KEYWORDS: Feature extraction, Hyperspectral imaging, Scene classification, Signal to noise ratio, Computer programming, Principal component analysis, Interference (communication), Unmanned aerial vehicles, Signal processing, GPU based image processing, Parallel computing
The classification of Hyperspectral images (HSIs) has been the focus of many recent research efforts, where feature extraction plays an important role. Discriminative feature extraction methods aim to reduce the data dimension of HSIs, retain effective image information to the greatest extent, and suppress noises at the same time. Besides, according to the characteristics of pixel-by-pixel-multi-band of HSIs and data redundancy between bands, the processing of HSIs in the classifier will bring huge computational overhead. In this paper, we present a parallel implementation of the improved noise adaptive principal component algorithm (INAPC) for feature extraction of hyperspectral images on commodity graphics processing units (GPUs). Aiming at maximizing the signal-to-noise ratio (SNR) instead of the variance, we firstly deploy two SVDs and more comprehensive noise estimation in the INAPC transform and constructed a complete feature extraction process. Then we deploy a complete CPU-GPU collaborative computing solution, and use several GPU programming optimization methods to achieve the maximum acceleration effect. Through the experiments on three real hyperspectral datasets, Experimental results show that the proposed INAPC has stable superiority and provides a significant speedup compared to the CPU implementation.
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.
Researches have shown that using convolution neural network (CNN) on spatial-spectral domain can improve the performance of hyperspectral image (HSI) classification in recently years. However, due to the existence of spectral redundancy and the high dimensional kernels used in 3D-CNN, the HSI classification models are often heavy with a huge number of parameters and high computation complexity. Motivated by the lightweight model, this paper introduced a modular convolution structure named three-dimensional interleaved group convolution (3D-IGC). This structure contains two successive group convolutions with a channel shuffle operation between them. First group convolution extracts feature on spatial-spectral domain. Then the channel shuffle enables cross-group information interchange. After this, the second group convolution perform the point-wise convolution. We proved that an IGC is wider than a normal convolution in most cases by inferred formula. The empirical results demonstrate that the increment of width in 3D-IGC model is beneficial to HSI classification with the computation complexity preserved, especially when the model has fewer parameters. Compared with the normal convolution, the 3D-IGC can largely reduce the redundancy of convolution filters in channel domain, which greatly decreases the number of parameters and the computation cost without losing classification accuracy. We also considered the effects of the 3D-IGC on deep neural networks, therefore we used the 3D-IGC to modify the residual unit and get a lightweight model compared with ResNets.
Deep residual networks (ResNets) can learn deep feature representation from hyperspectral images (HSIs), and therefore have been widely used for HSI classification. Despite their high accuracies, there still exist a lot of challenging cases, such as open world recognition, limited-sample learning and visualization of learned classification features, which cannot be well addressed. Most of the challenges in HSI classification can be attributed to the dependence on softmax based loss function and classifiers, which cause the lack of robustness for deep learning models and the hardness to visualize the learned classification features. To improve the robustness and achieve the visualization of learned classification features, we propose a novel learning framework called Residual Prototype Learning Network, a combination of residual network and prototypes learning mechanism. Under the framework, a prototype learning based loss function is proposed to enhance intra-class compactness and the inter-class separation of these feature representations; in addition, a prototype learning based classifier is simultaneously proposed to achieve the 2D or 3D visualization of the classification features. The effectiveness of our proposed learning framework is evaluated on several publicly available HSI benchmarks, and the experimental results show that our approach achieve better results than traditional softmax based ResNets.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.