GLOBAL CONTEXT AIDED SEMANTIC SEGMENTATION FOR CLOUD DETECTION OF REMOTE SENSING IMAGES

Abstract. Cloud detection is a vital preprocessing step for remote sensing image applications, which has been widely studied through Convolutional Neural Networks (CNNs) in recent years. However, the available CNN-based works only extract local/non-local features by stacked convolution and pooling layers, ignoring global contextual information of the input scenes. In this paper, a novel segmentation-based network is proposed for cloud detection of remote sensing images. We add a multi-class classification branch to a U-shaped semantic segmentation network. Through the encoder-decoder architecture, pixelwise classification of cloud, shadow and landcover can be obtained. Besides, the multi-class classification branch is built on top of the encoder module to extract global context by identifying what classes exist in the input scene. Linear representation encoded global contextual information is learned in the added branch, which is to be combined with featuremaps of the decoder and can help to selectively strengthen class-related features or weaken class-unrelated features at different scales. The whole network is trained and tested in an end-to-end fashion. Experiments on two Landsat-8 cloud detection datasets show better performance than other deep learning methods, which finally achieves 90.82% overall accuracy and 0.6992 mIoU on the SPARCS dataset, demonstrating the effectiveness of the proposed framework for cloud detection in remote sensing images.