Deep learning for semantic segmentation of remote sensing images with rich spectral content
This addresses the need for improved processing tools for remote sensing data with increased volume and richness, though it appears incremental in applying existing deep learning techniques to this domain.
The paper tackles semantic segmentation of remote sensing images with rich spectral content by testing various 2D architectures and introducing a new 3D model to jointly process spatial and spectral dimensions, achieving comparison of different spectral fusion schemes and assessing the use of noisy ground truth for training and testing.
With the rapid development of Remote Sensing acquisition techniques, there is a need to scale and improve processing tools to cope with the observed increase of both data volume and richness. Among popular techniques in remote sensing, Deep Learning gains increasing interest but depends on the quality of the training data. Therefore, this paper presents recent Deep Learning approaches for fine or coarse land cover semantic segmentation estimation. Various 2D architectures are tested and a new 3D model is introduced in order to jointly process the spatial and spectral dimensions of the data. Such a set of networks enables the comparison of the different spectral fusion schemes. Besides, we also assess the use of a " noisy ground truth " (i.e. outdated and low spatial resolution labels) for training and testing the networks.