Toward an Unsupervised Colorization Framework for Historical Land Use Classification

Abstract : We present an unsupervised colorization framework to improve both the visualization and the automatic land use clas- sification of historical aerial images. We introduce a novel algorithm built upon a cyclic generative adversarial neural network and a texture replacement method to homogeneously and automatically colorize unpaired VHR images. We apply our framework on historical aerial images acquired in France between 1970 and 1990. We demonstrate that our approach helps to disentangle hard to classify land use classes and hence improves the overall land use classification.
Complete list of metadatas

Cited literature [6 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02122014
Contributor : Rémi Ratajczak <>
Submitted on : Tuesday, May 7, 2019 - 7:32:49 PM
Last modification on : Tuesday, May 21, 2019 - 1:14:28 AM

File

ratajczak2019-igarss.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02122014, version 1

Citation

Rémi Ratajczak, Carlos Crispim-Junior, Laure Tougne, Élodie Faure, Béatrice Fervers. Toward an Unsupervised Colorization Framework for Historical Land Use Classification. International Geoscience and Remote Sensing Symposium (IGARSS 2019), IEEE, Jul 2019, Yokohama, Japan. ⟨hal-02122014⟩

Share

Metrics

Record views

72

Files downloads

52