Learning and Adapting Robust Features for Satellite Image Segmentation on Heterogeneous Data Sets

• Published in: IEEE transactions on geoscience and remote sensing Vol. 57; no. 9; pp. 6517 - 6529
• Main Authors: Ghassemi, Sina, Fiandrotti, Attilio, Francini, Gianluca, Magli, Enrico
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.09.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Coders; Convolutional neural network (CNN); Damage assessment; Datasets; deep learning; domain adaptation; encoder–decoder architecture; Human performance; Image processing; Image segmentation; Intervention; Neural networks; satellite image segmentation; Satellite imagery; Spaceborne remote sensing; Statistical methods; Statistics; Target recognition; Training
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2019.2906689

This paper addresses the problem of training a deep neural network for satellite image segmentation so that it can be deployed over images whose statistics differ from those used for training. For example, in postdisaster damage assessment, the tight time constraints make it impractical to train a network from scratch for each image to be segmented. We propose a convolutional encoder-decoder network able to learn visual representations of increasing semantic level as its depth increases, allowing it to generalize over a wider range of satellite images. Then, we propose two additional methods to improve the network performance over each specific image to be segmented. First, we observe that updating the batch normalization layers' statistics over the target image improves the network performance without human intervention. Second, we show that refining a trained network over a few samples of the image boosts the network performance with minimal human intervention. We evaluate our architecture over three data sets of satellite images, showing the state-of-the-art performance in binary segmentation of previously unseen images and competitive performance with respect to more complex techniques in a multiclass segmentation task.