Hyperspectral Image Classification Based on Fusion of Curvature Filter and Domain Transform Recursive Filter

Liao, Jianshang; Wang, Liguo

doi:10.3390/rs11070833

Cited by 6 publications

(1 citation statement)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Guo et al [55] applied guided filtering (GF) to the KNN classifier, while Wang et al [56] combined GF, principle component analysis (PCA) and deep neural networks to extract discriminative multi-features from HSI scenes. In [57], Liao and Wang fused two spatial-based filters, in particular curvature (CF) and domain transform recursive (DTRF) filtering to enhance the performance of HSI classification, and in [58] they implemented an adaptive manifold filter with spatial correlation feature (AMSCF) approach.…”

Section: A Traditional Machine Learning Methods For Spectral-spatialmentioning

confidence: 99%

Rotation Equivariant Convolutional Neural Networks for Hyperspectral Image Classification

et al. 2020

View full text Add to dashboard Cite

Detection of surface material based on hyperspectral imaging (HSI) analysis is an important and challenging task in remote sensing. It is widely known that spectral-spatial data exploitation performs better than traditional spectral pixel-wise procedures. Nowadays, convolutional neural networks (CNNs) have shown to be a powerful deep learning (DL) technique due their strong feature extraction ability. CNNs not only combine spectral-spatial information in a natural way, but have also shown to be able to learn translation-equivariant representations, i.e. a translation of input features into an equivalent internal CNN feature map. This provides great robustness to spatial feature locations. However, as far as we know, CNNs do not exhibit a natural way to exploit rotation equivariance, i.e. make use of the fact that data patches in a HSI data cube are observed in different orientations due to their orientation or on the varying paths/orbits of the airborne/spaceborne spectrometers. This paper presents a rotation-equivariant CNN2D model for HSI analysis, where traditional convolution kernels have been replaced by circular harmonic filters (CHFs). The obtained results over three well-known HSI datasets showcase the potential of the approach. INDEX TERMS Hyperspectral imaging (HSI), convolutional neural network (CNN), harmonic network (H-net), rotation invariance

show abstract

Section: A Traditional Machine Learning Methods For Spectral-spatialmentioning

confidence: 99%

Rotation Equivariant Convolutional Neural Networks for Hyperspectral Image Classification

et al. 2020

View full text Add to dashboard Cite

show abstract

Multiple Spatial Features Extraction and Fusion for Hyperspectral Images Classification

Liao

Wang

2020

Canadian Journal of Remote Sensing

View full text Add to dashboard Cite

Adaptive Hyperspectral Image Classification Based on the Fusion of Manifolds Filter and Spatial Correlation Features

Liao

Wang

2020

IEEE Access

View full text Add to dashboard Cite

In recent decades, the studies that obtain abundant spatial texture features, using a wide variety of filters for improving the performance of hyperspectral image (HSI) classification, have become a hotspot. However, the classification methods based on various filters are easy to fall into local feature extraction and neglect informative spatial correlation features. This paper presents an adaptive HSI classification method based on the fusion of adaptive manifold filter and spatial correlation feature (AMSCF). In which we use an adaptive manifold filter to extract spatial texture features, and use the domain transform normalized convolution filter and interpolated convolution filter to obtain the spatial correlation features. Besides, the spatial texture features and two correlation features are separately fused and classified by Large Margin Distribution Machine (LDM) to obtain the best classification. The experimental results demonstrate that the proposed AMSCF method is better than the other classification methods. INDEX TERMS Hyperspectral image, large margin distribution machine, adaptive manifold filter, domain transform convolution filter, classification.

show abstract

Hyperspectral Image Classification Based on Fusion of Curvature Filter and Domain Transform Recursive Filter

Cited by 6 publications

References 52 publications

Rotation Equivariant Convolutional Neural Networks for Hyperspectral Image Classification

Rotation Equivariant Convolutional Neural Networks for Hyperspectral Image Classification

Multiple Spatial Features Extraction and Fusion for Hyperspectral Images Classification

Adaptive Hyperspectral Image Classification Based on the Fusion of Manifolds Filter and Spatial Correlation Features

Contact Info

Product

Resources

About