Morphologically dilated convolutional neural network for hyperspectral image classification

Highlights：

• The neural network contains both 3D convolutional layers as well as a 2D convolutional layer. We use a mix of traditional and dilated convolution to increase the receptive field power, reduce trainable parameters, and reduce overfitting, which in turn results in the reduction of overall complexity of the model. The dilated convolution layer’s output feature map size is slightly less than the output of the traditional convolution layer, which reduces overall trainable parameters.

• The model simultaneously extracts the discriminatory spectral–spatial attributes or properties to achieve high classification accuracy by utilizing the spectral–spatial relationship.

• Experiments were performed on three different publicly available datasets to evaluate the performance of MDCNN model with other state-of-the-art methods.

摘要

•Mathematical morphological operations are applied to input hyperspectral data to extract spatial feature map as output. This output is concatenated with the input and fed into neural network to reduce the workload of CNN and provide better spatial features.•The neural network contains both 3D convolutional layers as well as a 2D convolutional layer. We use a mix of traditional and dilated convolution to increase the receptive field power, reduce trainable parameters, and reduce overfitting, which in turn results in the reduction of overall complexity of the model. The dilated convolution layer’s output feature map size is slightly less than the output of the traditional convolution layer, which reduces overall trainable parameters.•The model simultaneously extracts the discriminatory spectral–spatial attributes or properties to achieve high classification accuracy by utilizing the spectral–spatial relationship.•Experiments were performed on three different publicly available datasets to evaluate the performance of MDCNN model with other state-of-the-art methods.