Issue link: https://geospatial.trimble.com/en/resources/i/1397677
In France's Brittany region, stakeholders have been pressured to balance urban development demands with environmental protection policies, but insufficient vegetation maps have made that difficult. A botanical organization used Trimble's eCognition software to develop a semi-automated mapping system and produce Brittany's first-ever regional vegetation map. The goldmine of classified flora is giving stakeholders a holistic view of Brittany's biodiversity and the knowledge to protect, develop and manage it. overview Location FRANCE TRANSFORMING THE WAY THE WORLD WORKS TRANSFORMING THE WAY THE WORLD WORKS Vegetation maps are an essential tool for stakeholders in biodiversity conservation and land use planning. Traditionally, however, these maps have been produced for singular needs. The localized focus has made it difficult for regional development managers to understand the vegetation landscape as a whole. As specialists in studying, inventorying and preserving vegetation, the National Botanical Conservatory of Brest (CBN) offered to fill in that mapping gap and provide a common vegetation repository. Vanessa Sellin, a biologist and geology scientist with a Master's degree in GIS, joined the CBN in 2011 to develop a more efficient vegetation mapping methodology. After researching and testing options, she chose eCognition object-based image analysis (OBIA) technology to help her develop a semi-automated approach to vegetation mapping at a 1:25,000 scale. After a few years of experimenting and refining the methodology, in 2016 she put the technique through its most significant trial: mapping the main vegetation of the Armorique Regional Natural Park (PNRA), a 125,000-hectare protected territory in Finistère, a department in Brittany. To map the vegetation, she used eCognition with orthoimage mosaics and integrated ancillary data. Using predominantly texture images, brightness and a normalized difference vegetation index, eCognition analyzed each orthomosaic to first distinguish non-vegetated areas like roads, buildings and artificial areas like gardens. Based on tiered workflows, the software then used a series of multispectral segmentation algorithms to separate objects into different classes of vegetation, non-vegetation and artificial vegetation. After sorting these, eCognition began the process of identifying specific vegetation types, distinguishing the easiest class of vegetation (forest, dunes) to the most difficult (shrubs, heathland).