High-resolution image classification with convolutional networks - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

High-resolution image classification with convolutional networks

Emmanuel Maggiori
  • Fonction : Auteur
  • PersonId : 968713
Yuliya Tarabalka
  • Fonction : Auteur
  • PersonId : 929906
Pierre Alliez

Résumé

We address the pixelwise classification of high-resolution aerial imagery. While convolutional neural networks (CNNs) are gaining increasing attention in image analysis, it is still challenging to adapt them to produce fine-grained classification maps. This is due to a well-known trade-off between recognition and localization: the impressive capability of CNNs to recognize meaningful objects comes at the price of losing spatial precision. We here propose an architecture that addresses this issue. It learns features at different levels of detail and also learns a function to combine them. By integrating local and global information in an efficient and flexible manner, it outperforms previous techniques.
Fichier principal
Vignette du fichier
highres.pdf (1.36 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01660754 , version 1 (11-12-2017)

Identifiants

  • HAL Id : hal-01660754 , version 1

Citer

Emmanuel Maggiori, Yuliya Tarabalka, Guillaume Charpiat, Pierre Alliez. High-resolution image classification with convolutional networks. IEEE International Geoscience and Remote Sensing Symposium - IGARSS 2017, Jul 2017, Fort Worth, United States. ⟨hal-01660754⟩
252 Consultations
5706 Téléchargements

Partager

Gmail Facebook X LinkedIn More