Hyperspectral Remote Sensing: Dimensional Reduction and End member Extraction
Muhammad Ahmad1, Sungyoung Lee2, Ihsan Ul Haq3, Qaisar Mushtaq4
1Muhammad Ahmad, Department of Electronics Engineering, Faculty of Engineering and Technology, International Islamic University, Islamabad, Pakistan.
2Sungyoung Lee, Department of Computer Engineering, Kyung Hee University (Global Campus), South Korea.
3Ihsan Ul Haq, Department of Electronics Engineering, Faculty of Engineering and Technology, International Islamic University (IIU), Islamabad, Pakistan.
4Qaisar Mushtaq, Department of Computer Science, National Textile University (NTU), Faisalabad, Pakistan
Manuscript received on April 15, 2012. | Revised Manuscript received on April 20, 2012. | Manuscript published on May 05, 2012. | PP: 170-175 | Volume-2 Issue-2, May 2012 . | Retrieval Number: B0539042212/2012©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: 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: In this work, we present an algorithm to overcome the computational complexity of hyperspectral (HS) image data to detect multiple targets/endmembers accurately and efficiently by reducing time and complexity. In order to overcome the computational complexity standard deviation and chi square distance metric methods are considered. The number of endmembers is estimated by unbiased iterative correlation method. Hyperspectral remote sensing is widely used in real time applications such as; Surveillance, Mineralogy, Physics and Agriculture.
Keywords: Hyperspectral data, chi square, correlation, unbiased, Mat lab