Cloud Detection Based on Multi-Scale Dilation Convolutional Neural Network for ZY-3 Satellite Remote Sensing Imagery

To improve the accuracy of cloud detection, we propose a multi-scale dilation convolutional neural network method. Combining with the characteristic of satellite images, we design the deep convolution network structure, which includes a deep-feature coding module, a local dilation perception module, and a cloud-dense decoding module. First, the deep-features of cloud arc obtained by the basic convolutional layer in conjunction with the coding module. Second, multi-scale dilation convolution layers jointed with pooling layers arc used to perceive corporately. A nonlinear function is employed in each block to improve the effectiveness of network model expression. Finally, the cloud-dense decoding module integrate the features corresponding to those included in the coding module and then utilize the L1 regularization upsampling algorithm to accomplish the end-to-end pixel-level cloud detection task. Cloud detection experiments arc performed in the typical cloud mask areas; the results arc compared with those of the Otsu algorithm and the FCN-8S method. The results indicate that the accuracy of proposed method is higher and the Kappa coefficient is effectively improved.