Traditional hyperspectral feature extraction methods focus on spectral features and neglect spatial features,its extraction method is set in advance and is not suitable for all hyperspectral images. Faced with these problems, we propose a three-dimensional convolutional network for hyperspectral classification, which consists of a convolutional layer,2 downsampling layers, 2 identification layers, a flatten layer, and 4 fully connected layers. The proposed network employs three-dimensional convolution operation to extract spectral-spatial features from hyperspectral images,there are two reasons for this, the first reason is three-dimensional convolution can automatically learn a large number of mappings between input and output.The second reason is three-dimensional convolution can effectively extract spectral-spatial features and improve network classification performance. In order to extract high-level features and prevent network performance degradation, the proposed network adopts residual connections.More importantly, the OpenMax algorithm is employed to detect hyperspectral unknown targets. In addition to the probability that the output belongs to a known class, the OpenmMx adds the probability that the predicted input belongs to unknown classes, as a result,the deep convolutional network can respond to inputs of unknown classes.experiments based on typical hyperspectral data show that the proposed network perform accurately in the known classes classification and the openmax algorithm is suitable for unknown targets detection of hyperspectral images.
|