Spectral–Spatial Hyperspectral Image Classification With Edge-Preserving Filtering

By Xudong Kang, Shutao Li, Jon Atli Benediktsson. IEEE Transactions on Geoscience and Remote Sensing, 2014

671 citations recorded by the source corpus.

Subfields: Atmospheric Science, Media Technology

View Paper: https://www.semanticscholar.org/paper/c8b50b0346851a94b5b06f8c790340420aba575b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atmospheric Science

In Media Technology

Citations in the corpus

Optimal Clustering Framework for Hyperspectral Band Selection (2018, neutral): “They are k-nearest neighborhood (KNN) [46], linear discriminant analysis (LDA) [47], support vector machine (SVM) [48], and edge-preserving filtering (EPF) [49].”
Deep Learning for Remote Sensing Data: A Technical Tutorial on the State of the Art (2016, background): “As indicated in many spectral–spatial classification studies, the use of the spatial feature can significantly improve the classification accuracy [81]–[83].”
Hyperspectral Anomaly Detection With Attribute and Edge-Preserving Filters (2017, methodology): “For example, in [27], edge-preserving filtering is applied for the postprocessing of classification results obtained by a support vector machine classifier, in which edge-preserving filtering is demonstrated to be an effective way in making full use of the local spatial information of hyperspectral ”
Spectral–Spatial Residual Network for Hyperspectral Image Classification: A 3-D Deep Learning Framework (2018, positive): “Many papers suggested that methods expanding input data with more spatial information can improve the classification performance [11], [12].”
Local Binary Patterns and Extreme Learning Machine for Hyperspectral Imagery Classification (2015, methodology): “In [14], an edge preserving filter was employed to smooth a probability map produced by SVM while taking neighborhood information into account.”
Hyperspectral Pansharpening: A Review (2015, methodology): “Its application to HS data can be found in [47], where the guided filter was applied to transfer the structures of the principal components of the HS image to the initial classification maps.”
Hyperspectral Image Classification With Deep Feature Fusion Network (2018, methodology): “In [25], edge-preserving filtering (EPF) is proposed as a postprocessing technique to optimize the probabilistic results of the SVM.”
HSI-BERT: Hyperspectral Image Classification Using the Bidirectional Encoder Representation From Transformers (2020, methodology): “In 2014, an edge-preserving filtering-based spectral-spatial classification framework is proposed, which improves the classification accuracy of SVM significantly with much fewer computer resources [19].”
Recent Advances on Spectral–Spatial Hyperspectral Image Classification: An Overview and New Guidelines (2018, methodology): “Especially, [65]–[67] wrapped edge sensitive factors to devise”
Deep Learning for Hyperspectral Image Classification: An Overview (2019, methodology): “Classification maps for the University of Pavia data set obtained by (a) SVM [8], (b) EMP [19], (c) JSR [25], (d) EPF [24], (e) 3-D-CNN [56], (f) CNN-PPF [61], (g) Gabor-CNN [79], (h) S-CNN [89], (i) 3-D-GAN [46], and (j) DFFN [87].”
PCA-Based Edge-Preserving Features for Hyperspectral Image Classification (2017, methodology): “preserving filters have been successfully used in hyperspectral remote sensing applications [32], [37]–[39].”