METHOD FOR ESTIMATING THE NUMBER OF MIXED SPECTRAL ENDMEMBERS BASED ON FEATURE-ENHANCED SPATIAL SPECTRAL MATCHING ALGORITHM
Abstract
Based on the characteristics of space target components, this paper proposes a spectral in-degree distribution curve-matching algorithm. Simulation experiments showed the average accuracy of the proposed algorithm is improved in comparison with the Harsanyi–Farrand–Chang and HySime algorithms. The simulation experiments were performed for a case in which the number of mixed spectral bands was reasonably small. The results showed the number of endmembers could be estimated accurately when the number of endmembers was three to eight. The algorithm proposed in this paper is suitable for estimating the number of endmembers of a space target.
Keywords
intrinsic dimension,
in-degree value,
K-nearest neighbor,
spectral matching,
endmember number estimation
Supporting agencies: This work was supported by the National Natural Science Foundation of the P.R. China under Grant No. 61575015.
About the Authors
Qingbo Li
Beihang University
China
School of Instrumentation and Optoelectronic Engineering, Precision Opto-Mechatronics Technology Key Laboratory of Education Ministry, Haidian District
China
School of Instrumentation and Optoelectronic Engineering, Precision Opto-Mechatronics Technology Key Laboratory of Education Ministry, Haidian District
Qi Wang
Beihang University
China
School of Instrumentation and Optoelectronic Engineering, Precision Opto-Mechatronics Technology Key Laboratory of Education Ministry, Haidian District
China
School of Instrumentation and Optoelectronic Engineering, Precision Opto-Mechatronics Technology Key Laboratory of Education Ministry, Haidian District
Shaolin Shi
Beihang University
China
School of Instrumentation and Optoelectronic Engineering, Precision Opto-Mechatronics Technology Key Laboratory of Education Ministry, Haidian District
China
School of Instrumentation and Optoelectronic Engineering, Precision Opto-Mechatronics Technology Key Laboratory of Education Ministry, Haidian District
References
1. R. Heylen, P. Scheunders, IEEE J. Select. Top. Appl. Earth Observ. Rem. Sens ., 6 , N 2, 570–579 (2013).
2. E. Levina, P. J. Bickel, Int. Conf. Neural Inform. Proc. Systems , MIT Press, 777–784 (2004).
3. I. Chein Chang, IEEE J. Select. Top. Appl. Earth Observ. Remote Sens ., 11 , N 4, 1285–1305 (2018).
4. S. Devika, S. M. K. Chaitanya, IEEE Int. Conf. Res. Adv. Integrated Navigation Systems (2016).
5. J. M. Keller, M. R. Gray, J. A. Givens, IEEE Trans. Syst., Man. Cybern. , SMC-15(4), 580–585 (2012).
6. M. E. Newman, S. H. Strogatz, D. J. Watts, Phys. Rev. Statist. Nonlinear Soft Matter Phys., 64 , N 2, 026118 (2001).
7. O. Gaci, S. Balev, IEEE Int. Conf. Bioinform. Biomed. Workshop , 107–112 (2009).
8. A. Robin, K. Cawse-Nicholson, A. Mahmood, M. Sears, IEEE J. Select. Top. Appl. Earth Observ. Remote Sens ., 8 , N 6, 2854–2861 (2015).
9. Nelson Antunes, Shankar Bhamidi, Tianjian Guo, Vladas Pipiras, Bang Wang, Sampling-Based Estimation of In-degree Distribution with Applications to Directed Complex Networks , 40 , N 5, 501–505 (2018).
10. Wanjun Liu, Xiuhong Yang, Haicheng Qu, Yu Meng, J. Comput. Appl ., 35 , N 3, 844–848 (2015).
11. Q. Li, C. Niu, J. Appl. Remote Sens., 9 , N 1, 096008 (2015).
Review
For citations:
Li Q., Wang Q., Shi Sh. METHOD FOR ESTIMATING THE NUMBER OF MIXED SPECTRAL ENDMEMBERS BASED ON FEATURE-ENHANCED SPATIAL SPECTRAL MATCHING ALGORITHM. Zhurnal Prikladnoii Spektroskopii. 2020;87(2):350(1)-350(7).
Views: 312
Email this article 