Hyperspectral Imaging (HSI) has been extensively utilized in many real-life applications because it benefits from the detailed spectral information contained in each pixel. Notably, the complex characteristics i.e., the nonlinear relation among the captured spectral information and the corresponding object of HSI data make accurate classification challenging for traditional methods. In the last few years, Deep Learning (DL) has been substantiated as a powerful feature extractor that effectively addresses the nonlinear problems that appeared in a number of computer vision tasks. This prompts the deployment of DL for HSI classification (HSIC) which revealed good performance. This survey enlists a systematic overview of DL for HSIC and compared state-of-the-art strategies on the said topic. Primarily, we will encapsulate the main challenges of traditional machine learning for HSIC and then we will acquaint the superiority of DL to address these problems. This survey breakdown the state-of-the-art DL frameworks into spectral features, spatial features, and together spatial-spectral features to systematically analyze the achievements (future research directions as well) of these frameworks for HSIC. Moreover, we will consider the fact that DL requires a large number of labeled training examples whereas acquiring such a number for HSIC is challenging in terms of time and cost. Therefore, this survey discusses some strategies to improve the generalization performance of DL strategies which can provide some future guidelines.
Hyperspectral images involve abundant spectral and spatial information, playing an irreplaceable role in land-cover classification. Recently, based on deep learning technologies, an increasing number of HSI classification approaches have been proposed, which demonstrate promising performance. However, previous studies suffer from two major drawbacks: 1) the architecture of most deep learning models is manually designed, relies on specialized knowledge, and is relatively tedious. Moreover, in HSI classifications, datasets captured by different sensors have different physical properties. Correspondingly, different models need to be designed for different datasets, which further increases the workload of designing architectures; 2) the mainstream framework is a patch-to-pixel framework. The overlap regions of patches of adjacent pixels are calculated repeatedly, which increases computational cost and time cost. Besides, the classification accuracy is sensitive to the patch size, which is artificially set based on extensive investigation experiments. To overcome the issues mentioned above, we firstly propose a 3D asymmetric neural network search algorithm and leverage it to automatically search for efficient architectures for HSI classifications. By analysing the characteristics of HSIs, we specifically build a 3D asymmetric decomposition search space, where spectral and spatial information are processed with different decomposition convolutions. Furthermore, we propose a new fast classification framework, i,e., pixel-to-pixel classification framework, which has no repetitive operations and reduces the overall cost. Experiments on three public HSI datasets captured by different sensors demonstrate the networks designed by our 3D-ANAS achieve competitive performance compared to several state-of-the-art methods, while having a much faster inference speed.
Convolutional neural networks (CNNs) have achieved prominent progress in recent years and demonstrated remarkable properties in spectral-spatial hyperspectral image (HSI) classification. However, conventional spatial-context based CNNs commonly adopt the single patchwise scheme to represent the to-be-classified samples, which often fails to completely investigate the wealthy spectral-spatial information in complicated situations. For instance, it has great probability to cause misclassifications on the irregular or inhomogeneous areas, especially for the borders across different classes. To counteract this deficiency, we propose a unified multi-direction network (MDN) for HSI classification, which can exhaustively explore the abundant spectral and detailed spatial-context information through multi-direction samples. Additionally, considering the image-spectrum merged structure of the HSI, 3D Squeeze-and-Excitation residual (3DSERes) blocks are devised in each stream of the framework to consecutively learn the spectral and spatial from low-level to high-level features. Specifically, the 3DSERes can not only facilitate fluent gradient in backpropagation through skip-connections, but also emphasize the significant spectral-spatial features and constrain the futile ones. This characteristic is beneficial to enhance the model's generalization capability even with limited training samples. Furthermore, for properly aggregating the multi-direction deep features, we exploit the simple yet effective attentional spectral prior (ASP) creatively through leveraging the original spectral correlations. Extensive experiment results on three benchmark datasets indicate that the proposed MDN-ASP can achieve promising classification performance compared to the state-of-the-art methods.
Classification is an important aspect of hyperspectral images processing and application. At present, the researchers mostly use the classic airborne hyperspectral imagery as the benchmark dataset. However, existing datasets suffer from three bottlenecks: (1) low spatial resolution; (2) low labeled pixels proportion; (3) low degree of subclasses distinction. In this paper, a new benchmark dataset named the Wuhan UAV-borne hyperspectral image (WHU-Hi) dataset was built for hyperspectral image classification. The WHU-Hi dataset with a high spectral resolution (nm level) and a very high spatial resolution (cm level), which we refer to here as H2 imager. Besides, the WHU-Hi dataset has a higher pixel labeling ratio and finer subclasses. Some start-of-art hyperspectral image classification methods benchmarked the WHU-Hi dataset, and the experimental results show that WHU-Hi is a challenging dataset. We hope WHU-Hi dataset can become a strong benchmark to accelerate future research.
Hyperspectral images (HSIs) provide rich spectral-spatial information with stacked hundreds of contiguous narrowbands. Due to the existence of noise and band correlation, the selection of informative spectral-spatial kernel features poses a challenge. This is often addressed by using convolutional neural networks (CNNs) with receptive field (RF) having fixed sizes. However, these solutions cannot enable neurons to effectively adjust RF sizes and cross-channel dependencies when forward and backward propagations are used to optimize the network. In this article, we present an attention-based adaptive spectral-spatial kernel improved residual network (A²S²K-ResNet) with spectral attention to capture discriminative spectral-spatial features for HSI classification in an end-to-end training fashion. In particular, the proposed network learns selective 3-D convolutional kernels to jointly extract spectral-spatial features using improved 3-D ResBlocks and adopts an efficient feature recalibration (EFR) mechanism to boost the classification performance. Extensive experiments are performed on three well-known hyperspectral data sets, i.e., IP, KSC, and UP, and the proposed A²S²K-ResNet can provide better classification results in terms of overall accuracy (OA), average accuracy (AA), and Kappa compared with the existing methods investigated. The source code will be made available at https://github.com/suvojit-0x55aa/A2S2K-ResNet.
Hyperspectral image classification (HIC) is an important but challenging task, and a problem that limits the algorithmic development in this field is that the ground truths of hyperspectral images (HSIs) are extremely hard to obtain. Recently a handful of HIC methods are developed based on the graph convolution networks (GCNs), which effectively relieves the scarcity of labeled data for deep learning based HIC methods. To further lift the classification performance, in this work we propose a graph convolution network (GCN) based framework for HSI classification that uses two clustering operations to better exploit multi-hop node correlations and also effectively reduce graph size. In particular, we first cluster the pixels with similar spectral features into a superpixel and build the graph based on the superpixels of the input HSI. Then instead of performing convolution over this superpixel graph, we further partition it into several sub-graphs by pruning the edges with weak weights, so as to strengthen the correlations of nodes with high similarity. This second round of clustering also further reduces the graph size, thus reducing the computation burden of graph convolution. Experimental results on three widely used benchmark datasets well prove the effectiveness of our proposed framework.
Herein, we present a system for hyperspectral image segmentation that utilizes multiple class--based denoising autoencoders which are efficiently trained. Moreover, we present a novel hyperspectral data augmentation method for labelled HSI data using linear mixtures of pixels from each class, which helps the system with edge pixels which are almost always mixed pixels. Finally, we utilize a deep neural network and morphological hole-filling to provide robust image classification. Results run on the Salinas dataset verify the high performance of the proposed algorithm.
Deep learning techniques have provided significant improvements in hyperspectral image (HSI) classification. The current deep learning based HSI classifiers follow a patch-based learning framework by dividing the image into overlapping patches. As such, these methods are local learning methods, which have a high computational cost. In this paper, a fast patch-free global learning (FPGA) framework is proposed for HSI classification. In FPGA, an encoder-decoder based FCN is utilized to consider the global spatial information by processing the whole image, which results in fast inference. However, it is difficult to directly utilize the encoder-decoder based FCN for HSI classification as it always fails to converge due to the insufficiently diverse gradients caused by the limited training samples. To solve the divergence problem and maintain the abilities of FCN of fast inference and global spatial information mining, a global stochastic stratified sampling strategy is first proposed by transforming all the training samples into a stochastic sequence of stratified samples. This strategy can obtain diverse gradients to guarantee the convergence of the FCN in the FPGA framework. For a better design of FCN architecture, FreeNet, which is a fully end-to-end network for HSI classification, is proposed to maximize the exploitation of the global spatial information and boost the performance via a spectral attention based encoder and a lightweight decoder. A lateral connection module is also designed to connect the encoder and decoder, fusing the spatial details in the encoder and the semantic features in the decoder. The experimental results obtained using three public benchmark datasets suggest that the FPGA framework is superior to the patch-based framework in both speed and accuracy for HSI classification. Code has been made available at: https://github.com/Z-Zheng/FreeNet.
This study is focused on applying genetic algorithms (GA) to model and band selection in hyperspectral image classification. We use a forensic-inspired data set of seven hyperspectral images with blood and five visually similar substances to test GA-optimised classifiers in two scenarios: when the training and test data come from the same image and when they come from different images, which is a more challenging task due to significant spectra differences. In our experiments we compare GA with a classic model optimisation through grid search. Our results show that GA-based model optimisation can reduce the number of bands and create an accurate classifier that outperforms the GS-based reference models, provided that during model optimisation it has access to examples similar to test data. We illustrate this with experiment highlighting the importance of a validation set.
The inclusion of spatial information into spectral classifiers for fine-resolution hyperspectral imagery has led to significant improvements in terms of classification performance. The task of spectral-spatial hyperspectral image classification has remained challenging because of high intraclass spectrum variability and low interclass spectral variability. This fact has made the extraction of spatial information highly active. In this work, a novel hyperspectral image classification framework using the fusion of dual spatial information is proposed, in which the dual spatial information is built by both exploiting pre-processing feature extraction and post-processing spatial optimization. In the feature extraction stage, an adaptive texture smoothing method is proposed to construct the structural profile (SP), which makes it possible to precisely extract discriminative features from hyperspectral images. The SP extraction method is used here for the first time in the remote sensing community. Then, the extracted SP is fed into a spectral classifier. In the spatial optimization stage, a pixel-level classifier is used to obtain the class probability followed by an extended random walker-based spatial optimization technique. Finally, a decision fusion rule is utilized to fuse the class probabilities obtained by the two different stages. Experiments performed on three data sets from different scenes illustrate that the proposed method can outperform other state-of-the-art classification techniques. In addition, the proposed feature extraction method, i.e., SP, can effectively improve the discrimination between different land covers.
Deep learning methods have shown considerable potential for hyperspectral image (HSI) classification, which can achieve high accuracy compared with traditional methods. However, they often need a large number of training samples and have a lot of parameters and high computational overhead. To solve these problems, this paper proposes a new network architecture, LiteDepthwiseNet, for HSI classification. Based on 3D depthwise convolution, LiteDepthwiseNet can decompose standard convolution into depthwise convolution and pointwise convolution, which can achieve high classification performance with minimal parameters. Moreover, we remove the ReLU layer and Batch Normalization layer in the original 3D depthwise convolution, which significantly improves the overfitting phenomenon of the model on small sized datasets. In addition, focal loss is used as the loss function to improve the model's attention on difficult samples and unbalanced data, and its training performance is significantly better than that of cross-entropy loss or balanced cross-entropy loss. Experiment results on three benchmark hyperspectral datasets show that LiteDepthwiseNet achieves state-of-the-art performance with a very small number of parameters and low computational cost.
Subspace learning (SL) plays an important role in hyperspectral image (HSI) classification, since it can provide an effective solution to reduce the redundant information in the image pixels of HSIs. Previous works about SL aim to improve the accuracy of HSI recognition. Using a large number of labeled samples, related methods can train the parameters of the proposed solutions to obtain better representations of HSI pixels. However, the data instances may not be sufficient enough to learn a precise model for HSI classification in real applications. Moreover, it is well-known that it takes much time, labor and human expertise to label HSI images. To avoid the aforementioned problems, a novel SL method that includes the probability assumption called subspace learning with conditional random field (SLCRF) is developed. In SLCRF, first, the 3D convolutional autoencoder (3DCAE) is introduced to remove the redundant information in HSI pixels. In addition, the relationships are also constructed using the spectral-spatial information among the adjacent pixels. Then, the conditional random field (CRF) framework can be constructed and further embedded into the HSI SL procedure with the semi-supervised approach. Through the linearized alternating direction method termed LADMAP, the objective function of SLCRF is optimized using a defined iterative algorithm. The proposed method is comprehensively evaluated using the challenging public HSI datasets. We can achieve stateof-the-art performance using these HSI sets.
Hyperspectral image classification (HIC) is an active research topic in remote sensing. Hyperspectral images typically generate large data cubes posing big challenges in data acquisition, storage, transmission and processing. To overcome these limitations, this paper develops a novel deep learning HIC approach based on compressive measurements of coded-aperture snapshot spectral imagers (CASSI), without reconstructing the complete hyperspectral data cube. A new kind of deep learning strategy, namely 3D coded convolutional neural network (3D-CCNN) is proposed to efficiently solve for the classification problem, where the hardware-based coded aperture is regarded as a pixel-wise connected network layer. An end-to-end training method is developed to jointly optimize the network parameters and the coded apertures with periodic structures. The accuracy of classification is effectively improved by exploiting the synergy between the deep learning network and coded apertures. The superiority of the proposed method is assessed over the state-of-the-art HIC methods on several hyperspectral datasets.
Recently, multiscale spatial features have been widely utilized to improve the hyperspectral image (HSI) classification performance. However, fixed-size neighborhood involving the contextual information probably leads to misclassifications, especially for the boundary pixels. Additionally, it has been demonstrated that deep neural network (DNN) is practical to extract representative features for the classification tasks. Nevertheless, under the condition of high dimensionality versus small sample sizes, DNN tends to be over-fitting and it is generally time-consuming due to the deep-level feature learning process. To alleviate the aforementioned issues, we propose a multiscale context-aware ensemble deep kernel extreme learning machine (MSC-EDKELM) for efficient HSI classification. First, the scene of the HSI data set is over-segmented in multiscale via using the adaptive superpixel segmentation technique. Second, superpixel pattern (SP) and attentional neighboring superpixel pattern (ANSP) are generated by leveraging the superpixel maps, which can automatically comprise local and global contextual information, respectively. Afterward, an ensemble deep kernel extreme learning machine (EDKELM) is presented to investigate the deep-level characteristics in the SP and ANSP. Finally, the category of each pixel is accurately determined by the decision fusion and weighted output layer fusion strategy. Experimental results on four real-world HSI data sets demonstrate that the proposed frameworks outperform some classic and state-of-theart methods with high computational efficiency, which can be employed to serve real-time applications.
Recently, convolutional neural networks (CNNs) have attracted enormous attention in pattern recognition and demonstrated excellent performance in hyperspectral image (HSI) classification. However, high-dimensional HSI dataset versus limited training samples is easy to cause the overfitting phenomenon in deep neural networks. Additionally, the intraclass distance of the embedding features extracted through the softmax-based CNNs may be greater than that of the interclass, which makes it difficult to further improve the classification accuracy. To address these issues, this article proposes a deep prototypical network with hybrid residual attention, which can effectively investigate the spectral-spatial information in the HSI. Specifically, in order to improve the generalization capability of the model, feature extraction with a hybrid residual attention module is presented to enhance the critical spectral-spatial features and suppress the useless ones in the classification task. Furthermore, a novel discriminant distance-based cross-entropy loss is proposed to increase the intraclass compactness, to obtain more superior results. Extensive experiments on three benchmark datasets are carried out to convincingly evaluate the proposed framework. With the generation of optimal prototypes representing each class and more discriminative embedding features, encouraging classification results are achieved compared with state-of-the-art methods.
Nowadays, deep learning methods, especially the Graph Convolutional Network (GCN), have shown impressive performance in hyperspectral image (HSI) classification. However, the current GCN-based methods treat graph construction and image classification as two separate tasks, which often results in suboptimal performance. Another defect of these methods is that they mainly focus on modeling the local pairwise importance between graph nodes while lack the capability to capture the global contextual information of HSI. In this paper, we propose a Multi-level GCN with Automatic Graph Learning method (MGCN-AGL) for HSI classification, which can automatically learn the graph information at both local and global levels. By employing attention mechanism to characterize the importance among spatially neighboring regions, the most relevant information can be adaptively incorporated to make decisions, which helps encode the spatial context to form the graph information at local level. Moreover, we utilize multiple pathways for local-level graph convolution, in order to leverage the merits from the diverse spatial context of HSI and to enhance the expressive power of the generated representations. To reconstruct the global contextual relations, our MGCN-AGL encodes the long range dependencies among image regions based on the expressive representations that have been produced at local level. Then inference can be performed along the reconstructed graph edges connecting faraway regions. Finally, the multi-level information is adaptively fused to generate the network output. In this means, the graph learning and image classification can be integrated into a unified framework and benefit each other. Extensive experiments have been conducted on three real-world hyperspectral datasets, which are shown to outperform the state-of-the-art methods.
Current hyperspectral image classification assumes that a predefined classification system is closed and complete, and there are no unknown or novel classes in the unseen data. However, this assumption may be too strict for the real world. Often, novel classes are overlooked when the classification system is constructed. The closed nature forces a model to assign a label given a new sample and may lead to overestimation of known land covers (e.g., crop area). To tackle this issue, we propose a multitask deep learning method that simultaneously conducts classification and reconstruction in the open world (named MDL4OW) where unknown classes may exist. The reconstructed data are compared with the original data; those failing to be reconstructed are considered unknown, based on the assumption that they are not well represented in the latent features due to the lack of labels. A threshold needs to be defined to separate the unknown and known classes; we propose two strategies based on the extreme value theory for few-shot and many-shot scenarios. The proposed method was tested on real-world hyperspectral images; state-of-the-art results were achieved, e.g., improving the overall accuracy by 4.94% for the Salinas data. By considering the existence of unknown classes in the open world, our method achieved more accurate hyperspectral image classification, especially under the few-shot context.
Deep learning based methods have seen a massive rise in popularity for hyperspectral image classification over the past few years. However, the success of deep learning is attributed greatly to numerous labeled samples. It is still very challenging to use only a few labeled samples to train deep learning models to reach a high classification accuracy. An active deep-learning framework trained by an end-to-end manner is, therefore, proposed by this paper in order to minimize the hyperspectral image classification costs. First, a deep densely connected convolutional network is considered for hyperspectral image classification. Different from the traditional active learning methods, an additional network is added to the designed deep densely connected convolutional network to predict the loss of input samples. Then, the additional network could be used to suggest unlabeled samples that the deep densely connected convolutional network is more likely to produce a wrong label. Note that the additional network uses the intermediate features of the deep densely connected convolutional network as input. Therefore, the proposed method is an end-to-end framework. Subsequently, a few of the selected samples are labelled manually and added to the training samples. The deep densely connected convolutional network is therefore trained using the new training set. Finally, the steps above are repeated to train the whole framework iteratively. Extensive experiments illustrates that the method proposed could reach a high accuracy in classification after selecting just a few samples.
We consider the problem of segmentation and classification of high-resolution and hyperspectral remote sensing images. Unlike conventional natural (RGB) images, the inherent large scale and complex structures of remote sensing images pose major challenges such as spatial object distribution diversity and spectral information extraction when existing models are directly applied for image classification. In this study, we develop an attention-based pyramid network for segmentation and classification of remote sensing datasets. Attention mechanisms are used to develop the following modules: i) a novel and robust attention-based multi-scale fusion method effectively fuses useful spatial or spectral information at different and same scales; ii) a region pyramid attention mechanism using region-based attention addresses the target geometric size diversity in large-scale remote sensing images; and iii cross-scale attention} in our adaptive atrous spatial pyramid pooling network adapts to varied contents in a feature-embedded space. Different forms of feature fusion pyramid frameworks are established by combining these attention-based modules. First, a novel segmentation framework, called the heavy-weight spatial feature fusion pyramid network (FFPNet), is proposed to address the spatial problem of high-resolution remote sensing images. Second, an end-to-end spatial--spectral FFPNet is presented for classifying hyperspectral images. Experiments conducted on ISPRS Vaihingen and ISPRS Potsdam high-resolution datasets demonstrate the competitive segmentation accuracy achieved by the proposed heavy-weight spatial FFPNet. Furthermore, experiments on the Indian Pines and the University of Pavia hyperspectral datasets indicate that the proposed spatial--spectral FFPNet outperforms the current state-of-the-art methods in hyperspectral image classification.
Hyperspectral image (HSI) classification is one of the most active research topics and has achieved promising results boosted by the recent development of deep learning. However, most state-of-the-art approaches tend to perform poorly when the training and testing images are on different domains, e.g., source domain and target domain, respectively, due to the spectral variability caused by different acquisition conditions. Transfer learning-based methods address this problem by pre-training in the source domain and fine-tuning on the target domain. Nonetheless, a considerable amount of data on the target domain has to be labeled and non-negligible computational resources are required to retrain the whole network. In this paper, we propose a new transfer learning scheme to bridge the gap between the source and target domains by projecting the HSI data from the source and target domains into a shared abundance space based on their own physical characteristics. In this way, the domain discrepancy would be largely reduced such that the model trained on the source domain could be applied on the target domain without extra efforts for data labeling or network retraining. The proposed method is referred to as physically-constrained transfer learning through shared abundance space (PCTL-SAS). Extensive experimental results demonstrate the superiority of the proposed method as compared to the state-of-the-art. The success of this endeavor would largely facilitate the deployment of HSI classification for real-world sensing scenarios.