A Superpixel-Based Relational Auto-Encoder for Feature Extraction of Hyperspectral Images

Liang, Miaomiao; Jiao, Licheng; Meng, Zhe

doi:10.3390/rs11202454

Cited by 16 publications

(6 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Autoencoder is one of the deep-architecture models; the features are extracted with unsupervised ways [5]. In Figure 17 the proposed model by [3] is shown. This model is called Multi-Scale Relational Collaborative Auto Encoder (MS-RCAE).…”

Section: Model-3: Auto Encodersmentioning

confidence: 99%

Deep Learning Applications for Hyperspectral Imaging: A Systematic Review

Özdemir¹,

Polat²

2020

JIEC

View full text Add to dashboard Cite

Since the acquisition of digital images, scientific studies on these images have been making significant progress. The sizes and quality of the images obtained have increased greatly from past to present. However, when the information contained in these images remains on the visible band (RGB band), the results that can be obtained are limited. For this reason, the need to acquire images with more broadband information has emerged. Hyperspectral Imaging (HSI) method has been developed to meet this need. A hyperspectral image consists of reflections in hundreds of different bands of the electromagnetic spectrum. Each object exhibits a unique reflection characteristic. Due to this characteristic, objects can be separated from each other using hyperspectral imaging. Hyperspectral cameras are used to obtain this image. The information it contains is much more than an RGB image, so deeper results can be achieved than the human eye can see. In this respect, it has great importance. Artificial intelligence technologies are used extensively in image processing as well as in many other fields. As a result, classification studies are carried out on hyperspectral images with machine learning methods. Machine learning methods can be considered as the most general terms of supervised machine learning, unsupervised machine learning, and reinforced machine learning. Supervised machine learning methods mainly: Support Vector Machines(SVM), k-Nearest Neighborhood(k-NN), Decision Trees, Random Forest, Linear Regression and Neural Networks(NN). Neural networks are also used as an unsupervised learning method. However, Deep Learning, a specialized method of artificial neural networks, is highly preferred due to its unique structure. Artificial intelligence methods have been widely used in recent years, especially for the classification of hyperspectral images containing complex information. Considering the studies, it is seen that especially deep learning is used intensively. At this point, studies have revealed different types of models. The number of models and their successes are increasing day by day.

show abstract

Section: Model-3: Auto Encodersmentioning

confidence: 99%

Deep Learning Applications for Hyperspectral Imaging: A Systematic Review

Özdemir¹,

Polat²

2020

JIEC

View full text Add to dashboard Cite

show abstract

“…Among them, the feature extraction function can effectively capture the underlying structure of highdimensional input data and describe it using low-dimensional features. Therefore, the new features can be used not only as features but also as a representation of the original high-dimensional data [5].…”

Section: Introductionmentioning

confidence: 99%

A multidimensional feature fusion method for unsupervised hyperspectral information extraction

Gao,

Wang,

et al. 2024

Fourth International Conference on Geology, Mapping, and Remote Sensing (ICGMRS 2023)

View full text Add to dashboard Cite

The unsupervised algorithm extracts hyperspectral image features, focusing on one aspect and often ignoring some other information. To guarantee the effective extraction of information before image analysis, an unsupervised feature extraction technique with hyperspectral imaging data based on multidimensional feature fusion is proposed. First, we use principal component analysis (PCA) to map the high-dimensional data to a simpler space and extract the spectral features based on the elimination of redundant relationships. Then, the multi-directional spatial feature extraction algorithm of Gabor texture and morphology is utilized to extract each primary component's spatial properties. Finally, the spectral features, morphological features, and Gabor texture features are fused together by the vector stacking fusion. In this paper, the HSI information is extracted unsupervised using the previous technique, and HSI classification experiments using support vector machines are carried out to validate the efficacy of the information. The experiments demonstrate that the proposed method improves the Kappa coefficient by at least 14% in the MUUFL dataset and by 30% in the Trento dataset compared with the traditional spectral feature extraction, which significantly improves the classification accuracy.

show abstract

“…The existing superpixel-based methods, such as SuperPCA [28], S 3 PCA [29], and S-RAE [32], extract features from each superpixel region individually. While these methods can provide feature extractors for each superpixel region, they often neglect the relationship between samples from different superpixel regions.…”

Section: Introductionmentioning

confidence: 99%

A Collaborative Superpixelwise Autoencoder for Unsupervised Dimension Reduction in Hyperspectral Images

Yao,

Zheng,

Feng

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

The dimension reduction (DR) technique plays an important role in hyperspectral image (HSI) processing. Among various DR methods, superpixel-based approaches offer flexibility in capturing spectral–spatial information and have shown great potential in HSI tasks. The superpixel-based methods divide the samples into groups and apply the DR technique to the small groups. Nevertheless, we find these methods would increase the intra-class disparity by neglecting the fact the samples from the same class may reside on different superpixels, resulting in performance decay. To address this problem, a novel unsupervised DR named the Collaborative superpixelwise Auto-Encoder (ColAE) is proposed in this paper. The ColAE begins by segmenting the HSI into different homogeneous regions using a superpixel-based method. Then, a set of Auto-Encoders (AEs) is applied to the samples within each superpixel. To reduce the intra-class disparity, a manifold loss is introduced to restrict the samples from the same class, even if located in different superpixels, to have similar representations in the code space. In this way, the compact and discriminative spectral–spatial feature is obtained. Experimental results on three HSI data sets demonstrate the promising performance of ColAE compared to existing state-of-the-art methods.

show abstract

A Superpixel-Based Relational Auto-Encoder for Feature Extraction of Hyperspectral Images

Cited by 16 publications

References 34 publications

Deep Learning Applications for Hyperspectral Imaging: A Systematic Review

Deep Learning Applications for Hyperspectral Imaging: A Systematic Review

A multidimensional feature fusion method for unsupervised hyperspectral information extraction

A Collaborative Superpixelwise Autoencoder for Unsupervised Dimension Reduction in Hyperspectral Images

Contact Info

Product

Resources

About