Comparison of three segmentation methods for groves recognition in very resolution satellite images

Mougel Baptiste, Lelong Camille, Nicolas Jean-Marie. 2007. Comparison of three segmentation methods for groves recognition in very resolution satellite images. In : Proceedings of Physics in signal and image processing (PSIP 2007), Mulhouse, 31 janvier au 02 février 2007. s.l. : s.n., 5 p. Proceedings of Physics in Signal and Image Processing (PSIP 2007), Mulhouse, France, 31 Janvier 2007/2 Février 2007.

Résumé : This study is dedicated to the automatic recognition and mapping of tree crops by remote sensing, using very high resolution multi-spectral satellite images (0.7 m). Our goal is to segment the images in order to perform an independent classification according to a set of pre-determined land use types: apple groves, vineyards, miscellaneous young and old groves, pastured and cropped fields, food crop, fallow lands and forests. In this article, we compare three methods of segmentation that seem to provide suitable units for the resolution of our problem: SxS, eCognition and watersheds. A set of criteria are defined to quantitatively analyze the efficiency of these segmentations. We then try to select the more relevant method in terms of subsequent classification operability.

Mots-clés Agrovoc : identification, cartographie, arbuste, verger, végétation, méthode, télédétection, satellite, analyse d'image

Classification Agris : U30 - Méthodes de recherche

Auteurs et affiliations

• Mougel Baptiste, CIRAD-ES-UMR TETIS (FRA)
• Lelong Camille, CIRAD-ES-UMR TETIS (FRA) ORCID: 0000-0002-4850-1010
• Nicolas Jean-Marie, ENST (FRA)

Source : Cirad - Agritrop (https://agritrop.cirad.fr/539533/)

Métriques

[ Page générée et mise en cache le 2024-03-20 ]