Parameter estimation of linear motion blur based on principal component analysis

LI Hai-sen1; ZHANG Yan-ning1; YAO Rui1; Sun Jin-qiu2

doi:10.3788/OPE.20132110.2656

您当前的位置：

首页 >

文章列表页 >

Parameter estimation of linear motion blur based on principal component analysis

更新时间：2020-08-12

- Parameter estimation of linear motion blur based on principal component analysis
- Optics and Precision Engineering Vol. 21, Issue 10, Pages: 2656-2663(2013)
- 作者机构：
  
  1. 西北工业大学计算机学院，陕西西安 710129
  2. 西北工业大学精确制导与控制研究所,陕西西安,710072
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20132110.2656
  CLC： TP391.4
- Received：07 April 2013，
  
  Revised：13 May 2013，
  
  Published Online：19 October 2012，
  
  Published：15 October 2013
- 稿件说明：
移动端阅览
李海森张艳宁姚睿孙瑾秋. 基于主成分分析的直线运动模糊参数估计[J]. 光学精密工程, 2013,21(10): 2656-2663

LI Hai-sen ZHANG Yan-ning YAO Rui Sun Jin-qiu. Parameter estimation of linear motion blur based on principal component analysis[J]. Editorial Office of Optics and Precision Engineering, 2013,21(10): 2656-2663
李海森张艳宁姚睿孙瑾秋. 基于主成分分析的直线运动模糊参数估计[J]. 光学精密工程, 2013,21(10): 2656-2663 DOI： 10.3788/OPE.20132110.2656.

LI Hai-sen ZHANG Yan-ning YAO Rui Sun Jin-qiu. Parameter estimation of linear motion blur based on principal component analysis[J]. Editorial Office of Optics and Precision Engineering, 2013,21(10): 2656-2663 DOI： 10.3788/OPE.20132110.2656.

摘要

为了快速准确地估计直线运动模糊图像中的模糊参数，分析了直线运动模糊参数的长度和方向在频率域图像和倒谱图像中的表现形式，提出了一种基于主成分分析的运动模糊参数估计方法。首先，基于高斯建模对模糊图像中的倒谱图像进行二值化分割，得到倒谱图像中的亮线区域。然后，基于主成分分析提取亮线区域的主成分分量，主成分分量的方向即为模糊角度；依据估计的模糊角度，计算模糊图像傅里叶频率域图像相应角度的Radon变换，进行滤波去毛刺处理。最后，通过计算极小值之间的间距，估计模糊长度。实验结果表明：估计的模糊角度和模糊长度平均误差分别为0.138 4和0.273 9 pixel，在同精度条件下，速度是传统的Radon变换方法的10倍左右，表明该方法能快速、准确地估计直线运动模糊参数。

Abstract

To estimate the blur parameter of a linear motion blur image accurately and quickly

this paper analyses how the blur length and direction show in a frequency image and a cepstrum image

respectively

and proposes a motion blur parameter estimation method based on the Principal Component analysis (PCA). Firstly

the cepstrum image of the blur image was segmented in a binaryzation based on the Gaussian distribution modeling

and the highlight line region in the cepstrum image was obtained. Then

the principal component of the highlight line was extracted based on the PCA

and the direction of the principal component was the blur direction. After the blur direction was estimated

the Radon transform of frequency image for the blur image under the estimated direction was calculated

then the result of Radon transform was smoothed to reduce some artifacts. Finally

the blur length was estimated via calculating the interval between the two local-minimas of the Radon transform. Experiment results indicate that the errors of the estimated blur direction and length are 0.138 4and 0.273 9 pixel

respectively

and the calculation speed is nearly 10 times faster than that of the traditional estimated method based on Radon method with the same accuracy. It concludes that the proposed method can estimate the blur parameter accurately and rapidly.

关键词

Keywords

references

HARMELING S, HIRSCH M, SCHOLKOPF B. Space-variant single-image blind deconvlution of removing camera shake [C]. Proceedings of Advances in Neural Information Processing Systems 23, 2010:829-837.[2]BABACAN S D, MOLINA R, DO M N, et al.. Bayesian blind deconvolution with general sparse image priors [C]. Proceedings of the 12th European Conference on Computer Vision, Florence, Italy, 2012:341-355.[3]KRISHNAN D, TAY T, FERGUS R. Blind deconvolution using a normalized sparsity measure [C]. Proceedings of the 12th European Conference on Computer Vision, Colorado, USA, 2011: 233-240.[4]石明珠,许廷发,张坤.运动成像混合模糊的全变分图像复原[J].光学精密工程,2011，19(8):1973-1981.SHI M Z, XU T F, ZAHNG K. Total variation image restoration for mixed blur in moving image[J]. Opt. Precision Eng., 2011, 19(8): 1973-1981. (in Chinese) [5]范赐恩,陈曦,张立国, 等.双CMOS成像系统中运动模糊图像的复原[J].光学精密工程,2012，20(6): 1389-1396.FANG C E, CHEN X, ZHANG L G, et al.. Restoration of motion blurred image in dual CMOS imaging system [J]. Opt. Precision Eng., 2012, 20(6): 1389-1396 . (in Chinese) [6]冯亮,王平,许廷发, 等.运动模糊退化图像的双字典稀疏复原[J].光学精密工程,2011，19(8): 1982-1989. FENG L, WANG P, XU T F, et al.. Dual dictionary sparse restoration of blurred images[J]. Opt. Precision Eng., 2011, 19(8): 1982-1989. (in Chinese)[7]MICHAL D, LIBOR M, TOMAS F. Blurred image restoration : A fast method of finding the motion length and angle [J]. Digital Signal Processing, 2010,10: 1677-1686. [8]WU Z Y, HUANG X H, LI X D, et al.. A simultaneous localization and mapping method based on fast-Hough transform [J]. Information Technology Journal, 2008, 7(1): 190-194.[9]FANG X Y, WU H, WU Z B, et al.. An improved method for robust blur estimation [J]. Information Technology Journal, 2011, 10(9): 1709-1716.[10]孙辉,等. 相位相关技术实现离焦模糊图像运动估计[J]. 液晶与显示, 2012，27(2): 223-228. SUN H. Estimation of Displacement for out-of-focus blurred image using phase-only correlation[J]. Chinese Journal of Liquid Crystals and Displaqys, 2012, 27(2):223-228. (in Chinese)[11]LI H S, ZHANG Y N, ZHANG H C, et al.. Blind image deblurring based on sparse prior of dictionary pair[C]. Proceeding of 21st International Conference on. IEEE Pattern Recognition. 2012: 3054-3057.[12]BISHOP C M. Pattern Recognition and Machine Learning[M]. New York: Springer, 2006.

Views

331

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Robust principal component analysis based on soft mean filtering

Intelligent evaluation of grotto surface weathering based on spectral chromatic aberration and principal component feature fusion

Adaptive radon single-pixel imaging method

Normal estimation of scattered point cloud with sharp feature

Direct measurement of sound field

Related Author

GAO Yunlong

SHAO Guifang

ZHANG Haifeng

PAN Jinyan

Wang Xinjing

WU Qinting

Zhan WANG

Chi-peng CAO

Related Institution

College of Mechanical Engineering， South China Univ. of Tech

College of Information Engineering， Jimei University

School of Mechanical and Automotive Engineering，Shanghai University of Engineering Science

National Institute for Data Science in Health and Medicine， Xiamen University

School of Information and Control Engineering， Xi'an University of Architecture and Technology

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰