Détail de l'auteur
Auteur A.L. De Mendonça |
Documents disponibles écrits par cet auteur (1)
Ajouter le résultat dans votre panier Affiner la recherche Interroger des sources externes
Combined use of Quickbird and lidar data for mapping a urban environment / N.B. Da Luz in Revue Française de Photogrammétrie et de Télédétection, n° 198 - 199 (Septembre 2012)
[article]
Titre : Combined use of Quickbird and lidar data for mapping a urban environment Type de document : Article/Communication Auteurs : N.B. Da Luz, Auteur ; D.J. Dos Santos, Auteur ; A.L. De Mendonça, Auteur ; A.F. Buffara Antunes, Auteur ; H. Araki, Auteur ; Q. Chen, Auteur Année de publication : 2012 Article en page(s) : pp 78 - 87 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques
[Termes IGN] carte d'occupation du sol
[Termes IGN] cartographie urbaine
[Termes IGN] classification par arbre de décision
[Termes IGN] données lidar
[Termes IGN] données localisées 3D
[Termes IGN] image Quickbird
[Termes IGN] milieu urbain
[Termes IGN] modèle numérique de surface
[Termes IGN] Parana (Brésil)
[Termes IGN] segmentation d'image
[Termes IGN] semis de pointsRésumé : (Auteur) High resolution satellite imagery and airborne Lidar data can characterize the earth surface with unprecedented details in spatial and structure information, respectively. However, most studies have used them separately instead of in combination for land surface mapping. Considering their highly complementary nature, it is critical to investigate whether and how the integration of both can improve the accuracy of land cover and land use (LCLU) mapping. This study explored the use of Quickbird imagery and airborne Lidar data for mapping a complex urban environment in the City of Curitiba, Parana State, Southern Brazil, which is composed of secondary shrub vegetation, grass and climax primary Araucaria forests combined with urban objects such as roads and buildings. Airborne Lidar data were processed to generate DEM, DSM (Digital Surface Model), and DHM (Digital Height Model). The DSM generated from Lidar data were used to orthorectify Quickbird image with photogrammetric skills. A large number of metrics are generated from Lidar DHM, Lidar point cloud, Lidar intensity, and Quickbird imagery using object oriented segmentation approaches. Due to their power in handling non-parametric data, decision-tree based approaches were chosen to select the most relevant metrics and build rules for classification. It was found that the fusion of both types of data with decision trees increased the accuracy by 5 to 15% and resulted in an overall accuracy over 90%. Taking into account the increasing accessibility of Quickbird and airborne Lidar data, it is expected the methodology developed in this study has profound impacts in shifting our current paradigm in LCLU mapping. Numéro de notice : A2012-427 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : sans Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=31873
in Revue Française de Photogrammétrie et de Télédétection > n° 198 - 199 (Septembre 2012) . - pp 78 - 87[article]