Image distortion calibration of imaging spectrometer with grating by SVM

Han Jun; Chang Bo; Lu Shaojun; Wu Lingling; Zhan Chunlian

Imaging spectrometer was a kind of optical remote sensing instruments which combined image with spectrum. Grating imaging spectrometer can acquire data cube. When the sampling frequency and splicing was reasonable, because of the nonlinear about dispersive elements making spectral expansion, lead to the distortion of strip image, as well as the distortion of spliced image. The distortion feature points were extracted more accurate by using the gray gradient from the edge to the center and genetic algorithm. By choosing appropriate parameters, we established the support vector machine regression mathematical model to correct the distortion. Compared with the conventional distortion correction method. This method was able to balance effectively the error from the global and the local and improve the accuracy of correction. The calibration of error can be controlled within 0.5 pixels by experimental verification.

1. School of Optoelectronic Engineering,Xi'an Technological University,Xi'an 710032,China;

2. Xi'an Institute of Applied Optics,Xi'an 710065,China

Received Date: 2014-01-05

Rev Recd Date: 2014-02-10

Publish Date: 2014-09-25

Key words:

Abstract: Imaging spectrometer was a kind of optical remote sensing instruments which combined image with spectrum. Grating imaging spectrometer can acquire data cube. When the sampling frequency and splicing was reasonable, because of the nonlinear about dispersive elements making spectral expansion, lead to the distortion of strip image, as well as the distortion of spliced image. The distortion feature points were extracted more accurate by using the gray gradient from the edge to the center and genetic algorithm. By choosing appropriate parameters, we established the support vector machine regression mathematical model to correct the distortion. Compared with the conventional distortion correction method. This method was able to balance effectively the error from the global and the local and improve the accuracy of correction. The calibration of error can be controlled within 0.5 pixels by experimental verification.

HTML

Reference (15)

[1]	Xu Hong, Wang Xiangjun. Applications of multispectral/hyperspectral imaging technologies in military [J]. Infraredand Laser Engineering, 2007, 2(1): 13-15. (in Chinese)许洪, 王向军. 多光谱、超光谱成像技术在军事上的应用[J]. 红外与激光工程, 2007, 2(1): 13-15.
[2]
[3]
[4]	Fang Yu, Xiang Libin, Yuan Yan, et al. Design of theairborne prism dispersive imaging spectrometer system basedon offner relay configuration [J]. Spectroscopy and SpectralAnalysis, 2013, 3(3): 841-842. (in Chinese)方煜，相里斌，袁艳，等. 基于Offner 中继结构的机载棱镜色散成像光谱仪系统设计[J]. 光谱学与光谱分析, 2013,3(3): 841-842.
[5]	V1adimir N, Vapnik V. An overview of statistical learningtheory [J]． IEEE Transsaction on Neural Networks, 1999,10(5): 988-999．
[6]
[7]	Vapnik V. Estilnation of Dependencies Based on EmpiricalData [M]. USA: Springer New York, 1981．
[8]
[9]
[10]	Yuan Huize. Study on X-ray image dirtortion correction ofsub-pixels accuracy[D]. Harbin: Harbin Institute of Technology,2009. (in Chinese)袁泽慧. 亚像素精度X 射线图像畸变校正研究[D]. 哈尔滨: 哈尔滨工业大学, 2009.
[11]	Zhao Chunhui, Chen Wanhai, Guo Chunyan. Research andanalysis of methods for multiclass support vector machines[J]. CAAI Transactions on Intelligent Systems, 2007, 2 (2):11-17． (in Chinese)赵春晖, 陈万海, 郭春燕. 多类支持向量机方法的研究现状与分析[J]. 智能系统学报, 2007, 2(2): 11-17．
[12]
[13]	Li Haisheng. Algorithm and application research of supportvector machine regression [D]. Guangzhou: South ChinaUniversity of Technology, 2005. (in Chinese)李海生. 支持向量机回归算法的研究与应用[D]. 广州: 华南理工大学, 2005.
[14]
[15]	Vapnm V, Chapelle O． Bounds on error expectation forsupport vector machines [J] ． Neural Computation, 2000,12 (9): 2013-1036．

Image distortion calibration of imaging spectrometer with grating by SVM

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Related

Proportional views