Haze and Smoke Removal for Visualization of Multispectral Images: A DNN Physics Aware Architecture

Abstract

Remote sensing multispectral images are extensively used by applications in various fields. The degradation generated by haze or smoke negatively influences the visual analysis of the represented scene. In this paper, a deep neural network based method is proposed to address the visualization improvement of hazy and smoky images. The method is able to entirely exploit the information contained by all spectral bands, especially by the SWIR bands, which are usually not contaminated by haze or smoke. A dimensionality reduction of the spectral signatures or angular signatures is rapidly obtained by using a stacked autoencoders (SAE) trained based on contaminated images only. The latent characteristics obtained by the encoder are mapped to the R - G - B channels for visualization. The haze and smoke removal results of several Sentinel 2 scenes present an increased contrast and show the haze hidden areas from the initial natural color images.