Semantic Representation Fusion-Based Network for Robust Land Cover Classification in Foggy Conditions

Abstract

A precise and robust classification of land cover is crucial for land use estimation. A robust model that can provide rich semantic information is imperative for the challenging task of land cover classification in foggy conditions. We propose Semantic Representation Enhancement ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SRE</i> ) and Semantic Representation Aggregation ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SRA</i> ) modules for the fusion of semantic representation. The Dense Depthwise Separable Atrous Spatial Pyramid Pooling ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DDS-ASPP</i> ) module in SRE possesses a large receptive field, which covers an extensive scale range. Enhanced asymmetric convolution module ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">EACM</i> ) in SRE focus on features of various directions. DDS-ASPP and EACM generate the class-based and pixel-based representation respectively. By means of SRA and dual representations, we model the relationship between global context and coarse class regions to capture long-range correlation. Moreover, evaluated on Potsdam, Vaihingen and custom real-world datasets under fog, we demonstrate that our work is competitive with state-of-the-art models in terms of robustness. Code will be available at https://github.com/bowenroom/Robust-land-cover-classification.