Centre de documentation
scientifique

High-resolution aerial image labeling with convolutional neural networks / Emmanuel Maggiori in IEEE Transactions on geoscience and remote sensing, vol 55 n° 12 (December 2017)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 55 n° 12 (December 2017) . - pp 7092 - 7103 Titre : High-resolution aerial image labeling with convolutional neural networks Type de document : Article/Communication Auteurs : Emmanuel Maggiori, Auteur ; Yuliya Tarabalka, Auteur ; Guillaume Charpiat, Auteur ; Pierre Alliez, Auteur Année de publication : 2017 Article en page(s) : pp 7092 - 7103 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] image aérienne [Termes IGN] indexation sémantique [Termes IGN] inférence sémantique [Termes IGN] réseau neuronal convolutif Résumé : (Auteur) The problem of dense semantic labeling consists in assigning semantic labels to every pixel in an image. In the context of aerial image analysis, it is particularly important to yield high-resolution outputs. In order to use convolutional neural networks (CNNs) for this task, it is required to design new specific architectures to provide fine-grained classification maps. Many dense semantic labeling CNNs have been recently proposed. Our first contribution is an in-depth analysis of these architectures. We establish the desired properties of an ideal semantic labeling CNN, and assess how those methods stand with regard to these properties. We observe that even though they provide competitive results, these CNNs often underexploit properties of semantic labeling that could lead to more effective and efficient architectures. Out of these observations, we then derive a CNN framework specifically adapted to the semantic labeling problem. In addition to learning features at different resolutions, it learns how to combine these features. By integrating local and global information in an efficient and flexible manner, it outperforms previous techniques. We evaluate the proposed framework and compare it with state-of-the-art architectures on public benchmarks of high-resolution aerial image labeling. Numéro de notice : A2017-769 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2017.2740362 En ligne : https://doi.org/10.1109/TGRS.2017.2740362 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=88808 [article]

Recurrent neural networks to correct satellite image classification maps / Emmanuel Maggiori in IEEE Transactions on geoscience and remote sensing, vol 55 n° 9 (September 2017)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 55 n° 9 (September 2017) . - pp 4962 - 4971 Titre : Recurrent neural networks to correct satellite image classification maps Type de document : Article/Communication Auteurs : Emmanuel Maggiori, Auteur ; Guillaume Charpiat, Auteur ; Yuliya Tarabalka, Auteur ; Pierre Alliez, Auteur Année de publication : 2017 Article en page(s) : pp 4962 - 4971 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage automatique [Termes IGN] classification par réseau neuronal [Termes IGN] convolution (signal) [Termes IGN] itération [Termes IGN] réseau neuronal convolutif Résumé : (Auteur) While initially devised for image categorization, convolutional neural networks (CNNs) are being increasingly used for the pixelwise semantic labeling of images. However, the proper nature of the most common CNN architectures makes them good at recognizing but poor at localizing objects precisely. This problem is magnified in the context of aerial and satellite image labeling, where a spatially fine object outlining is of paramount importance. Different iterative enhancement algorithms have been presented in the literature to progressively improve the coarse CNN outputs, seeking to sharpen object boundaries around real image edges. However, one must carefully design, choose, and tune such algorithms. Instead, our goal is to directly learn the iterative process itself. For this, we formulate a generic iterative enhancement process inspired from partial differential equations, and observe that it can be expressed as a recurrent neural network (RNN). Consequently, we train such a network from manually labeled data for our enhancement task. In a series of experiments, we show that our RNN effectively learns an iterative process that significantly improves the quality of satellite image classification maps. Numéro de notice : A2017-659 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2017.2697453 En ligne : http://dx.doi.org/10.1109/TGRS.2017.2697453 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=87070 [article]