计算机工程

• 图形图像处理 • 上一篇    下一篇

基于B样条迭代配准的水下扭曲图像恢复算法

马春波,赵兰兰,敖珺,王克明   

  1. (桂林电子科技大学 信息与通信学院,广西 桂林 541004)
  • 收稿日期:2015-12-21 出版日期:2017-05-15 发布日期:2017-05-15
  • 作者简介:马春波(1975—),男,教授、博士,主研方向为图像信号处理、信息安全;赵兰兰,硕士研究生;敖珺,教授;王克明,硕士研究生。
  • 基金项目:
    国家自然科学基金(61167006);“认知无线电与信息处理”省部共建教育部重点实验室主任基金(CRKL150106)。

Recovery Algorithm of Underwater Distorted Images Based on B-spline Iteration Registration

MA Chunbo,ZHAO Lanlan,AO Jun,WANG Keming   

  1. (School of Information and Communication,Guilin University of Electronic Technology,Guilin,Guangxi 541004,China)
  • Received:2015-12-21 Online:2017-05-15 Published:2017-05-15

摘要: 针对水波纹对水下目标物体成像造成的扭曲、畸变等问题,通过改进相似测度和最优化方法,提出一种从多帧扭曲的图像中恢复出目标物体的迭代配准算法。通过相关系数法对序列图像进行选取,用区域归一化互信息作为相似测度,将拟牛顿差分进化作为优化算法,对序列和其均值图像进行基于B样条自由变换模型的迭代配准,得出运动网格,由网格变化进而得到无扭曲的图像,配准后的图像通过稀疏去噪消除噪声对图像质量的影响。实验结果表明,与传统的图像配准算法相比,该算法能缩短配准时间、提高配准精度、增强图像视觉效果。

关键词: 成像质量, 水下目标, 空间变换, 配准算法, 相似测度

Abstract: For the problem of image distortion and blurring caused by the ripples in the water,a new iterative registration algorithm adopting similarity measure and optimization method to recover the real image from some stretched-out ones is proposed.Firstly,distorted sequence images are chosen with the correlation coefficient method and the real images are got from the grid changes.Grids are obtained from the iterative registration of the sequence images and their mean value ones on the basis of B-spline free transformation model.Local-normalized Mutual Information(LRMI) is used as similarity measure,and the Differential Evolution-Quasi-Newton optimization(DE-LBFGS) algorithm is adopted for optimization.Noises are removed by sparse de-noising.Experimental results show that the proposed algorithm shortens the registration time and improves the registration precision and visual effect of the image.

Key words: imaging quality, underwater target, space transformation, registration algorithm, similarity measure

中图分类号: