A new Copernicus high resolution layer at pan-European scale: small woody features

Loic Faucqueur; Nathalie Morin; Antoine Masse; Pierre-Yves Remy; Justine Hugé; Clémence Kenner; Fabrice Dazin; Baudouin Desclée; Christophe Sannier

doi:10.1117/12.2532853

21 October 2019 A new Copernicus high resolution layer at pan-European scale: small woody features

Loic Faucqueur, Nathalie Morin, Antoine Masse, Pierre-Yves Remy, Justine Hugé, Clémence Kenner, Fabrice Dazin, Baudouin Desclée, Christophe Sannier

Author Affiliations +

Proceedings Volume 11149, Remote Sensing for Agriculture, Ecosystems, and Hydrology XXI; 111490X (2019) https://doi.org/10.1117/12.2532853
Event: SPIE Remote Sensing, 2019, Strasbourg, France

Abstract

Small Woody Features (SWF) represent some of the most stable vegetated linear and small landscape features providing numerous ecological and socio-cultural functions, which can be grouped in four main categories: soil and water conservation, climate protection and adaptation, support to biological diversity, and cultural identity. Copernicus Land monitoring service, through the High-Resolution Layers, aims to map those SWFs at Pan- European level (39 countries, 6 million square kilometers) with the use of more than 37,000 Very High Spatial Resolution (VHSR) Earth Observation (EO) scenes. This unprecedented mapping exercise is focused on the extraction of SWF with a maximum width of 30m and a minimum length of 50m for linear features and a minimum and maximum area of 200 and 5,000m respectively. The main outputs are vector and raster products from the Pan-European coverage of the VHSR image data available from the European Space Agency (ESA) Copernicus Space Component Data Access (CSCDA) VHR IMAGE 2015 dataset. To fulfill this goal with a semi-automated approach, we developed a classification processing chain with the goal of very high computer efficiency and accuracy, using Object Based Image Analysis (OBIA) approach and Cloud-computing solutions. This highly efficient methodology based on differential attribute profiles (DAP) and classical classifier such as Random-Forest is particularly adapted to this exercise since it combines the use of spatial information and the spectral signature of each pixel. In this paper, we present the detailed methodology validated at Pan-European scale with various VHSR data source and landscape characteristics as well as full production results and internal validation.

Conference Presentation

Citation Download Citation

Loic Faucqueur, Nathalie Morin, Antoine Masse, Pierre-Yves Remy, Justine Hugé, Clémence Kenner, Fabrice Dazin, Baudouin Desclée, and Christophe Sannier "A new Copernicus high resolution layer at pan-European scale: small woody features", Proc. SPIE 11149, Remote Sensing for Agriculture, Ecosystems, and Hydrology XXI, 111490X (21 October 2019); https://doi.org/10.1117/12.2532853

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available