SAR Image Colorization: Converting Single-Polarization to Fully Polarimetric Using Deep Neural Networks
This work addresses a domain-specific problem in remote sensing by providing a method to enhance SAR data usability, though it is incremental as it builds on existing deep learning techniques.
The paper tackles the problem of converting single-polarization grayscale SAR images to fully polarimetric ones using deep neural networks, achieving reconstructed images that agree well with true full-pol images and enabling direct application of existing PolSAR applications.
A deep neural networks based method is proposed to convert single polarization grayscale SAR image to fully polarimetric. It consists of two components: a feature extractor network to extract hierarchical multi-scale spatial features of grayscale SAR image, followed by a feature translator network to map spatial feature to polarimetric feature with which the polarimetric covariance matrix of each pixel can be reconstructed. Both qualitative and quantitative experiments with real fully polarimetric data are conducted to show the efficacy of the proposed method. The reconstructed full-pol SAR image agrees well with the true full-pol image. Existing PolSAR applications such as model-based decomposition and unsupervised classification can be applied directly to the reconstructed full-pol SAR images. This framework can be easily extended to reconstruction of full-pol data from compact-pol data. The experiment results also show that the proposed method could be potentially used for interference removal on the cross-polarization channel.