Hedgerow detection in HRS and VHRS images from different source (optical, radar)

Author

Ducrot, Danielle ; Masse, Antoine ; Ncibi, Abir

Author_Institution

CESBIO - Centre d´´Etudes Spatiales de la Biosphere, Toulouse, France

fYear

2012

fDate

22-27 July 2012

Firstpage

6348

Lastpage

6351

Abstract

The challenge of recreating a green belt (hedgerow, forest, green corridors ...) is to restore biodiversity that the ecological continuity required. A coherent ecological network allows species to move, interact, and continue to support human being. The main objective of this paper is to explore the potential of image processing methods to map hedgerows, corridors, woodlands of the green belt. We present a methodology based on unsupervised and supervised classification, segmentation and classification fusion. It is applied to a rural landscape and several sensors: Very High and High Resolution, optical and radar satellite, respectively FORMOSAT-2 (8m) SPOT 5 (2.5m and 10m) and TerraSar-X (3m).

Keywords

geophysical image processing; geophysical techniques; image classification; image fusion; image segmentation; radar imaging; remote sensing by radar; FORMOSAT-2 satellite; HRS image; Hedgerow detection; TerraSar-X satellite; VHRS image; biodiversity restoration; classification fusion; coherent ecological network; green belt; image processing methods; optical satellite; radar satellite; supervised classification; supervised segmentation; Belts; Green products; Laser radar; Optical sensors; Remote sensing; Spaceborne radar; classification; hedgerow detection; supervised/unsupervised techniques;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium (IGARSS), 2012 IEEE International

Conference_Location

Munich

ISSN

2153-6996

Print_ISBN

978-1-4673-1160-1

Electronic_ISBN

2153-6996

Type

conf

DOI

10.1109/IGARSS.2012.6352712

Filename

6352712