Hyperspectral Image Classification via Weighted Joint Nearest Neighbor and Sparse Representation

Tu, Bing; Huang, Siyuan; Fang, Leyuan; Zhang, Guoyun; Wang, Jinping; Zheng, Binxin

doi:10.1109/jstars.2018.2869376

Cited by 41 publications

(16 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…neighbor [5], support vector machine (SVM) [6], [7], multinomial logical regression [8], [9], extreme learning machine [10] and so on. Although those methods can make full use of spectral information, the final classification accuracy is unsatisfactory due to obvious intra-class differences and unobvious inter-class differences of hyperspectral data on the spectral domain.…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral Image Classification With Pre-Activation Residual Attention Network

et al. 2019

View full text Add to dashboard Cite

Recently, convolutional neural networks (CNNs) have been introduced for hyperspectral image (HSI) classification and shown considerable classification performance. However, the previous CNNs designed for spectral-spatial HSI classification lay stress on the learning for the spatial correlation of HSI data and neglect the channel responses of feature maps. Furthermore, the lack of training samples remains the major challenge for CNN-based HSI classification methods to achieve better performance. To address the aforementioned issues, this paper proposes a new end-to-end pre-activation residual attention network (PRAN) for HSI classification. The pre-activation mechanism and attention mechanism are introduced into the proposed network, and a pre-activation residual attention block (PRAB) is designed, which allows the proposed network to carry adaptively feature recalibration of channel responses and learn more robust spectral-spatial joint feature representations. The proposed PRAN is equipped with two PRABs and several convolutional layers with different kernel sizes, which enables the PRAN to extract high-level discriminative features. Experimental results on three benchmark HSI datasets reveal that the proposed method is provided with competitive performance over several state-of-the-art HSI classification methods, especially when the training set size is relatively small. INDEX TERMS Hyperspectral image classification, convolutional neural network, pre-activation mechanism, attention mechanism.

show abstract

Section: Introductionmentioning

confidence: 99%

Hyperspectral Image Classification With Pre-Activation Residual Attention Network

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Thus, various spatial-spectral feature extraction methods are developed to consider both spectral and contextual information [17]. The Gabor filter [18], wavelets [19], the extended morphological profile [15], Markov random field [20] and sparse representation [21] have been applied to the HSI classification. In [3], a 2-D extension to SSA method (denoted as 2D-SSA) is developed for effective spatial features extraction of HSI, in which each band image is decomposed into various components and reconstructed using trend and selected oscillation information.…”

Section: Introductionmentioning

confidence: 99%

Multiscale 2-D Singular Spectrum Analysis and Principal Component Analysis for Spatial–Spectral Noise-Robust Feature Extraction and Classification of Hyperspectral Images

Ren

Zhao

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

In hyperspectral images (HSI), most feature extraction and data classification methods rely on corrected dataset, in which the noisy and water absorption bands are removed. This can result in not only extra working burden but also information loss from removed bands. To tackle these issues, in this paper, we propose a novel spatial-spectral feature extraction framework, Multiscale 2D singular spectrum analysis (2D-SSA) with principal component analysis (2D-MSSP), for noise-robust feature extraction and data classification of HSI. First, multiscale 2D-SSA is applied to exploit the multiscale spatial features in each spectral band of HSI via extracting the varying trends within defined windows. Taking the extracted trend signals at each scale level as the input features, the principal component analysis (PCA) is employed to the spectral domain for dimensionality reduction and spatial-spectral feature extraction. The derived spatialspectral features in each scale are separately classified and then fused at decision-level for efficacy. As our 2D-MSSP method can extract features and simultaneously remove noise in both spatial and spectral domains, which ensures it to be noise-robust for classification of HSI, even the uncorrected dataset. Experiments on three publicly available datasets have fully validated the efficacy and robustness of the proposed approach, when benchmarked with ten state-of-the-art classifiers, including six spatial-spectral methods and four deep learning classifiers. In addition, both quantitative and qualitative assessment has validated the efficacy of our approach in noise-robust classification of HSI even with limited training samples, especially in classifying uncorrected data without filtering noisy bands.

show abstract

“…Based on the above considerations, we want to find a method which can both make good use of spectral and spatial information. To solve this problem, we propose the weighted joint k-nearest neighbor and Multitask Learning Sparse Representation method (WJNN-MTL-SR), which is able to combines the advantages of weighted joint k-nearest neighbor (WJNN) [26] and multitask learning sparse representation [27]. Multitask sparse representation utilizes interrelation between tasks, while WJNN weights domain pixels to make more reasonable use of spatial information.…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral Image Target Detection via Weighted Joint K-Nearest Neighbor and Multitask Learning Sparse Representation

Zhang

Wang

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Multitask sparse representation method improves the detection performance by constructing multiple associated sub-sparse representation tasks and jointly learning multiple sub-sparse representation tasks, and this method can make use of the spectral information. However, the using of spatial information needs to be improved. This paper designs a hyperspectral image target detection method which can both make use of spectral and spatial information, that is a weighted joint k-nearest neighbor and multitask learning sparse representation method (WJNN-MTL-SR) is proposed. This method mainly consists of the following steps:1) using multitask sparse representation to obtain the representation residuals. 2) weighted joint knearest neighbor is used into the joint region of test pixels to obtain the weighted joint Euclidean distance. 3) a decision function, combining the weighted joint Euclidean distance and residuals of the multitask sparse representation, is used to get target detection result. Experimental results demonstrate that the proposed method show better detection performance than state-of-the-art methods. INDEX TERMS K-nearest neighbor, sparse representation, multitask learning, hyperspectral image target detection.

show abstract

Hyperspectral Image Classification via Weighted Joint Nearest Neighbor and Sparse Representation

Cited by 41 publications

References 61 publications

Hyperspectral Image Classification With Pre-Activation Residual Attention Network

Hyperspectral Image Classification With Pre-Activation Residual Attention Network

Multiscale 2-D Singular Spectrum Analysis and Principal Component Analysis for Spatial–Spectral Noise-Robust Feature Extraction and Classification of Hyperspectral Images

Hyperspectral Image Target Detection via Weighted Joint K-Nearest Neighbor and Multitask Learning Sparse Representation

Contact Info

Product

Resources

About