Toward a Yearly Country-Scale CORINE Land-Cover Map without Using Images: A Map Translation Approach

CORINE Land-Cover (CLC) and its by-products are considered as a reference baseline for land-cover mapping over Europe subsequent applications. CLC is currently tediously produced each six years from both the visual interpretation automatic analysis of large amount remote sensing images. Observing that various European countries regularly produce in parallel their own country-scaled maps with specifications, we propose to directly infer an existing map, therefore steadily decreasing updating time-frame. No additional image required. In this paper, focus more specifically on translating country-scale sensed OSO (France), into Land Cover, supervised way. not only differ nomenclature but also spatial resolution. We jointly harmonize dimensions using contextual asymmetrical Convolution Neural Network positional encoding. show use cases our method achieves superior performance than traditional semantic-based translation approach, achieving 81% accuracy all France, close targeted 85% CLC.