Super Resolution of Hyper Spectral Image Based on NABO Spectral Unmixing
Gayathri S A1, Renjith R J2
1Gayathri S A, Department of ECE, SCT College of Engineering, Pappanamcode, Thiruvananthapuram (Kerala), India.
2Renjith R J, Department of ECE, SCT College of Engineering, Pappanamcode, Thiruvananthapuram (Kerala), India.
Manuscript received on 13 June 2016 | Revised Manuscript received on 20 June 2016 | Manuscript Published on 30 June 2016 | PP: 82-86 | Volume-5 Issue-5, June 2016 | Retrieval Number: E4611065516/16©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Hyperspectral imaging has become an important image analysis technique in remote sensing. Processing and enhancing hyperspectral images are a difficult task. The spectral information contained in the hyperspectral images are extracted by spectral unmixing techniques. This paper proposes a novel method for enhancing spatial resolution of hyperspectral images based on spectral unmixing. Many applications needs images containing both high spectral resolution and high spatial resolution. In this paper a NABO (Negative Abundance Oriented) spectral unmixing based hyperspectral-multispectral image fusion algorithm is proposed for the purpose of enhancing the spatial resolution of hyperspectral image(HSI). As a result, a high-spatial-resolution HSI is reconstructed based on the high spectral characters of the HSI represented by endmember spectra and the high spatial characters of the multispectral image(MSI) represented by abundance fractions. Experiments were done on Airborne Visible/Infrared Imaging Spectrometer data. NABO unmixing based fusion gives better results than existing Endmember Extraction (EE).
Keywords: Hyperspectral Imaging, Linear Mixing Model, Spectral Unmixing, Multispectral Images, Endmember Extraction Algorithms, Resolution Enhancement.
Scope of the Article: Image Processing