Large-Scale Land Cover Mapping on Sentinel-1 SAR Imagery Using Deep Transfer Learning
Land cover mapping and monitoring are essential for understanding the environment and the effects of human activities on the environment. The automatic approaches to land cover mapping are predominantly based on the traditional machine learning that requires heuristic feature design. Such approaches are relatively slow and they are often suitable only for a particular type of satellite sensor or geographical area. Recently, deep learning has outperformed traditional machine learning approaches on a range of image processing tasks including image classification and segmentation. In this study, we demonstrated the suitability of deep learning models to land cover mapping on a large scale using satellite C-band SAR images. We used a set of 14 ESA Sentinel-1 scenes acquired during the summer season over a wide area in Finland representative of the land cover in the country. These imagery were used as an input to seven state-of-the-art deep-learning models for semantic segmentation, namely U-Net, DeepLabV3+, PSPNet, BiSeNet, SegNet, FC-DenseNet, and FRRN-B. These models were pre-trained on the ImageNet dataset and further fine-tuned in this study. To the best of our knowledge, this is the first successful demonstration of transfer learning for SAR imagery in the context of wide-area land-cover mapping. CORINE land cover map produced by the Finnish Environment Institute was used as a reference, and the models were trained to distinguish between 5 Level-1 CORINE classes. Upon the evaluation and benchmarking, we found that all the models demonstrated solid performance, with the top FC-DenseNet model achieving an overall accuracy of 90.66%. These results indicate the suitability of deep learning methods to support efficient wide-area mapping using satellite SAR imagery.