Centre de documentation
scientifique

Automatische Extraktion von Bäumen aus Fernerkundungsdaten / B.M. Straub (2003)  

Public Titre : Automatische Extraktion von Bäumen aus Fernerkundungsdaten Titre original : [Extraction automatique des arbres à partir des données de télédétection] Type de document : Thèse/HDR Auteurs : B.M. Straub, Auteur Editeur : Munich : Bayerische Akademie der Wissenschaften Année de publication : 2003 Collection : DGK - C Sous-collection : Dissertationen num. 572 Importance : 97 p. Format : 21 x 30 cm ISBN/ISSN/EAN : 978-3-7696-5011-2 Note générale : Bibliographie Langues : Allemand (ger) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] arbre (flore) [Termes IGN] classification floue [Termes IGN] extraction automatique [Termes IGN] objet géographique zonal [Termes IGN] photo-interprétation assistée par ordinateur [Termes IGN] reconnaissance de formes [Termes IGN] segmentation d'image Index. décimale : 35.20 Traitement d'image Résumé : (Auteur) A new approach for automatic extraction of trees from remote sensing data - aerial imagery and surface models - is introduced in this thesis. A detailed description of the most important considerations, leading to the development of the approach, is given: for the model of an individual tree, which is the base of the approach and for the strategy for low-level feature extraction and generation of hypotheses. In addition to that, the extraction of individual trees is discussed in relation to other topographic objects. The aim of this discussion is showing possibilities for the integration of the approach for trees into a system for automatic interpretation of remote sensing data. Here, extraction should be understood as the cognitive recognition of objects and their identification and reconstruction. The process of object extraction from images and/or surface models generally depends on an object model as well as a strategy for extraction of image features, their combination, and their relation to the model. A generic geometric model of a tree is used which basically consists of a function describing the tree top. Based on this model features are identified, which are used to recognise single trees from the image data. The basic idea for this strategy consists of two steps. At first, the often very complex fine structures are removed from the surface model by using various scale levels in linear scale space. As a result of scale-space transformation the tree top can be identified in the surface model based on the coarse structure. Here, the main problem is, that on the one hand the diameter of a single tree continuously varies in reality, but also strongly influences the choice of filter parameters. To overcome this difficulty, the image data was examined at different scale levels of linear scale-space. The extraction of the trees is performed using an algorithm: Firstly, segmentation of each scale-level with the watershed transformation is carried out. The resulting segments, which are potential candidates for tree tops, are evaluated with the help of fuzzy functions and based on the resulting membership values hypotheses are generated. The last step is the reconstruction of the crown's outline using a snake-algorithm. The procedure, developed for the extraction of trees from images and surface models in the context of this thesis, is applied in various small test areas. The positive as well as the negative results of these projects are presented, and the problems are discussed based on subsets of the test areas. An evaluation of the approach, and proposals for further development and research are given at the end of the thesis. Numéro de notice : 13202 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Thèse étrangère DOI : sans En ligne : https://dgk.badw.de/fileadmin/user_upload/Files/DGK/docs/c-572.pdf Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=54912

Exemplaires(2)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
13202-01	35.20	Livre	Centre de documentation	Télédétection	Disponible
13202-02	35.20	Livre	Centre de documentation	Télédétection	Disponible

Image analysis for GIS data acquisition : paper read at a Technical Meeting of the Photogrammetric Society on 14th March 2000 / Christian Heipke in Photogrammetric record, vol 16 n° 96 (October 2000 - March 2001)  

Public [article]  inPhotogrammetric record > vol 16 n° 96 (October 2000 - March 2001) . - pp 963 - 985 Titre : Image analysis for GIS data acquisition : paper read at a Technical Meeting of the Photogrammetric Society on 14th March 2000 Type de document : Article/Communication Auteurs : Christian Heipke, Auteur ; K. Parzad, Auteur ; B.M. Straub, Auteur Année de publication : 2000 Article en page(s) : pp 963 - 985 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] analyse d'image numérique [Termes IGN] interprétation automatique [Termes IGN] système d'information géographique Numéro de notice : A2000-158 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1111/0031-868X.00160 En ligne : https://doi.org/10.1111/0031-868X.00160 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=21574 [article]

Exemplaires(2)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
106-00021	RAB	Revue	Centre de documentation	En réserve L003	Disponible
106-00022	RAB	Revue	Centre de documentation	En réserve L003	Disponible