scholarly journals Adaptable Convolutional Network for Hyperspectral Image Classification

2021 ◽  
Vol 13 (18) ◽  
pp. 3637
Author(s):  
Mercedes E. Paoletti ◽  
Juan M. Haut
Keyword(s):  
High Performance ◽  
Hyperspectral Image ◽  
Filter Design ◽  
Computational Cost ◽  
Hyperspectral Data ◽  
Imaging Data ◽  
Convolutional Network ◽  
Spatial Features ◽  
Convolution Model ◽  
Convolution Kernels

Nowadays, a large number of remote sensing instruments are providing a massive amount of data within the frame of different Earth Observation missions. These instruments are characterized by the wide variety of data they can collect, as well as the impressive volume of data and the speed at which it is acquired. In this sense, hyperspectral imaging data has certain properties that make it difficult to process, such as its large spectral dimension coupled with problematic data variability. To overcome these challenges, convolutional neural networks have been proposed as classification models because of their ability to extract relevant spectral–spatial features and learn hidden patterns, along their great architectural flexibility. Their high performance relies on the convolution kernels to exploit the spatial relationships. Thus, filter design is crucial for the correct performance of models. Nevertheless, hyperspectral data may contain objects with different shapes and orientations, preventing filters from “seeing everything possible” during the decision making. To overcome this limitation, this paper proposes a novel adaptable convolution model based on deforming kernels combined with deforming convolution layers to fit their effective receptive field to the input data. The proposed adaptable convolutional network (named DKDCNet) has been evaluated over two well-known hyperspectral scenes, demonstrating that it is able to achieve better results than traditional strategies with similar computational cost for HSI classification.

scholarly journals Hybrid Depth-Separable Residual Networks for Hyperspectral Image Classification

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-17
Author(s):  
Cuijie Zhao ◽  
Hongdong Zhao ◽  
Guozhen Wang ◽  
Hong Chen
Keyword(s):  
Hyperspectral Image ◽  
Computational Cost ◽  
Ground Truth ◽  
Hyperspectral Data ◽  
Deep Convolutional Neural Networks ◽  
Convolutional Network ◽  
Benchmark Datasets ◽  
Deep Convolutional Network ◽  
3D Cnn

At present, the classification of the hyperspectral image (HSI) based on the deep convolutional network has made great progress. Due to the high dimensionality of spectral features, limited samples of ground truth, and high nonlinearity of hyperspectral data, effective classification of HSI based on deep convolutional neural networks is still difficult. This paper proposes a novel deep convolutional network structure, namely, a hybrid depth-separable residual network, for HSI classification, called HDSRN. The HDSRN model organically combines 3D CNN, 2D CNN, multiresidual network ROR, and depth-separable convolutions to extract deeper abstract features. On the one hand, due to the addition of multiresidual structures and skip connections, this model can alleviate the problem of over fitting, help the backpropagation of gradients, and extract features more fully. On the other hand, the depth-separable convolutions are used to learn the spatial feature, which reduces the computational cost and alleviates the decline in accuracy. Extensive experiments on the popular HSI benchmark datasets show that the performance of the proposed network is better than that of the existing prevalent methods.

scholarly journals Multiscale Spatial-Spectral Convolutional Network with Image-Based Framework for Hyperspectral Imagery Classification

2019 ◽  
Vol 11 (19) ◽  
pp. 2220 ◽  
Author(s):  
Ximin Cui ◽  
Ke Zheng ◽  
Lianru Gao ◽  
Bing Zhang ◽  
Dong Yang ◽  
...  
Keyword(s):  
Receptive Field ◽  
Hyperspectral Image ◽  
Receptive Fields ◽  
Feature Representation ◽  
Superior Performance ◽  
Processing Efficiency ◽  
Convolutional Network ◽  
Spatial Features ◽  
Classification Framework ◽  
Field Feature

Jointly using spatial and spectral information has been widely applied to hyperspectral image (HSI) classification. Especially, convolutional neural networks (CNN) have gained attention in recent years due to their detailed representation of features. However, most of CNN-based HSI classification methods mainly use patches as input classifier. This limits the range of use for spatial neighbor information and reduces processing efficiency in training and testing. To overcome this problem, we propose an image-based classification framework that is efficient and straightforward. Based on this framework, we propose a multiscale spatial-spectral CNN for HSIs (HyMSCN) to integrate both multiple receptive fields fused features and multiscale spatial features at different levels. The fused features are exploited using a lightweight block called the multiple receptive field feature block (MRFF), which contains various types of dilation convolution. By fusing multiple receptive field features and multiscale spatial features, the HyMSCN has comprehensive feature representation for classification. Experimental results from three real hyperspectral images prove the efficiency of the proposed framework. The proposed method also achieves superior performance for HSI classification.

scholarly journals A Dual-Path Small Convolution Network for Hyperspectral Image Classification

2021 ◽  
Vol 13 (17) ◽  
pp. 3411
Author(s):  
Lanxue Dang ◽  
Peidong Pang ◽  
Xianyu Zuo ◽  
Yang Liu ◽  
Jay Lee
Keyword(s):  
Hyperspectral Image ◽  
Middle Layer ◽  
Hyperspectral Data ◽  
Model Parameters ◽  
Data Sets ◽  
Testing Time ◽  
Spatial Features ◽  
Current State ◽  
Proposed Model ◽  
Fully Connected

Convolutional neural network (CNN) has shown excellent performance in hyperspectral image (HSI) classification. However, the structure of the CNN models is complex, requiring many training parameters and floating-point operations (FLOPs). This is often inefficient and results in longer training and testing time. In addition, the label samples of hyperspectral data are limited, and a deep network often causes the over-fitting phenomenon. Hence, a dual-path small convolution (DPSC) module is proposed. It is composed of two 1 × 1 small convolutions with a residual path and a density path. It can effectively extract abstract features from HSI. A dual-path small convolution network (DPSCN) is constructed by stacking DPSC modules. Specifically, the proposed model uses a DPSC module to complete the extraction of spectral and spectral–spatial features successively. It then uses a global average pooling layer at the end of the model to replace the conventional fully connected layer to complete the final classification. In the implemented study, all convolutional layers of the proposed network, except the middle layer, use 1 × 1 small convolution, effectively reduced model parameters and increased the speed of feature extraction processes. DPSCN was compared with several current state-of-the-art models. The results on three benchmark HSI data sets demonstrated that the proposed model is of lower complexity, has stronger generalization ability, and has higher classification efficiency.

scholarly journals Multiscale Deep Spatial Feature Extraction Using Virtual RGB Image for Hyperspectral Imagery Classification

2020 ◽  
Vol 12 (2) ◽  
pp. 280 ◽  
Author(s):  
Liqin Liu ◽  
Zhenwei Shi ◽  
Bin Pan ◽  
Ning Zhang ◽  
Huanlin Luo ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Deep Learning ◽  
Hyperspectral Image ◽  
Feature Fusion ◽  
Hyperspectral Data ◽  
Learning Technology ◽  
Learning Networks ◽  
Spatial Features ◽  
Training Samples ◽  
Rgb Image

In recent years, deep learning technology has been widely used in the field of hyperspectral image classification and achieved good performance. However, deep learning networks need a large amount of training samples, which conflicts with the limited labeled samples of hyperspectral images. Traditional deep networks usually construct each pixel as a subject, ignoring the integrity of the hyperspectral data and the methods based on feature extraction are likely to lose the edge information which plays a crucial role in the pixel-level classification. To overcome the limit of annotation samples, we propose a new three-channel image build method (virtual RGB image) by which the trained networks on natural images are used to extract the spatial features. Through the trained network, the hyperspectral data are disposed as a whole. Meanwhile, we propose a multiscale feature fusion method to combine both the detailed and semantic characteristics, thus promoting the accuracy of classification. Experiments show that the proposed method can achieve ideal results better than the state-of-art methods. In addition, the virtual RGB image can be extended to other hyperspectral processing methods that need to use three-channel images.

Active Learning via Multi-View and Local Proximity Co-Regularization for Hyperspectral Image Classification

2011 ◽  
Vol 5 (3) ◽  
pp. 618-628 ◽  
Author(s):  
Wei Di ◽  
Melba M. Crawford
Keyword(s):  
Active Learning ◽  
Image Classification ◽  
Hyperspectral Image ◽  
Computational Cost ◽  
Hyperspectral Data ◽  
Unlabeled Data ◽  
Support Vector ◽  
Svm Classifier ◽  
Small Subset ◽  
Hyperspectral Image Classification

A novel co-regularization framework for active learning is proposed for hyperspectral image classification. The first regularizer explores the intrinsic multi-view information embedded in the hyperspectral data. By adaptively and quantitatively measuring the disagreement level, it focuses only on samples with high uncertainty and builds a contention pool which is a small subset of the overall unlabeled data pool, thereby mitigating the computational cost. The second regularizer is based on the “consistency assumption” and designed on a spatial or the spectral based manifold space. It serves to further focus on the most informative samples within the contention pool by penalizing rapid changes in the classification function evaluated on proximally close samples in a local region. Such changes may be due to the lack of capability of the current learner to describe the unlabeled data. Incorporating manifold learning into the active learning process enforces the clustering assumption and avoids the degradation of the distance measure associated with the original high-dimensional spectral features. One spatial and two local spectral embedding methods are considered in this study, in conjunction with the support vector machine (SVM) classifier implemented with a radial basis function (RBF) kernel. Experiments show excellent performance on AVIRIS and Hyperion hyperspectral data as compared to random sampling and the state-of-the-art SVMSIMPLE.

scholarly journals Spectral and Spatial Classification of Hyperspectral Images Based on Random Multi-Graphs

2018 ◽  
Vol 10 (8) ◽  
pp. 1271 ◽  
Author(s):  
Feng Gao ◽  
Qun Wang ◽  
Junyu Dong ◽  
Qizhi Xu
Keyword(s):  
Image Classification ◽  
Spatial Information ◽  
Hyperspectral Image ◽  
Small Sample ◽  
Hyperspectral Data ◽  
Hyperspectral Images ◽  
High Dimensional ◽  
Hyperspectral Image Classification ◽  
Spatial Classification ◽  
Spatial Features

Hyperspectral image classification has been acknowledged as the fundamental and challenging task of hyperspectral data processing. The abundance of spectral and spatial information has provided great opportunities to effectively characterize and identify ground materials. In this paper, we propose a spectral and spatial classification framework for hyperspectral images based on Random Multi-Graphs (RMGs). The RMG is a graph-based ensemble learning method, which is rarely considered in hyperspectral image classification. It is empirically verified that the semi-supervised RMG deals well with small sample setting problems. This kind of problem is very common in hyperspectral image applications. In the proposed method, spatial features are extracted based on linear prediction error analysis and local binary patterns; spatial features and spectral features are then stacked into high dimensional vectors. The high dimensional vectors are fed into the RMG for classification. By randomly selecting a subset of features to create a graph, the proposed method can achieve excellent classification performance. The experiments on three real hyperspectral datasets have demonstrated that the proposed method exhibits better performance than several closely related methods.

scholarly journals Depthwise Separable Relation Network for Small Sample Hyperspectral Image Classification

Symmetry ◽  
2021 ◽  
Vol 13 (9) ◽  
pp. 1673
Author(s):  
Aili Wang ◽  
Chengyang Liu ◽  
Dong Xue ◽  
Haibin Wu ◽  
Yuxiao Zhang ◽  
...  
Keyword(s):  
Hyperspectral Image ◽  
Computational Cost ◽  
Optimal Solution ◽  
Image Data ◽  
Small Sample ◽  
Hyperspectral Data ◽  
Small Samples ◽  
Model Training ◽  
Metric Distance ◽  
Training Efficiency

Although hyperspectral data provide rich feature information and are widely used in other fields, the data are still scarce. Training small sample data classification is still a major challenge for HSI classification based on deep learning. Recently, the method of mining sample relationships has been proved to be an effective method for training small samples. However, this strategy requires high computational power, which will increase the difficulty of network model training. This paper proposes a modified depthwise separable relational network to deeply capture the similarity between samples. In addition, in order to effectively mine the similarity between samples, the feature vectors of support samples and query samples are symmetrically spliced. According to the metric distance between symmetrical structures, the dependence of the model on samples can be effectively reduced. Firstly, in order to improve the training efficiency of the model, depthwise separable convolution is introduced to reduce the computational cost of the model. Secondly, the Leaky-ReLU function effectively activates all neurons in each layer of neural network to improve the training efficiency of the model. Finally, the cosine annealing learning rate adjustment strategy is introduced to avoid the model falling into the local optimal solution and enhance the robustness of the model. The experimental results on two widely used hyperspectral remote sensing image data sets (Pavia University and Kennedy Space Center) show that compared with seven other advanced classification methods, the proposed method achieves better classification accuracy under the condition of limited training samples.

scholarly journals Spectral-Spatial Hyperspectral Image Semisupervised Classification by Fusing Maximum Noise Fraction and Adaptive Random Multigraphs

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Eryang Chen ◽  
Ruichun Chang ◽  
Kaibo Shi ◽  
Ansheng Ye ◽  
Fang Miao ◽  
...  
Keyword(s):  
Spatial Information ◽  
Hyperspectral Image ◽  
Hyperspectral Data ◽  
Spatial Features ◽  
Training Samples ◽  
Semisupervised Classification ◽  
Ground Object ◽  
Multiscale Local Binary Pattern ◽  
Noise Fraction ◽  
Reduced Data

Hyperspectral images (HSIs) contain large amounts of spectral and spatial information, and this provides the possibility for ground object classification. However, when using the traditional method, achieving a satisfactory classification result is difficult because of the insufficient labeling of samples in the training set. In addition, parameter adjustment during HSI classification is time-consuming. This paper proposes a novel fusion method based on the maximum noise fraction (MNF) and adaptive random multigraphs for HSI classification. Considering the overall spectrum of the object and the correlation of adjacent bands, the MNF was utilized to reduce the spectral dimension. Next, a multiscale local binary pattern (LBP) analysis was performed on the MNF dimension-reduced data to extract the spatial features of different scales. The obtained multiscale spatial features were then stacked with the MNF dimension-reduced spectral features to form multiscale spectral-spatial features (SSFs), which were sent into the RMG for HSI classification. Optimal performance was obtained by fusion. For all three real datasets, our method achieved competitive results with only 10 training samples. More importantly, the classification parameters corresponding to different hyperspectral data can be automatically optimized using our method.

Unmixing of large-scale hyperspectral data based on projected mini-batch gradient descent

2017 ◽  
Vol 15 (06) ◽  
pp. 1750059 ◽  
Author(s):  
Jing Li ◽  
Xiaorun Li ◽  
Liaoying Zhao
Keyword(s):  
Minimization Problem ◽  
Gradient Descent ◽  
Large Scale ◽  
Hyperspectral Image ◽  
Computational Cost ◽  
Nonnegative Matrix ◽  
Image Data ◽  
Real Data ◽  
Optimization Method ◽  
Hyperspectral Data

The minimization problem of reconstruction error over large hyperspectral image data is one of the most important problems in unsupervised hyperspectral unmixing. A variety of algorithms based on nonnegative matrix factorization (NMF) have been proposed in the literature to solve this minimization problem. One popular optimization method for NMF is the projected gradient descent (PGD). However, as the algorithm must compute the full gradient on the entire dataset at every iteration, the PGD suffers from high computational cost in the large-scale real hyperspectral image. In this paper, we try to alleviate this problem by introducing a mini-batch gradient descent-based algorithm, which has been widely used in large-scale machine learning. In our method, the endmember can be updated pixel set by pixel set while abundance can be updated band set by band set. Thus, the computational cost is lowered to a certain extent. The performance of the proposed algorithm is quantified in the experiment on synthetic and real data.

scholarly journals Multi-Feature Manifold Discriminant Analysis for Hyperspectral Image Classification

2019 ◽  
Vol 11 (6) ◽  
pp. 651 ◽  
Author(s):  
Hong Huang ◽  
Zhengying Li ◽  
Yinsong Pan
Keyword(s):  
Discriminant Analysis ◽  
Spatial Information ◽  
Hyperspectral Image ◽  
Feature Fusion ◽  
Local Binary Patterns ◽  
Hyperspectral Data ◽  
Spectral Features ◽  
Spatial Features ◽  
Combined Features ◽  
Low Dimensional

Hyperspectral image (HSI) provides both spatial structure and spectral information for classification, but many traditional methods simply concatenate spatial features and spectral features together that usually lead to the curse-of-dimensionality and unbalanced representation of different features. To address this issue, a new dimensionality reduction (DR) method, termed multi-feature manifold discriminant analysis (MFMDA), was proposed in this paper. At first, MFMDA explores local binary patterns (LBP) operator to extract textural features for encoding the spatial information in HSI. Then, under graph embedding framework, the intrinsic and penalty graphs of LBP and spectral features are constructed to explore the discriminant manifold structure in both spatial and spectral domains, respectively. After that, a new spatial-spectral DR model for multi-feature fusion is built to extract discriminant spatial-spectral combined features, and it not only preserves the similarity relationship between spectral features and LBP features but also possesses strong discriminating ability in the low-dimensional embedding space. Experiments on Indian Pines, Heihe and Pavia University (PaviaU) hyperspectral data sets demonstrate that the proposed MFMDA method performs significantly better than some state-of-the-art methods using only single feature or simply stacking spectral features and spatial features together, and the classification accuracies of it can reach 95.43%, 97.19% and 96.60%, respectively.

Sign in / Sign up

Export Citation Format

Share Document