Skip to main content
Publications | Persons | Institutes | Projects
[ report an error in this record ]basket (0): add | show Print this page

Improving ecotope segmentation by combining topographic and spectral data
Radoux, J.; Bourdouxhe, A.; Coos, W.; Dufrêne, M.; Defourny, P. (2019). Improving ecotope segmentation by combining topographic and spectral data. Remote Sens. 11(3): 354. https://dx.doi.org/10.3390/rs11030354
In: Remote Sensing. MDPI: Basel. ISSN 2072-4292; e-ISSN 2072-4292, more
Peer reviewed article  

Available in  Authors 

Author keywords
    GEOBIA; biodiversity; LIDAR; orthophoto; segmentation; classification; biotope distribution model

Authors  Top 

Abstract
    Ecotopes are the smallest ecologically distinct landscape features in a landscape mapping and classification system. Mapping ecotopes therefore enables the measurement of ecological patterns, process and change. In this study, a multi-source GEOBIA workflow is used to improve the automated delineation and descriptions of ecotopes. Aerial photographs and LIDAR data provide input for landscape segmentation based on spectral signature, height structure and topography. Each segment is then characterized based on the proportion of land cover features identified at 2 m pixel-based classification. The results show that the use of hillshade bands simultaneously with spectral bands increases the consistency of the ecotope delineation. These results are promising to further describe biotopes of high ecological conservation value, as suggested by a successful test on ravine forest biotope.

All data in the Integrated Marine Information System (IMIS) is subject to the VLIZ privacy policy Top | Authors