Skip to Main content Skip to Navigation
Conference papers

Réseaux de neurones profonds et fusion de données pour la segmentation sémantique d'images aériennes

Abstract : This work investigates the use of deep fully convolutional neural networks (DFCNN) for pixel-wise scene labeling of Earth Observation images. Especially, we train a variant of the SegNet architecture on remote sensing data over an urban area and study different strategies for performing accurate semantic segmentation. Our contributions are the following : 1) we transfer efficiently a DFCNN from generic everyday images to remote sensing images ; 2) we perform data fusion from heterogeneous sensors (optical and laser) using residual correction. Our framework improves state-of-the-art accuracy on the ISPRS Vaihingen 2D Semantic Labeling dataset.
Document type :
Conference papers
Complete list of metadatas

Cited literature [38 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01672871
Contributor : Sébastien Lefèvre <>
Submitted on : Thursday, June 7, 2018 - 11:25:29 AM
Last modification on : Wednesday, August 5, 2020 - 3:50:49 AM
Long-term archiving on: : Saturday, September 8, 2018 - 1:25:55 PM

Identifiers

  • HAL Id : hal-01672871, version 1

Citation

Nicolas Audebert, Bertrand Le Saux, Sébastien Lefèvre. Réseaux de neurones profonds et fusion de données pour la segmentation sémantique d'images aériennes. ORASIS, GREYC, 2017, Colleville-sur-Mer, France. ⟨hal-01672871⟩

Share

Metrics

Record views

809

Files downloads

2721