Noise estimation algorithm based on relevance vector machine for hyperspectral imagery

Wang Xiaofei; Hou Chuanlong; Yan Qiujing; Zhang Junping; Wang Aihua

In order to more accurately estimate noise intensity for hyperspectral imagery, the paper proposed a noise estimation algorithm based on relevance vector machine(RVM)for hyperspectral imagery. And the algorithm that used RVM regression, residuals and noise was studied. First of all, this paper introduced the characteristics and shortage of spatial/spectral dimension decorrelation in noise estimation that used widely nowadays for hyperspectral imagery. Then, the nonlinear regression analysis of RVM was introduced. And the residuals will be too large, when there was a strong nonlinear correlation in the system for spatial/spectral dimension decorrelation. To this problem, the paper proposed a new method that used RVM regression to remove strong signal correlation and used the residual images to estimate the noise, so as to improve the stability of the assessment system. Experimental results indicate that the precision of the noise intensity is better than 8%, and show that the method is more effective compared to the traditional method. It concludes that the RVM can satisfy the system requirements of higher precision and stabilization in noise estimation for automatic hyperspectral imagery.

1. Beijing Twenty-First Century Science& Technology Development Co. Ltd,Beijing 100096,China;

2. Key Laboratory of Electronic Enginerring,College of Heilongjiang Province,Heilongjiang University,Harbin 150080,China;

3. Department of Information Engineering,Harbin Institute of Technology,Harbin 150001,China;

4. Twenty First Century Aerospace Technology Co. Ltd,Beijing 100096,China

Received Date: 2014-04-10

Rev Recd Date: 2014-05-15

Publish Date: 2014-12-25

Key words:

Abstract: In order to more accurately estimate noise intensity for hyperspectral imagery, the paper proposed a noise estimation algorithm based on relevance vector machine(RVM)for hyperspectral imagery. And the algorithm that used RVM regression, residuals and noise was studied. First of all, this paper introduced the characteristics and shortage of spatial/spectral dimension decorrelation in noise estimation that used widely nowadays for hyperspectral imagery. Then, the nonlinear regression analysis of RVM was introduced. And the residuals will be too large, when there was a strong nonlinear correlation in the system for spatial/spectral dimension decorrelation. To this problem, the paper proposed a new method that used RVM regression to remove strong signal correlation and used the residual images to estimate the noise, so as to improve the stability of the assessment system. Experimental results indicate that the precision of the noise intensity is better than 8%, and show that the method is more effective compared to the traditional method. It concludes that the RVM can satisfy the system requirements of higher precision and stabilization in noise estimation for automatic hyperspectral imagery.

HTML

Reference (19)

[1]
[2]	Liu Danfeng, Wang Liguo. Color display of hyperspectral data in three levels [J]. Infrared and Laser Engineering, 2012, 41(9): 2527-2533. (in Chinese) 刘丹凤, 王立国. 高光谱数据三级彩色显示方法[J]. 红外与激光工程, 2012, 41(9): 2527-2533.
[3]
[4]	Cheng Xin, Zhang Bao, Hong Yongfeng, et al. Optical design of an airborne dual-wavelength imaging spectrometer with high throughput [J]. Infrared and Laser Engineering, 2012, 41(3): 690-695. (in Chinese) 程欣, 张葆, 洪永丰, 等. 机载高光通量双波段成像光谱仪的设计[J]. 红外与激光工程, 2012, 41(3): 690-695.
[5]	Zhang Bing, Gao Lianru. Hyperspectral Image Classification and Target Detection [M]. Beijing: Science Press, 2011. (in Chinese) 张兵, 高连如. 高光谱图像分类与目标探测[M]. 北京院科学出版社, 2011.
[6]
[7]
[8]	Curran P J, Dungan J L. Estimation of signal-to-noise:a new procedure applied to AVIRIS data [J]. IEEE Transactions on Geoscience and Remote Sensing, 1989, 27 (5): 620-628.
[9]	Gao B C. An operational method for estimating signal to noise ratios from data acquired with imaging spectrometers[J]. Remote Sensing of Environment, 1993, 43(1): 23-33.
[10]
[11]	Roger R E, Arnold J F. Reliably estimating the noise in AVIRIS hyperspectral images [J]. International Journal of Remote Sensing, 1996, 17(10): 1951-1962.
[12]
[13]
[14]	Liu Xiang. Target detection on hyperspectral imagery based on transformation of spectral dimensions [D]. Beijing:Graduate University of the Chinese Academy of Sciences, 2008. (in Chinese) 刘翔. 基于光谱维变换的高光谱图像目标探测研究[D]. 北京院中国科学院研究生大学, 2008.
[15]	Wei Feng, He Mingyi, Mei Shaohui. Hyperspectral data feature extraction using spatial coherence based neighborhood preserving embedding [J]. Infrared and Laser Engineering, 2012, 41(5): 1249-1254. (in Chinese) 魏峰, 何明一, 梅少辉. 空间一致性邻域保留嵌入的高光谱数据特征提取[J]. 红外与激光工程, 2012, 41(5): 1249-1254.
[16]
[17]	Shutin D, Buchgraber T, Kulkarni S R, et al. Fast variational sparse bayesian learning with automatic relevance determination for superimposed signals[J]. IEEE Transctions on Signal Processing, 2011, 59(12): 6257-6261.
[18]
[19]	Tipping M. Sparse Bayesian learning and the relevance vector machine [J]. Journal of Machine Learning Research, 2001 (1): 211-244.

Noise estimation algorithm based on relevance vector machine for hyperspectral imagery

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Related

Proportional views