Author:
Zhang Yangming,Yang Kun,Yuan Lei
Abstract
Abstract
In recent years, the convolutional neural network (CNN) has had a wide application in hyperspectral image (HSI) classification. HSI has many spectral and spatial features, which is well known that different spectral bands and spatial positions in the cubes have different discriminative abilities. Therefore, this paper proposes a classification method with CNN, which uses attention-enhanced spectral and spatial features (CNN-ASS). First, we use spectral and spatial subnetworks to extract spectral and spatial features. At the same time, spectral attention and spatial attention are added to the two subnetworks, respectively. Then, we sum the weights of the classification results of the two subnetworks to get the final classification result. This paper conducts experiments on three typical hyperspectral image data sets, and the experiment results show the CNN-ASS has a competitive advantage compared with some advanced methods.
Subject
General Physics and Astronomy
Reference17 articles.
1. ImageNet classification with deep convolutional neural networks;Krizhevsky,2012
2. Recurrent network models for human dynamics;Fragkiadaki,2015
3. Hyperspectral image classification via contextual deep learning;Ma,2015
4. Deep Learning Based Feature Selection for Remote Sensing Scene Classification;Zou;IEEE Geoscience and Remote Sensing Letters,2015
5. Deep Convolutional Neural Networks for Hyperspectral Image Classification;Wei,2015