Semantic segmentation of multispectral image using deep learning

This example shows how to perform semantic segmentation of a multispectral image using deep learning. The example uses an environmental application where the percentage of vegetation in a territory is measured. The percentage of vegetation is determined by the detected segmentation categories (e.g., trees, grass). The neural network uses convolution (CNN), rectified linear units (RELU) and max pooling to perform the encoding and decoding phases where the input is randomly chosen patches of a large image and