scholarly journals Hyperspectral Image Classification Based on Cross-Scene Adaptive Learning

Symmetry ◽  
2021 ◽  
Vol 13 (10) ◽  
pp. 1878
Author(s):  
Aili Wang ◽  
Chengyang Liu ◽  
Dong Xue ◽  
Haibin Wu ◽  
Yuxiao Zhang ◽  
...  
Keyword(s):  
Image Classification ◽  
Adaptive Learning ◽  
Classification Accuracy ◽  
Hyperspectral Image ◽  
Computational Cost ◽  
Manhattan Distance ◽  
Hyperspectral Image Classification ◽  
Shot Classification ◽  
Manhattan Metric ◽  
Deep Embedding

Aiming at few-shot classification in the field of hyperspectral remote sensing images, this paper proposes a classification method based on cross-scene adaptive learning. First, based on the unsupervised domain adaptive technology, cross-scene knowledge transfer learning is carried out to reduce the differences between source scene and target scene. At the same time, depthwise over-parameterized convolution is used in the deep embedding model to improve the convergence speed and feature extraction ability. Second, two symmetrical subnetworks are designed in the model to further reduce the differences between source scene and target scene. Then, Manhattan distance is learned in the Manhattan metric space in order to reduce the computational cost of the model. Finally, the weighted K-nearest neighbor is introduced for classification, in which the weighted Manhattan metric distance is assigned to the clustered samples to improve the processing ability to the imbalanced hyperspectral image data. The effectiveness of the proposed algorithm is verified on the Pavia and Indiana hyperspectral dataset. The overall classification accuracy is 90.90% and 65.01%. Compared with six other kinds of hyperspectral image classification methods, the proposed cross-scene method has better classification accuracy.

scholarly journals Hyperspectral Image Classification Based on Multi-Scale Residual Network with Attention Mechanism

2021 ◽  
Vol 13 (3) ◽  
pp. 335
Author(s):  
Yuhao Qing ◽  
Wenyi Liu
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Image Classification ◽  
Classification Accuracy ◽  
Hyperspectral Image ◽  
Principal Component ◽  
Hyperspectral Image Classification ◽  
Deep Network ◽  
Multi Scale

In recent years, image classification on hyperspectral imagery utilizing deep learning algorithms has attained good results. Thus, spurred by that finding and to further improve the deep learning classification accuracy, we propose a multi-scale residual convolutional neural network model fused with an efficient channel attention network (MRA-NET) that is appropriate for hyperspectral image classification. The suggested technique comprises a multi-staged architecture, where initially the spectral information of the hyperspectral image is reduced into a two-dimensional tensor, utilizing a principal component analysis (PCA) scheme. Then, the constructed low-dimensional image is input to our proposed ECA-NET deep network, which exploits the advantages of its core components, i.e., multi-scale residual structure and attention mechanisms. We evaluate the performance of the proposed MRA-NET on three public available hyperspectral datasets and demonstrate that, overall, the classification accuracy of our method is 99.82 %, 99.81%, and 99.37, respectively, which is higher compared to the corresponding accuracy of current networks such as 3D convolutional neural network (CNN), three-dimensional residual convolution structure (RES-3D-CNN), and space–spectrum joint deep network (SSRN).

A NEW SPECTRAL–SPATIAL JOINTED HYPERSPECTRAL IMAGE CLASSIFICATION APPROACH BASED ON FRACTAL DIMENSION ANALYSIS

Fractals ◽  
2019 ◽  
Vol 27 (05) ◽  
pp. 1950079
Author(s):  
JUNYING SU ◽  
YINGKUI LI ◽  
QINGWU HU
Keyword(s):  
Fractal Dimension ◽  
Image Classification ◽  
Classification Accuracy ◽  
Hyperspectral Image ◽  
Spatial Domain ◽  
Spectral Domain ◽  
Hyperspectral Image Classification ◽  
Self Similarity ◽  
Classification Approach ◽  
Image Set

To maximize the advantages of both spectral and spatial information, we introduce a new spectral–spatial jointed hyperspectral image classification approach based on fractal dimension (FD) analysis of spectral response curve (SRC) in spectral domain and extended morphological processing in spatial domain. This approach first calculates the FD image based on the whole SRC of the hyperspectral image and decomposes the SRC into segments to derive the FD images with each SRC segment. These FD images based on the segmented SRC are composited into a multidimensional FD image set in spectral domain. Then, the extended morphological profiles (EMPs) are derived from the image set through morphological open and close operations in spatial domain. Finally, all these EMPs and FD features are combined into one feature vector for a probabilistic support vector machine (SVM) classification. This approach was demonstrated using three hyperspectral images in urban areas of the university campus and downtown area of Pavia, Italy, and the Washington DC Mall area in the USA, respectively. We assessed the potential and performance of this approach by comparing with PCA-based method in hyperspectral image classification. Our results indicate that the classification accuracy of our proposed method is much higher than the accuracies of the classification methods based on the spectral or spatial domain alone, and similar to or slightly higher than the classification accuracy of PCA-based spectral–spatial jointed classification method. The proposed FD approach also provides a new self-similarity measure of land class in spectral domain, a unique property to represent hyperspectral self-similarity of SRC in hyperspectral imagery.

scholarly journals Hyperspectral Image Classification Using Feature Relations Map Learning

2020 ◽  
Vol 12 (18) ◽  
pp. 2956 ◽  
Author(s):  
Peng Dou ◽  
Chao Zeng
Keyword(s):  
Image Classification ◽  
Classification Accuracy ◽  
Hyperspectral Image ◽  
Image Data ◽  
Hyperspectral Images ◽  
Hyperspectral Image Classification ◽  
Map Learning ◽  
Feature Extractor ◽  
Spatial Domains ◽  
Normalized Difference Index

Recently, deep learning has been reported to be an effective method for improving hyperspectral image classification and convolutional neural networks (CNNs) are, in particular, gaining more and more attention in this field. CNNs provide automatic approaches that can learn more abstract features of hyperspectral images from spectral, spatial, or spectral-spatial domains. However, CNN applications are focused on learning features directly from image data—while the intrinsic relations between original features, which may provide more information for classification, are not fully considered. In order to make full use of the relations between hyperspectral features and to explore more objective features for improving classification accuracy, we proposed feature relations map learning (FRML) in this paper. FRML can automatically enhance the separability of different objects in an image, using a segmented feature relations map (SFRM) that reflects the relations between spectral features through a normalized difference index (NDI), and it can then learn new features from SFRM using a CNN-based feature extractor. Finally, based on these features, a classifier was designed for the classification. With FRML, our experimental results from four popular hyperspectral datasets indicate that the proposed method can achieve more representative and objective features to improve classification accuracy, outperforming classifications using the comparative methods.

scholarly journals Multi-scale guided feature extraction and classification algorithm for hyperspectral images

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Shiqi Huang ◽  
Ying Lu ◽  
Wenqing Wang ◽  
Ke Sun
Keyword(s):  
Feature Extraction ◽  
Image Classification ◽  
Classification Accuracy ◽  
Hyperspectral Image ◽  
Image Data ◽  
Hyperspectral Images ◽  
Hyperspectral Image Classification ◽  
Multi Scale ◽  
Hyperspectral Image Data ◽  
Guided Filtering

AbstractTo solve the problem that the traditional hyperspectral image classification method cannot effectively distinguish the boundary of objects with a single scale feature, which leads to low classification accuracy, this paper introduces the idea of guided filtering into hyperspectral image classification, and then proposes a multi-scale guided feature extraction and classification (MGFEC) algorithm for hyperspectral images. Firstly, the principal component analysis theory is used to reduce the dimension of hyperspectral image data. Then, guided filtering algorithm is used to achieve multi-scale spatial structure extraction of hyperspectral image by setting different sizes of filtering windows, so as to retain more edge details. Finally, the extracted multi-scale features are input into the support vector machine classifier for classification. Several practical hyperspectral image datasets were used to verify the experiment, and compared with other spectral feature extraction algorithms. The experimental results show that the multi-scale features extracted by the MGFEC algorithm proposed in this paper are more accurate than those extracted by only using spectral information, which leads to the improvement of the final classification accuracy. This fully shows that the proposed method is not only effective, but also suitable for processing different hyperspectral image data.

scholarly journals Hyperspectral Image Classification Based on Spectral and Spatial Information Using Multi-Scale ResNet

2019 ◽  
Vol 9 (22) ◽  
pp. 4890 ◽  
Author(s):  
Zong-Yue Wang ◽  
Qi-Ming Xia ◽  
Jing-Wen Yan ◽  
Shu-Qi Xuan ◽  
Jin-He Su ◽  
...  
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Classification Accuracy ◽  
Spatial Information ◽  
Hyperspectral Image ◽  
Computational Cost ◽  
Data Cube ◽  
Hyperspectral Image Classification ◽  
Fixed Size ◽  
Multi Scale

Hyperspectral imaging (HSI) contains abundant spectrums as well as spatial information, providing a great basis for classification in the field of remote sensing. In this paper, to make full use of HSI information, we combined spectral and spatial information into a two-dimension image in a particular order by extracting a data cube and unfolding it. Prior to the step of combining, principle component analysis (PCA) is utilized to decrease the dimensions of HSI so as to reduce computational cost. Moreover, the classification block used during the experiment is a convolutional neural network (CNN). Instead of using traditionally fixed-size kernels in CNN, we leverage a multi-scale kernel in the first convolutional layer so that it can scale to the receptive field. To attain higher classification accuracy with deeper layers, residual blocks are also applied to the network. Extensive experiments on the datasets from Pavia University and Salinas demonstrate that the proposed method significantly improves the accuracy in HSI classification.

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.

HSI-GCN: hyperspectral image classification algorithm based on Gabor convolutional networks

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Houari Youcef Moudjib ◽  
Duan Haibin ◽  
Baochang Zhang ◽  
Mohammed Salah Ahmed Ghaleb
Keyword(s):  
Image Classification ◽  
Classification Accuracy ◽  
Hyperspectral Image ◽  
Feature Learning ◽  
Hyperspectral Data ◽  
Spectral Features ◽  
Hyperspectral Image Classification ◽  
Content Type ◽  
Convolutional Networks ◽  
The Rich

Purpose Hyperspectral imaging (HSI) systems are becoming potent technologies for computer vision tasks due to the rich information they uncover, where each substance exhibits a distinct spectral distribution. Although the high spectral dimensionality of the data empowers feature learning, the joint spatial–spectral features have not been well explored yet. Gabor convolutional networks (GCNs) incorporate Gabor filters into a deep convolutional neural network (CNN) to extract discriminative features of different orientations and frequencies. To the best if the authors’ knowledge, this paper introduces the exploitation of GCNs for hyperspectral image classification (HSI-GCN) for the first time. HSI-GCN is able to extract deep joint spatial–spectral features more rapidly and accurately despite the shortage of training samples. The authors thoroughly evaluate the effectiveness of used method on different hyperspectral data sets, where promising results and high classification accuracy have been achieved compared to the previously proposed CNN-based and Gabor-based methods. Design/methodology/approach The authors have implemented the new algorithm of Gabor convolution network on the hyperspectral images for classification purposes. Findings Implementing the new GCN has shown unexpectable results with an excellent classification accuracy. Originality/value To the best of the authors’ knowledge, this work is the first one that implements this approach.

Sign in / Sign up

Export Citation Format

Share Document