Skip to Main content Skip to Navigation
Conference papers

Semantic Segmentation of Earth Observation Data Using Multimodal and Multi-scale Deep Networks

Nicolas Audebert 1, 2 Bertrand Le Saux 1 Sébastien Lefèvre 2
2 OBELIX - Environment observation with complex imagery
UBS - Université de Bretagne Sud, IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
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 introduce a multi-kernel convolutional layer for fast aggregation of predictions at multiple scales; 3) 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.
Complete list of metadatas

Cited literature [35 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01360166
Contributor : Nicolas Audebert <>
Submitted on : Tuesday, September 20, 2016 - 4:05:39 PM
Last modification on : Friday, July 10, 2020 - 4:26:01 PM

Files

accv16_final_483.pdf
Files produced by the author(s)

Identifiers

Citation

Nicolas Audebert, Bertrand Le Saux, Sébastien Lefèvre. Semantic Segmentation of Earth Observation Data Using Multimodal and Multi-scale Deep Networks. Asian Conference on Computer Vision (ACCV16), Nov 2016, Taipei, Taiwan. ⟨10.1007/978-3-319-54181-5_12⟩. ⟨hal-01360166⟩

Share

Metrics

Record views

2293

Files downloads

856