Spectral-Spatial Hyperspectral Image Classification Using Subspace-Based Support Vector Machines and Adaptive Markov Random Fields

Yu, Haoyang; Gao, Lianru; Li, Jun; Li, Shan Shan; Zhang, Bing; Benediktsson, Jón Atli

doi:10.3390/rs8040355

Cited by 73 publications

(48 citation statements)

References 40 publications

(37 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For illustrative purposes, the image scene in pseudocolor is shown in Figure 3a. The ground truth map available for the scene with 9 mutually-exclusive ground-truth classes is showed in Figure 3b [41].…”

Section: Data Used In the Experimentsmentioning

confidence: 99%

A Novel Tri-Training Technique for Semi-Supervised Classification of Hyperspectral Images Based on Diversity Measurement

Tan

Zhu

et al. 2016

Remote Sensing

View full text Add to dashboard Cite

This paper introduces a novel semi-supervised tri-training classification algorithm based on diversity measurement for hyperspectral imagery. In this algorithm, three measures of diversity, i.e., double-fault measure, disagreement metric and correlation coefficient, are applied to select the optimal classifier combination from different classifiers, e.g., support vector machine (SVM), multinomial logistic regression (MLR), extreme learning machine (ELM) and k-nearest neighbor (KNN). Then, unlabeled samples are selected using an active learning (AL) method, and consistent results of any other two classifiers combined with a spatial neighborhood information extraction strategy are employed to predict their labels. Moreover, a multi-scale homogeneity (MSH) method is utilized to refine the classification result with the highest accuracy in the classifier combination, generating the final classification result. Experiments on three real hyperspectral data indicate that the proposed approach can effectively improve classification performance.

show abstract

Section: Data Used In the Experimentsmentioning

confidence: 99%

A Novel Tri-Training Technique for Semi-Supervised Classification of Hyperspectral Images Based on Diversity Measurement

Tan

Zhu

et al. 2016

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Two different algorithms are presented here by taking the SVM algorithm, for example. First let us review the SVM algorithm [37,38] briefly. For a simple purpose, we first consider a binary classification problem.…”

Section: Implementation Of Diversity Criteria Within Slmentioning

confidence: 99%

Incorporating Diversity into Self-Learning for Synergetic Classification of Hyperspectral and Panchromatic Images

Lu¹,

Zhang²,

Li³

et al. 2016

Remote Sensing

View full text Add to dashboard Cite

Abstract:Derived from semi-supervised learning and active learning approaches, self-learning (SL) was recently developed for the synergetic classification of hyperspectral (HS) and panchromatic (PAN) images. Combining the image segmentation and active learning techniques, SL aims at selecting and labeling the informative unlabeled samples automatically, thereby improving the classification accuracy under the condition of small samples. This paper presents an improved synergetic classification scheme based on the concept of self-learning for HS and PAN images. The investigated scheme considers three basic rules, namely the identity rule, the uncertainty rule, and the diversity rule. By integrating the diversity of samples into the SL scheme, a more stable classifier is trained by using fewer samples. Experiments on three synthetic and real HS and PAN images reveal that the diversity criterion can avoid the problem of bias sampling, and has a certain advantage over the primary self-learning approach.

show abstract

“…To obtain the local spatial weight coefficients β i , Haoyang Yu [43] etc. used the noise-adjusted principal components (NAPC) transform to obtain the first principal component to calculate the β i ,…”

Section: Algorithm 1 Ta Assisted Esammentioning

confidence: 99%

Spectral and Spatial Cloud Detection Onboard for Hyperspectral Remote Sensing Image

Li¹,

Zheng²,

Han³

et al. 2017

Preprint

View full text Add to dashboard Cite

It is strongly desirable to accurately detect the clouds in hyperspectral images onboard before compression. However, conventional onboard cloud detection methods are not appropriate to all situation such as shadowed cloud or darken snow covered surfaces which are not identified properly in the NDSI test. In this paper, we propose a new spectral-spatial classification strategy to enhance the orbiting cloud screen performances obtained on hyperspectral images by integrating threshold assisted exponential spectral angle map (TESAM), adaptive Markov random fields (aMRFs) and dynamic stochastic resonance (DSR). First, TESAM is performed to classify the cloud pixels coarsely based on spectral information. Then aMRFs is performed to do optimal process by using spatial information, which improved the classification performance significantly. But some misclassification points still exist after aMRFs processing because of the noise of data in the onboard environment. DSR is used to eliminate misclassification points in binary labeling image after aMRFs. Taking level 0.5 data from hyperion as dataset, the average overall accuracy of the proposed algorithm is 96.28% after test. The method can provide an accurate cloud mask for the on-going EO-1 images and the similar satellites with the same spectral settings without manual intervention. The experiment indicate that the proposed method reveals better performance than the classical onboard cloud detection or current advanced hyperspectral classification methods.

show abstract

Spectral-Spatial Hyperspectral Image Classification Using Subspace-Based Support Vector Machines and Adaptive Markov Random Fields

Cited by 73 publications

References 40 publications

A Novel Tri-Training Technique for Semi-Supervised Classification of Hyperspectral Images Based on Diversity Measurement

A Novel Tri-Training Technique for Semi-Supervised Classification of Hyperspectral Images Based on Diversity Measurement

Incorporating Diversity into Self-Learning for Synergetic Classification of Hyperspectral and Panchromatic Images

Spectral and Spatial Cloud Detection Onboard for Hyperspectral Remote Sensing Image

Contact Info

Product

Resources

About