with or without a reference segmentation, we have found several measures of segmentation quality and feature performance that can help users narrow the range of appropriate segmentations. Furthermore, our work finds that given this range, performance of machine learning algorithms remains relatively constant for any given segmentation as long as features used for classification are chosen correctly. We find that the range of scale parameters capable of producing an accurate classification is much broader than typically assumed and trial and error methods for finding this parameter may be an acceptable approach. Numéro de notice : A2019-472 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.jag.2019.06.005 Date de publication en ligne : 08/06/2019 En ligne : https://doi.org/https://doi.org/10.1016/j.jag.2019.06.005 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93632 [article]