Catalogue en ligne IGN

Wissensbasierte Interpretation von Vegetationsflächen aus multitemporalen Fernerkundungsdaten / Kian Pakzad (2001)

Public

Titre :	Wissensbasierte Interpretation von Vegetationsflächen aus multitemporalen Fernerkundungsdaten
Titre original :	[L'interprétation basée sur les connaissances des surfaces végétales a partir de données de télédétection multi temporelles]
Type de document :	Thèse/HDR
Auteurs :	Kian Pakzad, Auteur
Editeur :	Munich : Bayerische Akademie der Wissenschaften
Année de publication :	2001
Collection :	DGK - C
Sous-collection :	Dissertationen num. 543
Importance :	104 p.
Format :	21 x 30 cm
ISBN/ISSN/EAN :	978-3-7696-9582-3
Note générale :	Bibliographie
Langues :	Allemand (ger)
Descripteur :	[Vedettes matières IGN] Applications de télédétection [Termes IGN] analyse diachronique [Termes IGN] classification à base de connaissances [Termes IGN] image multitemporelle [Termes IGN] interprétation automatique [Termes IGN] lande [Termes IGN] réseau sémantique [Termes IGN] segmentation d'image [Termes IGN] surveillance de la végétation [Termes IGN] système expert
Résumé :	(Auteur) The thesis in hand presents a general concept for the automatic interpretation of remote sensing data with the interpretation of vegetation areas brought into focus, which uses both structural features and temporal knowledge. Based on this concept, a method for automatic multitemporal interpretation of moorland is explained. The developed procedures rely on a knowledge based image analysis system, which uses Semantic Nets for knowledge representation in standard language. During the interpretation process these are used for deriving hypotheses by applying a continuous symbolic processing, to verify them, and thus gain a symbolic description of the examined landscape scene. Verification of the hypotheses is carried out in the remote sensing data using specific processing operators. The introduced general concept for interpretation of remote sensing data groups the object classes found in the landscape into various categories, according to their characteristics. Thus object classes were discerned which possess a given geometry, given texture, given pattern, or characteristic features. Interpretation strategies are suggested for each category, which relate to the creation of the semantic nets as well as to the specific image processing operators. Then the interpretation of vegetation areas belonging to the latter category is brought into focus. As such areas often are inhomogeneous and show numerous structures, the approaches of multispectral classification applied so far are less suitable as they result in oversegmentation, and either do not or to a little extent utilize structural features for interpretation. The new strategy presented here proceeds from given segment borders and searches for structural features within the borders. Such structural features are described by standard language and may be for example "tracks", "irregular structure", or "vegetation". Their verification in the images is done by feature analysis operators. For interpretation of temporal changes a new concept is suggested, which discretely describes temporal conditions of regions, and which transfers the most probable temporal changes of the given conditions as temporal knowledge into a state transition diagram, then using it for multitemporal interpretation. Thus the temporal history of the past interpretations is used for the interpretation of images of a particular epoch by favouring certain interpretation methods, and a priori excluding others. Based on the described approaches a procedure for automatic multitemporal interpretation of industrially used moorland was successfully developed. Proceeding from an initial segmentation based on GeoData a resegmentation and an interpretation of the segments is carried out for each investigated epoch. By using temporal knowledge it is possible to separate moor classes, which can only be detected in temporal order. The application of temporal knowledge and structural features enables the exclusive use of grey scale images for interpretation of vegetation areas. The results show that the presented procedure is suitable for multitemporal interpretation of moorland, and that it is able to distinguish additional moor classes compared to the approaches used so far. It is further applicable for a more robust multitemporal interpretation, and does not depend on colour images.
Numéro de notice :	13067
Affiliation des auteurs :	non IGN
Thématique :	IMAGERIE
Nature :	Thèse étrangère
Permalink :	https://documentation.ensg.eu/index.php?lvl=notice_display&id=54867

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
13067-01	35.41	Livre	Centre de documentation	Télédétection	Disponible

IGN

Centre de documentation
scientifique

Accueil

Sélection de la langue

Adresse

Se connecter

Actualité

L'actu ! Horaires du CDOS

Informations pratiques

Exemplaires(1)

IGN / ENSG

L'IGN a pour vocation

Accès directs

2014 -2024 IGN

IGN

Centre de documentationscientifique

Accueil

Sélection de la langue

Adresse

Se connecter

Actualité

L'actu ! Horaires du CDOS

Informations pratiques

Exemplaires(1)

IGN / ENSG

L'IGN a pour vocation

Accès directs

2014 -2024 IGN

Centre de documentation
scientifique