15 February 2016 Impact factor analysis of mixture spectra unmixing based on independent component analysis
Author Affiliations +
Abstract
Based on spectral independence of different materials, independent component analysis (ICA), a blind source separation technique, can be applied to separate mixed hyperspectral signals. For the purpose of detecting objects on the sea and improving the precision of target recognition, an original ICA method is applied by analyzing the influence exerted by spectral features of different materials and mixture materials on spectral unmixing results. Due to the complexity of targets on the sea, several measured spectra of different materials have been mixed with water spectra to simulate mixed spectra for mixture spectra decomposition. Synthetic mixed spectra are generated by linear combinations of different materials and water spectra to obtain separated results. We then compared the separated results with the measured spectra of each endmember by coefficient of determination. We conclude that these factors that will change the original spectral characteristics of Gaussian distribution have significant influence on the separated results and selecting a proper initial matrix, and processing spectral data with lower noise can help improve the ICA method for more accurate separated results from hyperspectral data.
© 2016 Society of Photo-Optical Instrumentation Engineers (SPIE)
Lei Chen, Shengbo Chen, Xulin Guo, Chao Zhou, "Impact factor analysis of mixture spectra unmixing based on independent component analysis," Journal of Applied Remote Sensing 10(1), 015012 (15 February 2016). https://doi.org/10.1117/1.JRS.10.015012 . Submission:
JOURNAL ARTICLE
14 PAGES


SHARE
Back to Top