Semantic Segmentation Refinement with Deep Edge Superpixels to Enhance Historical Land Cover - Archive ouverte HAL
Communication Dans Un Congrès Année : 2020

Semantic Segmentation Refinement with Deep Edge Superpixels to Enhance Historical Land Cover

Résumé

In this work, we explore a post-processing method to enhance coarse semantic segmentation of historical aerial images. We propose to use deep edges to generate semantically meaningful superpixels that we integrate as additional pairwise potentials in a dense conditional random field. We apply our approach on very high resolution images acquired between 1975 and 1995 and annotated with land use land cover labels. Results show the interest of our approach compared to other post-processing methods.
Fichier non déposé

Dates et versions

hal-03067384 , version 1 (15-12-2020)

Identifiants

Citer

Rémi Ratajczak, Carlos F Crispim-Junior, Béatrice Fervers, Élodie Faure, Laure Tougne. Semantic Segmentation Refinement with Deep Edge Superpixels to Enhance Historical Land Cover. International Geoscience and Remote Sensing Symposium (IGARSS 2020), IEEE, Sep 2020, Virtual Symposium, United States. ⟨10.1109/IGARSS39084.2020.9324375⟩. ⟨hal-03067384⟩
87 Consultations
0 Téléchargements

Altmetric

Partager

More