Can Semantic Labeling Methods Generalize to Any City? The Inria Aerial Image Labeling Benchmark - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Can Semantic Labeling Methods Generalize to Any City? The Inria Aerial Image Labeling Benchmark

Résumé

New challenges in remote sensing impose the necessity of designing pixel classification methods that, once trained on a certain dataset, generalize to other areas of the earth. This may include regions where the appearance of the same type of objects is significantly different. In the literature it is common to use a single image and split it into training and test sets to train a classifier and assess its performance, respectively. However, this does not prove the generalization capabilities to other inputs. In this paper, we propose an aerial image labeling dataset that covers a wide range of urban settlement appearances, from different geographic locations. Moreover, the cities included in the test set are different from those of the training set. We also experiment with convolutional neural networks on our dataset.
Fichier principal
Vignette du fichier
AerialImageLabelingDataset.pdf (5.5 Mo) Télécharger le fichier
Vignette du fichier
thumbnail.jpg (101.3 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Format : Figure, Image
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01468452 , version 1 (13-03-2017)

Identifiants

  • HAL Id : hal-01468452 , version 1

Citer

Emmanuel Maggiori, Yuliya Tarabalka, Guillaume Charpiat, Pierre Alliez. Can Semantic Labeling Methods Generalize to Any City? The Inria Aerial Image Labeling Benchmark. IEEE International Symposium on Geoscience and Remote Sensing (IGARSS), Jul 2017, Fort Worth, United States. ⟨hal-01468452⟩
2065 Consultations
11608 Téléchargements

Partager

Gmail Facebook X LinkedIn More