A Deep Learning Method for Near-Real-Time Cloud and Cloud Shadow Segmentation from Gaofen-1 Images

<div>The proposed network for cloud and cloud shadow segmentation. “Conv2d (<i>k </i>×<i> k</i>)” stands for the convolutional kernel with the size of <i>k </i>×<i> k</i>; “Batch Norm.” denotes batch normalization; “LReLU” denotes the leaky rectified linear units; and “RCDD” denotes the residual convolutional layer based on depth dropout.</div>

Computational Intelligence and Neuroscience

fig1

Figure 1

Figure 1: A Deep Learning Method for Near-Real-Time Cloud and Cloud Shadow Segmentation from Gaofen-1 Images 