Superpixel Partitioning of Very High Resolution Satellite Images for Large-Scale Classification Perspectives with Deep Convolutional Neural Networks

Tristan Postadjian (1) , Arnaud Le Bris (1) , Clément Mallet (1) , Hichem Sahbi (2)

1 MATIS - Méthodes d'Analyses pour le Traitement d'Images et la Stéréorestitution
2 MLIA - Machine Learning and Information Access

Supervised classification is the fundamental task for land-cover map generation. Deep neural networks recently outperformed other state-of-the-art classifiers in many machine learning challenges, from semantic segmentation to speech recognition. Such strategies are now commonly employed in the literature for the purpose of land-cover mapping. This paper develops the strategy for the use of deep networks to label very high resolution satellite images, with the perspective of mapping regions at country scale. Therefore, a superpixel based method is introduced in order to (i) ensure correct delineation of objects and (ii) perform the classification in a dense way but with decent computing times.

Domaines: Informatique [cs]

Tristan Postadjian, Arnaud Le Bris, Clément Mallet, Hichem Sahbi. Superpixel Partitioning of Very High Resolution Satellite Images for Large-Scale Classification Perspectives with Deep Convolutional Neural Networks. IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Jul 2018, Valencia, Spain. pp.1328-1331, ⟨10.1109/IGARSS.2018.8519222⟩. ⟨hal-02325850⟩