Loading [MathJax]/extensions/TeX/upgreek.js
Multi-Feature-Based Decision Fusion Framework for Hyperspectral Imagery Classification | IEEE Conference Publication | IEEE Xplore

Multi-Feature-Based Decision Fusion Framework for Hyperspectral Imagery Classification

Publisher: IEEE

Abstract:

Classification of a hyperspectral image (HSI) is a very active topic in remote sensing, which has practical applications in many fields, In this paper, a multitask sparse...View more

Abstract:

Classification of a hyperspectral image (HSI) is a very active topic in remote sensing, which has practical applications in many fields, In this paper, a multitask sparse logistic regression method based on multi-feature and decision fusion approach (MTSLR-MPGF) is proposed for cross-scene hyperspectral image classification. Specifically, the Gabor Features with certain orientations and morphology feature are utilized and used for hyperspectral imagery classification. Next, we used feature fusion methods in order to produce an accurate thematic map based on the remote sensed hyperspectral image classification. The extensive experiments on two real hyperspectral data sets have demonstrated superior performance of the proposed MTSLR-MPGF approach over the state-of-the-art methods in terms of overall accuracy and average accuracy.
Date of Conference: 22-27 July 2018
Date Added to IEEE Xplore: 04 November 2018
ISBN Information:

ISSN Information:

Publisher: IEEE
Conference Location: Valencia, Spain

References

References is not available for this document.