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

Tan, Kun; Zhu, Jishuai; Du, Qian; Wu, Lei; Du, Peijun

doi:10.3390/rs8090749

Cited by 19 publications

(21 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared with supervised classification methods, the advantage of semi-unsupervised methods for HSIs can be summarized as follows. First, the supervised classification needs a great deal of labeled samples to improve the classifier performance [47]. However HSI classification often faces the issue of limited number of labeled data, which are often costly, effortful, and time-consuming [28].…”

Section: Discussionmentioning

confidence: 99%

Class Probability Propagation of Supervised Information Based on Sparse Subspace Clustering for Hyperspectral Images

et al. 2017

View full text Add to dashboard Cite

Hyperspectral image (HSI) clustering has drawn increasing attention due to its challenging work with respect to the curse of dimensionality. In this paper, we propose a novel class probability propagation of supervised information based on sparse subspace clustering (CPPSSC) algorithm for HSI clustering. Firstly, we estimate the class probability of unlabeled samples by way of partial known supervised information, which can be addressed by sparse representation-based classification (SRC). Then, we incorporate the class probability into the traditional sparse subspace clustering (SSC) model to obtain a more accurate sparse representation coefficient matrix accompanied by obvious block diagonalization, which will be used to build the similarity matrix. Finally, the cluster results can be obtained by applying the spectral clustering on similarity matrix. Extensive experiments on a variety of challenging data sets illustrate that our proposed method is effective.

show abstract

Section: Discussionmentioning

confidence: 99%

Class Probability Propagation of Supervised Information Based on Sparse Subspace Clustering for Hyperspectral Images

et al. 2017

View full text Add to dashboard Cite

show abstract

“…The spatial information based on the segmentation objects in each scale is then used to constrain the first candidate and construct the candidate set S u . Finally, the final additional unlabeled samples S are chosen from the candidate set S u with an AL method based on the breaking ties (BT) algorithm [50], for the training samples of the ensemble system in the next scale layer. The BT algorithm is used to measure the information of the samples by comparing the difference between the maximum probability and sub-probability of posterior probability of samples.…”

Section: Unlabeled Sample Selectionmentioning

confidence: 99%

Object-Based Change Detection Using Multiple Classifiers and Multi-Scale Uncertainty Analysis

et al. 2019

Self Cite

View full text Add to dashboard Cite

The drawback of pixel-based change detection is that it neglects the spatial correlation with neighboring pixels and has a high commission ratio. In contrast, object-based change detection (OBCD) depends on the accuracy of the segmentation scale, which is of great significance in image analysis. Accordingly, an object-based approach for automatic change detection using multiple classifiers and multi-scale uncertainty analysis (OB-MMUA) in high-resolution (HR) remote sensing images is proposed in this paper. In this algorithm, the gray-level co-occurrence matrix (GLCM), morphological, and Gabor filter texture features are extracted to construct the input data, along with the spectral features, to utilize the respective advantages of the features and to compensate for the insufficient spectral information. In addition, random forest is used to select the features and determine the optimal feature vectors for the change detection. Change vector analysis (CVA) based on uncertainty analysis is then implemented to select the initial training samples. According to the diversity, support vector machine (SVM), k-nearest neighbor (KNN), and extra-trees (ExT) classifiers are then chosen as the base classifiers for Dempster-Shafer (D-S) evidence theory fusion, and unlabeled samples are selected using an active learning method with spatial information. Finally, multi-scale object-based D-S evidence theory fusion and uncertainty analysis is used to classify the difference image. To validate the proposed approach, we conducted experiments using multispectral images collected by the ZY-3 and GF-2 satellites. The experimental results confirmed the effectiveness and superiority of the proposed approach, which integrates the respective advantages of the pixel-based and object-based methods.Remote Sens. 2019, 11, 359 2 of 17 fields, such as urban development [6], environmental monitoring, vegetation coverage studies [7], and land-use monitoring [8,9].Change detection can be divided into pixel-based and object-based change detection (OBCD). Many scholars have proposed a variety of pixel-based change detection methods, including change vector analysis (CVA) [10,11], Markov random field (MRF)-based change detection [12], etc. With the development of machine learning, methods such as the extreme learning machine (ELM) algorithm [13], support vector machine (SVM) [14], random forest (RF) [15], k-nearest neighbor (KNN) [16], the multi-layer perceptron neural network (MLPNN) [17], and convolutional neural network (CNN) [18,19] have improved the accuracy of classification and change detection. However, a single classifier cannot detect all the change information in an image effectively. To address this issue, ensemble learning has been applied to the research and application of change detection and classification [20][21][22]. [23] proposed an ensemble system based on multiple classifiers, and achieved good classification results. Zhang et al. (2017) [24] combined deep learning with feature change analysis for remote sensing image change d...

show abstract

“…In [47], the optimal classifier combination selected by the diversity measures was multinomial logistic regression (MLR), k-nearest neighbor (KNN), and extreme learning machine (ELM). In this study, the correlation coefficient, disagreement metric, and double-fault measure were implemented to select the optimal classifier combination.…”

Section: Cooperative Training Strategy Combining Local Featuresmentioning

confidence: 99%

A Novel Tri-Training Technique for the Semi-Supervised Classification of Hyperspectral Images Based on Regularized Local Discriminant Embedding Feature Extraction

Tan

et al. 2019

Remote Sensing

Self Cite

View full text Add to dashboard Cite

This paper introduces a novel semi-supervised tri-training classification algorithm based on regularized local discriminant embedding (RLDE) for hyperspectral imagery. In this algorithm, the RLDE method is used for optimal feature information extraction, to solve the problems of singular values and over-fitting, which are the main problems in the local discriminant embedding (LDE) and local Fisher discriminant analysis (LFDA) methods. An active learning method is then used to select the most useful and informative samples from the candidate set. In the experiments undertaken in this study, the three base classifiers were multinomial logistic regression (MLR), k-nearest neighbor (KNN), and random forest (RF). To confirm the effectiveness of the proposed RLDE method, experiments were conducted on two real hyperspectral datasets (Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) and Reflective Optics System Imaging Spectrometer (ROSIS)), and the proposed RLDE tri-training algorithm was compared with its counterparts of tri-training alone, LDE, and LFDA. The experiments confirmed that the proposed approach can effectively improve the classification accuracy for hyperspectral imagery.

show abstract

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

Cited by 19 publications

References 42 publications

Class Probability Propagation of Supervised Information Based on Sparse Subspace Clustering for Hyperspectral Images

Class Probability Propagation of Supervised Information Based on Sparse Subspace Clustering for Hyperspectral Images

Object-Based Change Detection Using Multiple Classifiers and Multi-Scale Uncertainty Analysis

A Novel Tri-Training Technique for the Semi-Supervised Classification of Hyperspectral Images Based on Regularized Local Discriminant Embedding Feature Extraction

Contact Info

Product

Resources

About