Unmixing method for hyperspectral data based on sub-space method with learning process

• Published in: Advances in space research Vol. 44; no. 4; pp. 517 - 523
• Main Authors: Arai, Kohei, Chen, Huahui
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 17.08.2009; Elsevier
• Subjects: Astronomy; AVIRIS; Category decomposition; Earth, ocean, space; Exact sciences and technology; External geophysics; Hyperspectral data; Learning process; Sub-space method; Unmixing; Learning process; AVIRIS; Hyperspectral data; Sub-space method; Category decomposition; Unmixing; Spectral band; Space remote sensing; Observation data; Satellite observation; Space research
• ISSN: 0273-1177; 1879-1948
• DOI: 10.1016/j.asr.2009.04.034

An unmixing method for hyperspectral Earth observation satellite imagery data is proposed. It is based on a sub-space method with learning process. The proposed method utilizes a sub-space for feature space during unmixing. It is used to be done in a feature space which consists of spectral bands of observation vectors. As the results from the experiments with airborne based hyperspectral imagery data, AVIRIS, it is found that the proposed unmixing is superior to the other existing method in terms of decomposition accuracy and the process time required for the decompositions.