Cloud and snow detection is one of the most important tasks in remote sensing (RS) image processing areas.Distinguishing cloud and snow from RS images is a challenging task. Short-wave infrared (SWIR) band has been widelyused for ice/snow detection. However, due to the lack of SWIR in high-resolution multispectral images, such as ZY-3satellite imagery, traditional SWIR-based methods are no longer practical. In order to mitigate the adverse effects ofcloud and snow detection, in this work, we propose an effective convolutional neural network (CNN) with a multilevel/scale feature fusion module (MFFM), a channel and spatial attention module, and an encoder-decoder networkstructure for cloud and snow detection form ZY-3 satellite imageries. The MFFM can aggregate multiple-level/scalefeature maps from the backbone network, ResNet50, for providing representative semantic feature information for cloudand snow detection. Channel and spatial attention module (CSAM) is used to further refine the semantic feature mapsthat outputs by MFFM thus making the network have better detection performance. The encoder-decoder structureallows the proposed CNN to restore detailed object boundaries thus making the detection results more accuracy.Experimental results on the ZY-3 satellite imageries dataset demonstrate that the proposed network can accurately detectcloud and snow, and outperforms several state-of-the-art methods.
展开▼