Detection of Vegetation Coverage in Urban Agglomeration of Brussels by NDVI Indicator Using eCognition Software and Remote Sensing Measurements

Abstract

The study focuses on the semi-automatic detection of the vegetation on the satellite panchromatic image covering area of Brussels, Belgium. Using functions of the Normalized Difference Vegetation Index (NDVI) and spectral reflectance parameters of the image, the vegetation was identified on the satellite scene. The research question was to assess, how NDVI measurements can be used for urban studies using remote sensing data. The aim is to distinguish and separate on the map built-up areas from the green spaces (parks, gardens, etc) within the urban landscape. The research is supported by the raster image and the eCognition software for image analysis. The results show detected vegetation areas in eastern part of Brussels. The research demonstrated methodological applicability of eCognition software for GIS-based urban mapping and ecological assessment (areas and sizes of vegetation coverage).

Keywords: image analysis, eCognition, NDVI, spectral reflectance, urbanization, Brussels, mapping, GIS

JEL Classification: Y92, Q00, Q01, Q24, Q55, Q56