Hyperspectral remote sensing image classification based on tighter random projection with minimal intra-class variance algorithm

Zhao, Quanhua; Jia, Shuhan; Li, Yu

doi:10.1016/j.patcog.2020.107635

Cited by 24 publications

(8 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We can conclude that the SVM-RBF and SVM-Linear obtains good generalization performance on anonymous data and is more suitable for practical use than traditional parametric classifiers. However, there is a need for further research with respect to the implementation of the SVM-RBF and SVM-Linear on RS image classification [ 7 , 18 ]. Firstly, the probabilities of SVM-RBF and SVM-Linear are much higher than MLC and MDC, especially in the cross validation for the parameter optimization of

and C. As a future study, the parameter optimization may be accomplished in other more efficient ways.…”

Section: Resultsmentioning

confidence: 99%

“…In the area of sustainable development, image classification in RS can be used to assess changes in different ecosystems—namely, to monitor global climate change, to assess natural disasters, to track forest fires, to determine air pollution and to observe air quality [ 6 ]. Compared with field investigation, RS technology is much more efficient and cheaper in terms of time and cost [ 7 ]. RS image classification is a significant part of the overall field of RS, which can be thought of as a joint venture between both image processing and classification techniques [ 8 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improved Support Vector Machine Enabled Radial Basis Function and Linear Variants for Remote Sensing Image Classification

Razaque

Frej

Almiani

et al. 2021

Sensors

View full text Add to dashboard Cite

Remote sensing technologies have been widely used in the contexts of land cover and land use. The image classification algorithms used in remote sensing are of paramount importance since the reliability of the result from remote sensing depends heavily on the classification accuracy. Parametric classifiers based on traditional statistics have successfully been used in remote sensing classification, but the accuracy is greatly impacted and rather constrained by the statistical distribution of the sensing data. To eliminate those constraints, new variants of support vector machine (SVM) are introduced. In this paper, we propose and implement land use classification based on improved SVM-enabled radial basis function (RBF) and SVM-Linear for image sensing. The proposed variants are applied for the cross-validation to determine how the optimization of parameters can affect the accuracy. The accuracy assessment includes both training and test sets, addressing the problems of overfitting and underfitting. Furthermore, it is not trivial to determine the generalization problem merely based on a training dataset. Thus, the improved SVM-RBF and SVM-Linear also demonstrate the outstanding generalization performance. The proposed SVM-RBF and SVM-Linear variants have been compared with the traditional algorithms (Maximum Likelihood Classifier (MLC) and Minimum Distance Classifier (MDC)), which are highly compatible with remote sensing images. Furthermore, the MLC and MDC are mathematically modeled and characterized with new features. Also, we compared the proposed improved SVM-RBF and SVM-Linear with the current state-of-the-art algorithms. Based on the results, it is confirmed that proposed variants have higher overall accuracy, reliability, and fault-tolerance than traditional as well as latest state-of-the-art algorithms.

show abstract

and C. As a future study, the parameter optimization may be accomplished in other more efficient ways.…”

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Improved Support Vector Machine Enabled Radial Basis Function and Linear Variants for Remote Sensing Image Classification

Razaque

Frej

Almiani

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Due to the large number of hyperspectral bands and strong correlation between bands, the increase of feature dimension may cause the performance of the classifier to deteriorate when the feature dimension reaches to a certain critical point. This is the so-called Hughes phenomenon, occurring in traditional machine learning classification methods that rely on spectral features and sample size [38,39]. Additionally, the variance of the spectra within the same class is usually large for hyperspectral images, leading a poor separability of hyperspectral features [39][40][41].…”

Section: Introductionmentioning

confidence: 99%

“…This is the so-called Hughes phenomenon, occurring in traditional machine learning classification methods that rely on spectral features and sample size [38,39]. Additionally, the variance of the spectra within the same class is usually large for hyperspectral images, leading a poor separability of hyperspectral features [39][40][41]. These problems might greatly affect the accuracy of forest stand classification [42][43][44], and the classification result is not robust to noise when using hyperspectral images [36].…”

Section: Introductionmentioning

confidence: 99%

Tree Species Classification of Forest Stands Using Multisource Remote Sensing Data

et al. 2021

View full text Add to dashboard Cite

The spatial distribution of forest stands is one of the fundamental properties of forests. Timely and accurately obtained stand distribution can help people better understand, manage, and utilize forests. The development of remote sensing technology has made it possible to map the distribution of tree species in a timely and accurate manner. At present, a large amount of remote sensing data have been accumulated, including high-spatial-resolution images, time-series images, light detection and ranging (LiDAR) data, etc. However, these data have not been fully utilized. To accurately identify the tree species of forest stands, various and complementary data need to be synthesized for classification. A curve matching based method called the fusion of spectral image and point data (FSP) algorithm was developed to fuse high-spatial-resolution images, time-series images, and LiDAR data for forest stand classification. In this method, the multispectral Sentinel-2 image and high-spatial-resolution aerial images were first fused. Then, the fused images were segmented to derive forest stands, which are the basic unit for classification. To extract features from forest stands, the gray histogram of each band was extracted from the aerial images. The average reflectance in each stand was calculated and stacked for the time-series images. The profile curve of forest structure was generated from the LiDAR data. Finally, the features of forest stands were compared with training samples using curve matching methods to derive the tree species. The developed method was tested in a forest farm to classify 11 tree species. The average accuracy of the FSP method for ten performances was between 0.900 and 0.913, and the maximum accuracy was 0.945. The experiments demonstrate that the FSP method is more accurate and stable than traditional machine learning classification methods.

show abstract

“…Compared with traditional panchromatic and multispectral remote sensing images, hyperspectral imagery carry a wealth of spectral information, which enables more accurate discrimination of different objects. Consequently, in recent years, hyperspectral imagery has gained extensive attention for a variety of applications in Earth observations [1,[6][7][8][9][10], such as urban mapping, precision agriculture, and environmental monitoring [11][12][13][14][15]. The hyperspectral image classification is a significant research topic and it centers on assigning class labels to pixels.…”

Section: Introductionmentioning

confidence: 99%

SMOTE-Based Weighted Deep Rotation Forest for the Imbalanced Hyperspectral Data Classification

et al. 2021

View full text Add to dashboard Cite

Conventional classification algorithms have shown great success in balanced hyperspectral data classification. However, the imbalanced class distribution is a fundamental problem of hyperspectral data, and it is regarded as one of the great challenges in classification tasks. To solve this problem, a non-ANN based deep learning, namely SMOTE-Based Weighted Deep Rotation Forest (SMOTE-WDRoF) is proposed in this paper. First, the neighboring pixels of instances are introduced as the spatial information and balanced datasets are created by using the SMOTE algorithm. Second, these datasets are fed into the WDRoF model that consists of the rotation forest and the multi-level cascaded random forests. Specifically, the rotation forest is used to generate rotation feature vectors, which are input into the subsequent cascade forest. Furthermore, the output probability of each level and the original data are stacked as the dataset of the next level. And the sample weights are automatically adjusted according to the dynamic weight function constructed by the classification results of each level. Compared with the traditional deep learning approaches, the proposed method consumes much less training time. The experimental results on four public hyperspectral data demonstrate that the proposed method can get better performance than support vector machine, random forest, rotation forest, SMOTE combined rotation forest, convolutional neural network, and rotation-based deep forest in multiclass imbalance learning.

show abstract

Hyperspectral remote sensing image classification based on tighter random projection with minimal intra-class variance algorithm

Cited by 24 publications

References 23 publications

Improved Support Vector Machine Enabled Radial Basis Function and Linear Variants for Remote Sensing Image Classification

Improved Support Vector Machine Enabled Radial Basis Function and Linear Variants for Remote Sensing Image Classification

Tree Species Classification of Forest Stands Using Multisource Remote Sensing Data

SMOTE-Based Weighted Deep Rotation Forest for the Imbalanced Hyperspectral Data Classification

Contact Info

Product

Resources

About