基于互学习的自适应PSO算法的亚像素定位研究

J4 ›› 2016, Vol. 38 ›› Issue (04): 747-754.

基于互学习的自适应PSO算法的亚像素定位研究

刘欢1，2,肖根福3，欧阳春娟1

（1.井冈山大学电子与信息工程学院，江西吉安 343009;
2.流域生态与地理环境监测国家测绘地理信息局重点实验室，江西吉安 343009;
3.井冈山大学机电工程学院，江西吉安 343009）

收稿日期:2015-05-21 修回日期:2015-07-10 出版日期:2016-04-25 发布日期:2016-04-25
基金资助:
国家自然科学基金(61462016)；江西省科技厅青年科学基金(20151BAB217012)；江西省科技厅自然科学基金(20151BAB207026)；江西省教育厅2014年度科技计划(GJJ14559)；江西省高校人文社科研究项目（YS1546）;流域生态与地理环境监测国家测绘地理信息局重点实验室资助课题；井冈山大学博士启动项目（JZB15016,JZB15009）

Subpixel registration based on adaptive particle
swarm optimization with mutual learning

LIU Huan1，2,XIAO Genfu3，OUYANG Chunjuan1

（1.School of Electronics and Information Engineering,Jinggangshan University,Ji’an 343009;
2.Key Laboratory of Watershed Ecology and Geographical Environment Monitoring,NASG,Ji’an 343009;
3.College of Machanical & Electrical Engineering,Jinggangshan University,Ji’an 343009,China）

Received:2015-05-21 Revised:2015-07-10 Online:2016-04-25 Published:2016-04-25

摘要/Abstract

摘要：

针对数字图像相关方法（DIC）的亚像素精确定位运算量大、时间代价高的问题，提出了一种改进的粒子群优化方法的亚像素精确定位。依据待测物图像中特征点变形程度的差异自适应地调整粒子飞行的速度和范围并细化到x和y二维方向上，改善特征点位移解的质量；另外，引入粒子间的互相学习机制，充分利用前一粒子的历史信息，减少迭代次数，提高算法运行效率；最后，将这种互学习的自适应粒子群的亚像素定位算法与牛顿拉夫森（NewtonRaphson）算法和牛顿拉夫森粒子群（NRPSO）算法作比较。实验结果表明，本文算法具有更高的精度、有效性和可行性，尤其在处理大数据量时，该算法的时间成本优势更为显著。

Abstract:

In order to solve the problem of huge computation and high time cost in subpixel registration resolution of digital image correlation, we propose a new improved PSO for subpixel registration of the respective flight velocities. The flying velocity and range of particles which are subdivided at two directions x and y, can adaptively adjust according to the deformation degree of each interest point so as to improve their displacement solution quality. In addition, the reliable mutual learning mechanism is introduced and the historical information of the previous feature points is fully utilized, which helps to reduce the number of iterations and enhance algorithm efficiency. Compared with the NewtonRaphson and the NRPSO, the proposed method has higher accuracy, and the feasibility and availability are verified. Particularly, the superiority of time cost is more distinct when dealing with a large number of interest points.

Key words: digital image correlation;subpixel registration resolution;mutual learning adaptive particle swarm optimization;NewtonRaphson algorithm

刘欢1，2,肖根福3，欧阳春娟1. 基于互学习的自适应PSO算法的亚像素定位研究[J]. J4, 2016, 38(04): 747-754.

LIU Huan1，2,XIAO Genfu3，OUYANG Chunjuan1. Subpixel registration based on adaptive particle
swarm optimization with mutual learning [J]. J4, 2016, 38(04): 747-754.

参考文献［20］

［1］	Peters W H,Ranson W F. Digital imaging techniques in experimental stressanalysis［J］. Optical Engineering,1982,21（3）:427431．
［2］	Jin Guanchang,Meng Libo,Chen Junda,et al. The progress and application of digital speckle correlation method［J］. Journal of Experimental Mechanics，2006,21（6）:120129．(in Chinese)
［3］	Qiu Tian,Guo Li,Li Donghui,et al. Extremum method for processing digital laser speckle images to extract sub pixel displacement［J］.Opto Electronic Engineering,2006，33（9）:10761078．(in Chinese)
［4］	Wattisse B C,Muracciole A,NemozGaillard J M. Analysis of strain localization during tensile tests by digitial image correlation［J］. Experimental Mechanics,2001,41（1）:2939．
［5］	Pan B,Wu D F,Xie　H M,et al. Spatialgradientbased digital volume correlation technique for internal deformation measurement［J］. Actaopticasinica,2011,31（6）:0612005106120057．
［6］	Pan Bing,Xu Boqin. Subpixel registration using quadratic surface fitting in digital image correlation［J］. Acta Metrologica Sinica,2005,26（2）:128134．(in Chinese)
［7］	Verhulp E,Van Reitbergen B,Husikes R. A threedimensional digital image correlation technique for strain measurements in microstructures［J］. Journal of Biomechanics,2004,37（9）:13131320．
［8］	Wang H W,Kang Y L. Improved digital speckle correlation method and its application in fracture analysis of metallic foil［J］. Optical Engineering,2002,41（11）:27932798．
［9］	Gao Jianxin, Zhou Xingeng. Principle and applications of digital speckle correlation method［J］. Acta Mechanica Sinica,1995,27（6）:724731．(in Chinese)
［10］	Zhang Jinkui,Li Yazhi,Zhang Li,et al. Digital image correlation strain measurement based on moving leastsquares fitting［J］.Science Technology and Engineering,2010,10（3）:686690．(in Chinese)
［11］	Wang Shibin,Li Xiangyu,Li Linan,et al. Determination of displacement fields by means of maximum a posteriori estimator［J］. Journal of Experimental Mechanics,2004,19（3）:371375．(in Chinese)
［12］	Pan Bing, Xie Huimin. Digital image correlation method with different evolution［J］. Journal of Optoelectronics:Laser,2007,18（1）:100103．(in Chinese)
［13］	Tang C,Liu M,Yan H,et al. The improved genetic algorithms for digital image correlation method［J］. Chinese Optics Letters,2004,2（10）:574577．
［14］	Pilch A, Mahajan A, Chu T. Measurement of wholefiled surface displacements and strain using a genetic algorithm based intelligent image correlation method［J］. Journal of Dynamic Systems,Measurement and ControlTransactions of the ASME,2004,126（3）:479488．
［15］	Jiang Zhinian. New algorithm for digital image speckle correlation method based on ant colony optimization［J］.Journal of Applied Optics,2012,33（3）:527531．(in Chinese)
［16］	Pan B,Li K. A fast digital image correlation method for deformation measurement［J］. Optics and Lasers in Engineering,2011,49（7）:841847．
［17］	Kennedy J,Eberhart R C. Particle swarm optimization［C］∥Proc of the IEEE International Conference on Neural Network,1995:19421948．
［18］	Feng Xuefang,Wu Xisheng. Adaptive accelerated particle swarm algorithm for image registration based on normalized edge mutual information［J］. Computer Engineering & Science,2013,35（1）:119123．(in Chinese)
［19］	Gou Jin,Wang Fei. Shape error detection based on a variable searching area and adaptive learning PSO algorithm［J］. Journal of Chinese Computer Systems,2014,35（7）:16151619．(in Chinese)
［20］	Du Yazhi,Wang Xuebin. Digital image correlation method based on NewtonRaphson method and particle swarm optimization algorithm［J］.Computer Engineering and Application,2012,48（34）:184189.(in Chinese)
	附中文参考文献：
［2］	金观昌,孟利波,陈俊达,等. 数字散斑相关技术进展及应用［J］. 实验力学,2006,21（6）:120129．
［3］	邱天,郭立,李东晖,等. 数字激光散斑图像的极值位移测量法［J］. 光电工程,2006,33（9）:10761078．
［6］	潘兵,续伯钦. 数字图像相关中亚像素位移测量的曲面拟合法［J］. 计量学报,2005,26（2）:128134．
［9］	高建新,周新庚. 数字散斑相关方法的原理与应用［J］. 力学学报,1995,27（6）:724731．
［10］	张金奎,李亚智,张丽,等. 基于移动最小二乘拟合的数字图像相关应变测量［J］. 科学技术与工程,2010,10（3）:686690．
［11］	王世斌,李翔宇,李林安,等. 后验概率算法用于位移场的确定［J］. 实验力学,2004,19（3）:371375．
［12］	潘兵,谢惠民. 基于差分进化的数字图像相关方法［J］.光电子·激光,2007,18（1）:100103．
［15］	蒋志年. 数字图像散斑相关技术的蚁群优化方法［J］. 应用光学,2012,33（3）:527531．
［18］	冯雪芳,吴锡生. 基于归一化边缘互信息与自适应加速粒子群的图像配准方法互信息测度［J］. 计算机工程与科学,2013,35（1）:119123．
［19］	缑锦,王飞. 基于可变搜索区域的自适应学习粒子群优化算法的形状误差检测［J］. 小型微型计算机系统,2014,35（7）:16151619．
［20］	杜亚志,王学滨. 基于NewtonRaphson迭代与PSO算法的数字图像相关方法［J］.计算机工程与应用，2012,48（34）:184189．