Skip to Main content Skip to Navigation
Journal articles

Spectral-Spatial Classification of Hyperspectral Images Using ICA and Edge-Preserving Filter via an Ensemble Strategy

Abstract : In order to obtain accurate classification results of hyperspectral images, both the spectral and spatial information should be fully exploited in the classification process. In this paper, we propose a novel method using independent component analysis (ICA) and edge-preserving filtering (EPF) via an ensemble strategy for the classification of hyperspectral data. First, several subsets are randomly selected from the original feature space. Second, ICA is used to extract spectrally independent components followed by an effective EPF method, to produce spatial features. Two strategies (i.e., parallel and concatenated) are presented to include the spatial features in the analysis. The spectral-spatial features are then classified with a random forest (RF) or rotation forest (RoF) classifier. Experimental results on two real hyperspectral datasets demonstrate the effectiveness of the proposed methods. A sensitivity analysis of the new classifiers is also performed.
Document type :
Journal articles
Complete list of metadata

Cited literature [44 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01379723
Contributor : Lionel Bombrun Connect in order to contact the contributor
Submitted on : Wednesday, October 12, 2016 - 8:31:35 AM
Last modification on : Tuesday, December 8, 2020 - 9:55:10 AM
Long-term archiving on: : Saturday, February 4, 2017 - 7:44:02 PM

File

Xia16_TGRS.pdf
Files produced by the author(s)

Identifiers

Citation

Junshi Xia, Lionel Bombrun, Tülay Adalı, Yannick Berthoumieu, Christian Germain. Spectral-Spatial Classification of Hyperspectral Images Using ICA and Edge-Preserving Filter via an Ensemble Strategy. IEEE Transactions on Geoscience and Remote Sensing, Institute of Electrical and Electronics Engineers, 2016, 54 (8), pp.4971 - 4982. ⟨10.1109/TGRS.2016.2553842⟩. ⟨hal-01379723⟩

Share

Metrics

Record views

259

Files downloads

1188