scholarly journals Classification Endmember Selection with Multi-Temporal Hyperspectral Data

2020 ◽  
Vol 12 (10) ◽  
pp. 1575
Author(s):  
Tingxuan Jiang ◽  
Harald van der Werff ◽  
Freek van der Meer
Keyword(s):  
Classification Accuracy ◽  
Infrared Imaging ◽  
Reference Data ◽  
Hyperspectral Image ◽  
Hyperspectral Data ◽  
Single Image ◽  
Hyperspectral Image Classification ◽  
Imaging Spectrometer ◽  
Spectral Angle Mapper ◽  
Multi Temporal

In hyperspectral image classification, so-called spectral endmembers are used as reference data. These endmembers are either extracted from an image or taken from another source. Research has shown that endmembers extracted from an image usually perform best when classifying a single image. However, it is unclear if this also holds when classifying multi-temporal hyperspectral datasets. In this paper, we use spectral angle mapper, which is a frequently used classifier for hyperspectral datasets to classify multi-temporal airborne visible/infrared imaging spectrometer (AVIRIS) hyperspectral imagery. Three classifications are done on each of the images with endmembers being extracted from the corresponding image, and three more classifications are done on the three images while using averaged endmembers. We apply image-to-image registration and change detection to analyze the consistency of the classification results. We show that the consistency of classification accuracy using the averaged endmembers (around 65%) outperforms the classification results generated using endmembers that are extracted from each image separately (around 40%). We conclude that, for multi-temporal datasets, it is better to have an endmember collection that is not directly from the image, but is processed to a representative average.

scholarly journals COUPLE GRAPH BASED LABEL PROPAGATION METHOD FOR HYPERSPECTRAL REMOTE SENSING DATA CLASSIFICATION

2018 ◽  
Vol XLII-3 ◽  
pp. 1795-1798
Author(s):  
X. P. Wang ◽  
Y. Hu ◽  
J. Chen
Keyword(s):  
Manifold Learning ◽  
Classification Accuracy ◽  
Supervised Classification ◽  
Hyperspectral Image ◽  
Remote Sensing Data ◽  
Graph Laplacian ◽  
Hyperspectral Data ◽  
Label Propagation ◽  
Hyperspectral Image Classification ◽  
Adjacency Graph

Graph based semi-supervised classification method are widely used for hyperspectral image classification. We present a couple graph based label propagation method, which contains both the adjacency graph and the similar graph. We propose to construct the similar graph by using the similar probability, which utilize the label similarity among examples probably. The adjacency graph was utilized by a common manifold learning method, which has effective improve the classification accuracy of hyperspectral data. The experiments indicate that the couple graph Laplacian which unite both the adjacency graph and the similar graph, produce superior classification results than other manifold Learning based graph Laplacian and Sparse representation based graph Laplacian in label propagation framework.

scholarly journals Hyperspectral image classification incorporating bacterial foraging-optimized spectral weighting

2012 ◽  
Vol 1 (1) ◽  
pp. 63 ◽  
Author(s):  
Ankush Chakrabarty ◽  
Olivia Choudhury ◽  
Pallab Sarkar ◽  
Avishek Paul ◽  
Debarghya Sarkar
Keyword(s):  
Image Classification ◽  
Hyperspectral Image ◽  
Kernel Functions ◽  
Hyperspectral Data ◽  
Superior Performance ◽  
Support Vector ◽  
Hyperspectral Image Classification ◽  
Bacterial Foraging Optimization ◽  
Imaging Spectrometer ◽  
Bacterial Foraging

The present paper describes the development of a hyperspectral image classification scheme using support vector machines (SVM) with spectrally weighted kernels. The kernels are designed during the training phase of the SVM using optimal spectral weights estimated using the Bacterial Foraging Optimization (BFO) algorithm, a popular modern stochastic optimization algorithm. The optimized kernel functions are then in the SVM paradigm for bi-classification of pixels in hyperspectral images. The effectiveness of the proposed approach is demonstrated by implementing it on three widely used benchmark hyperspectral data sets, two of which were taken over agricultural sites at Indian Pines, Indiana, and Salinas Valley, California, by the Airborne Visible Infra-Red Imaging Spectrometer (AVIRIS) at NASA’s Jet Propulsion Laboratory. The third dataset was acquired using the Reflective Optical System Imaging Spectrometer (ROSIS) over an urban scene at Pavia University, Italy to demonstrate the efficacy of the proposed approach in an urban scenario as well as with agricultural data. Classification errors for One-Against-One (OAO) and classification accuracies for One-Against-All (OAA) schemes were computed and compared to other methods developed in recent times. Finally, the use of the BFO-based technique is recommended owing to its superior performance, in comparison to other contemporary stochastic bio-inspired algorithms.

scholarly journals NON-LINEAR AUTOENCODER BASED ALGORITHM FOR DIMENSIONALITY REDUCTION OF AIRBORNE HYPERSPECTRAL DATA

2019 ◽  
Vol XLII-3/W6 ◽  
pp. 593-598
Author(s):  
S. Priya ◽  
R. Ghosh ◽  
B. K. Bhattacharya
Keyword(s):  
Remote Sensing ◽  
Dimensionality Reduction ◽  
Infrared Imaging ◽  
Hyperspectral Image ◽  
Signal To Noise Ratio ◽  
Hyperspectral Data ◽  
Correlation Technique ◽  
Spectral Correlation ◽  
Spectral Angle Mapper ◽  
Non Linear

<p><strong>Abstract.</strong> Hyperspectral remote sensing is an advanced remote sensing technology that enhances the ability of accurate classification due to presence of narrow contiguous bands. The large number of continuous bands present in hyperspectral data introduces the problem of computational complexity due to presence of redundant information. There is a need for dimensionality reduction to enhance the ability of users for better characterization of features. Due to presence of high spectral correlation in the hyperspectral datasets, optimum de-correlation technique is required which transforms the hyperspectral data to lower dimensions without compromising with the desirable information present in the data. In this paper, focus has been to reduce the spectral dimensionality problem. So, this research aimed to develop computationally efficient non-linear autoencoder algorithm taking the advantage of non-linear properties of hyperspectral data. The proposed algorithm was applied on airborne hyperspectral image of Airborne Visible Infrared Imaging Spectrometer - Next Generation (AVIRIS-NG) over Anand region of Gujarat and the performance of the algorithm was evaluated. The Signal-to-Noise Ratio (SNR) increased from 22.78 dB to 48.48 dB with increase in number of nodes in bottleneck layer for reconstruction of image. Spectral distortion was also measured using Spectral Angle Mapper Algorithm (SAM), which reduced from 0.38 to 0.05 with increase in number of nodes in bottleneck layer up to 10. So, this algorithm was able to give good reconstruction of original image from the nodes present in the bottleneck layer.</p>

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.

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).

scholarly journals Deep Spectral Spatial Inverted Residual Network for Hyperspectral Image Classification

2021 ◽  
Vol 13 (21) ◽  
pp. 4472
Author(s):  
Tianyu Zhang ◽  
Cuiping Shi ◽  
Diling Liao ◽  
Liguo Wang
Keyword(s):  
Image Classification ◽  
Data Augmentation ◽  
Hyperspectral Image ◽  
Classification Performance ◽  
Hyperspectral Data ◽  
Hyperspectral Images ◽  
Hyperspectral Image Classification ◽  
Feature Maps ◽  
Spatial Feature ◽  
Global Context

Convolutional neural networks (CNNs) have been widely used in hyperspectral image classification in recent years. The training of CNNs relies on a large amount of labeled sample data. However, the number of labeled samples of hyperspectral data is relatively small. Moreover, for hyperspectral images, fully extracting spectral and spatial feature information is the key to achieve high classification performance. To solve the above issues, a deep spectral spatial inverted residuals network (DSSIRNet) is proposed. In this network, a data block random erasing strategy is introduced to alleviate the problem of limited labeled samples by data augmentation of small spatial blocks. In addition, a deep inverted residuals (DIR) module for spectral spatial feature extraction is proposed, which locks the effective features of each layer while avoiding network degradation. Furthermore, a global 3D attention module is proposed, which can realize the fine extraction of spectral and spatial global context information under the condition of the same number of input and output feature maps. Experiments are carried out on four commonly used hyperspectral datasets. A large number of experimental results show that compared with some state-of-the-art classification methods, the proposed method can provide higher classification accuracy for hyperspectral images.

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.

Image Fusion in Hyperspectral Image Classification using Genetic Algorithm

2016 ◽  
Vol 2 (3) ◽  
pp. 703 ◽  
Author(s):  
B. Saichandana ◽  
K. Srinivas ◽  
R. KiranKumar
Keyword(s):  
Genetic Algorithm ◽  
Image Fusion ◽  
Image Classification ◽  
Empirical Mode Decomposition ◽  
Hyperspectral Image ◽  
Image Data ◽  
Hyperspectral Data ◽  
Hyperspectral Image Classification ◽  
Mode Decomposition ◽  
Fused Image

<p>Hyperspectral remote sensors collect image data for a large number of narrow, adjacent spectral bands. Every pixel in hyperspectral image involves a continuous spectrum that is used to classify the objects with great detail and precision. This paper presents hyperspectral image classification mechanism using genetic algorithm with empirical mode decomposition and image fusion used in preprocessing stage. 2-D Empirical mode decomposition method is used to remove any noisy components in each band of the hyperspectral data. After filtering, image fusion is performed on the hyperspectral bands to selectively merge the maximum possible features from the source images to form a single image. This fused image is classified using genetic algorithm. Different indices, such as K-means (KMI), Davies-Bouldin Index (DBI), and Xie-Beni Index (XBI) are used as objective functions. This method increases classification accuracy of hyperspectral image.</p>

scholarly journals A Sparse Representation-Based Sample Pseudo-Labeling Method for Hyperspectral Image Classification

2020 ◽  
Vol 12 (4) ◽  
pp. 664 ◽  
Author(s):  
Binge Cui ◽  
Jiandi Cui ◽  
Yan Lu ◽  
Nannan Guo ◽  
Maoguo Gong
Keyword(s):  
Sparse Representation ◽  
Image Classification ◽  
Information Entropy ◽  
Hyperspectral Image ◽  
Hyperspectral Data ◽  
Hyperspectral Images ◽  
Hyperspectral Image Classification ◽  
Training Set ◽  
Training Samples ◽  
Labeling Method

Hyperspectral image classification methods may not achieve good performance when a limited number of training samples are provided. However, labeling sufficient samples of hyperspectral images to achieve adequate training is quite expensive and difficult. In this paper, we propose a novel sample pseudo-labeling method based on sparse representation (SRSPL) for hyperspectral image classification, in which sparse representation is used to select the purest samples to extend the training set. The proposed method consists of the following three steps. First, intrinsic image decomposition is used to obtain the reflectance components of hyperspectral images. Second, hyperspectral pixels are sparsely represented using an overcomplete dictionary composed of all training samples. Finally, information entropy is defined for the vectorized sparse representation, and then the pixels with low information entropy are selected as pseudo-labeled samples to augment the training set. The quality of the generated pseudo-labeled samples is evaluated based on classification accuracy, i.e., overall accuracy, average accuracy, and Kappa coefficient. Experimental results on four real hyperspectral data sets demonstrate excellent classification performance using the new added pseudo-labeled samples, which indicates that the generated samples are of high confidence.

Sign in / Sign up

Export Citation Format

Share Document