Centre de documentation
scientifique

Classification of water surfaces using airborne topographic lidar data / Julien Smeeckaert (2013)  

Public Titre : Classification of water surfaces using airborne topographic lidar data Type de document : Article/Communication Auteurs : Julien Smeeckaert, Auteur ; Clément Mallet , Auteur ; Nicolas David , Auteur Editeur : International Society for Photogrammetry and Remote Sensing ISPRS Année de publication : 2013 Collection : International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, ISSN 1682-1750 num. 40-1/W1 Conférence : ISPRS 2013, Hannover Workshop 21/05/2013 24/05/2013 Hanovre Allemagne OA ISPRS Archives Importance : pp 321 - 326 Format : 21 x 30 cm Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] chaîne de traitement [Termes IGN] classification dirigée [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] cours d'eau [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] eau de surface [Termes IGN] interpolation [Termes IGN] littoral [Termes IGN] modèle numérique de terrain [Termes IGN] rivage [Termes IGN] segmentation en régions [Termes IGN] semis de points Résumé : (auteur) Accurate Digital Terrain Models (DTM) are inevitable inputs for mapping areas subject to natural hazards. Topographic airborne laser scanning has become an established technique to characterize the Earth surface: lidar provides 3D point clouds allowing a fine reconstruction of the topography. For flood hazard modeling, the key step before terrain modeling is the discrimination of land and water surfaces within the delivered point clouds. Therefore, instantaneous shoreline, river borders, inland waters can be extracted as a basis for more reliable DTM generation. This paper presents an automatic, efficient, and versatile workflow for land/water classification of airborne topographic lidar data. For that purpose, a classification framework based on Support Vector Machines (SVM) is designed. First, a restricted set of features, based only 3D lidar point coordinates and flightline information, is defined. Then, the SVM learning step is performed on small but well-targeted areas thanks to an automatic region growing strategy. Finally, label probabilities given by the SVM are merged during a probabilistic relaxation step in order to remove pixel-wise misclassification. Results show that survey of millions of points are labelled with high accuracy (>95% in most cases for coastal areas, and >89% for rivers) and that small natural and anthropic features of interest are still well classified though we work at low point densities (0.5-4 pts/m2). Our approach is valid for coasts and rivers, and provides a strong basis for further discrimination of land-cover classes and coastal habitats. Numéro de notice : C2013-055 Affiliation des auteurs : LASTIG MATIS+Ext (2012-2019) Thématique : IMAGERIE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.5194/isprsarchives-XL-1-W1-321-2013 Date de publication en ligne : 02/05/2013 En ligne : https://doi.org/10.5194/isprsarchives-XL-1-W1-321-2013 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92183