高动态环境下的运动模糊图像配准

付强; 孙秀霞; 彭轲; 刘树光

doi:10.3788/OPE.20152313.0523

您当前的位置：

首页 >

文章列表页 >

高动态环境下的运动模糊图像配准

更新时间：2020-08-13

- 高动态环境下的运动模糊图像配准
- Registration of moving fuzzy image in high dynamic environment
- 光学精密工程 2015年23卷第10z期页码：522-527
- 作者机构：
  
  空军工程大学航空航天工程学院,陕西西安,710038
- 作者简介：
- 基金信息：
  
  中国博士后科学基金资助项目(No.2014M562629),陕西省自然科学基金资助项目(No.2014JM8332)()
- DOI：10.3788/OPE.20152313.0523
  中图分类号： TP391.4
- 收稿日期：2015-04-20，
  
  修回日期：2015-05-28，
  
  纸质出版日期：2015-11-14
- 稿件说明：
移动端阅览
付强, 孙秀霞, 彭轲等. 高动态环境下的运动模糊图像配准[J]. 光学精密工程, 2015,23(10z): 522-527

FU Qiang, SUN Xiu-xia, PENG Ke etc. Registration of moving fuzzy image in high dynamic environment[J]. Editorial Office of Optics and Precision Engineering, 2015,23(10z): 522-527
付强, 孙秀霞, 彭轲等. 高动态环境下的运动模糊图像配准[J]. 光学精密工程, 2015,23(10z): 522-527 DOI： 10.3788/OPE.20152313.0523.

FU Qiang, SUN Xiu-xia, PENG Ke etc. Registration of moving fuzzy image in high dynamic environment[J]. Editorial Office of Optics and Precision Engineering, 2015,23(10z): 522-527 DOI： 10.3788/OPE.20152313.0523.

摘要

由于高动态环境下摄像机拍摄的待配准图像存在大旋转变换的同时还会受运动模糊退化的影响

故本文设计了一种高动态环境下的运动模糊图像配准方法。分析了传统尺度不变特征变换(SIFT)算法实时性差的原因

利用灰度级变换对SIFT算法进行改进

对两幅待配准图像特征点的提取进行简化

从而避开检测出大量无用特征点带来实时性差的问题。然后选取简化后的特征点进行特征匹配

使配准算法精度更高。最后通过实验验证了本文设计方法的实效性。实验结果表明:提出的算法的特征点数以及匹配对数保持在改善算法前的10%以内

大大减少了计算量;该算法对图像旋转的稳定性更强

匹配对数占检测出的特征点数的比值范围从0.1505减小到0.1365。相比SIFT算法效率更高

稳定性更强

更能满足高动态环境下的图像配准要求。

Abstract

In matching the under-registration images in a high dynamic environment

there is large rotation distortion meanwhile the images may turn into blur in motion states

so traditional algorithms fail to match the images accurately in real-time. To solve these problems

a registration algorithm of fuzzy image in the high dynamic environment was designed in this paper. Based on the analysis of the cause of the Scale Invarian Feature Transform(SIFT) algorithm's poor timeliness

the gray-scale transform was chosen as a threshold to change the pixels of image and to reduce the number of feature points. Then

simplified feature points were chosen to implement the feature matching to improve the accuracy of the registration. Finally

an experiment was performed to demonstrate the effectiveness of this method. Experimental results indicate that the number of matching-pairs and feature points are 10% that of the original algorithm; the stability is stronger than that of the original SIFT algorithm

and the ratio of matching-pair and feature points are reduced from 0.1505 to 0.1365. Compared with the traditional SIFT algorithm

this method owns better efficiency and stability

and can satisfy the requirements of image matching in the high dynamic environment.

关键词

Keywords

references

余先川,吕中华,胡丹. 遥感图像配准技术综述[J]. 光学精密工程,2013,21(11):2960-2972. YU X CH, LÜ ZH H, HU D. Review of remote sensing image registration techniques[J]. Opt. Precision Eng., 2013,21(11):2960-2972.(in Chinese)

王健博,朱明. 基于字典描述向量的实时图像配准[J]. 光学精密工程, 2014,22(6):1613-1621. WANG J B, ZHU M. Real time image registration based on dictionary feature descriptor[J].Opt. Precision Eng.,2014,22(6):1613-1621.(in Chinese)

沈同圣,张健,娄树理. 面向目标检测的空间观测图像精确配准[J]. 光学精密工程,2014,22(8):2205-2213. SHEN T SH, ZHANG J, LOU SH L. Precise registration of space observation images for target detection[J]. Opt. Precision Eng.,2014,22(8):2205-2213.(in Chinese)

刘佳,傅卫平,王雯,等. 基于改进SIFT算法的图像匹配[J]. 仪器仪表学报, 2013,34(5):1107-1112. LIU J, FU W P, WANG W, et al.. Image matching based on improved SIFT algorithm[J]. Chinese Journal of Scientific Instrument, 2013,34(5):1107-1112.(in Chinese)

刘辉,申海龙. 一种基于改进SIFT算法的图像配准方法[J]. 微电子学与计算机,2014,31(1):38-42. LIU H, SHEN H L. Image match method based on improved SIFT algorithm[J].Microelectronics and Computer, 2014,31(1):38-42.(in Chinese)

尚明姝. 基于改进SIFT特征匹配的快速图像拼接算法[J]. 微电子学与计算机,2014,31(1):64-67. SHANG M SH. A fast image mosaic algorithm based on improved SIFT feature matching[J]. Microelectronics and Computer, 2014,31(1):64-67.(in Chinese)

齐乃新,曹立佳,杨小冈,等. 基于方向约束的改进SIFT匹配算法[J]. 计算机科学,2014,41(6A):125-128. QI N X, CAO L J, YANG X G, et al.. Improved SIFT matching algorithm based on orientation constraint[J]. Computer Science, 2014,41(6A):125-128.(in Chinese)

张德全,董世存. 改进SIFT算法在图像数据相似性匹配中的应用研究[J]. 计算机科学,2014,41(6A):122-124. ZHANG D Q, DONG SH C. Application research on comparability matching for image-data based on enhanced SIFT algorithm[J]. Computer Science, 2014,41(6A):122-124.(in Chinese)

师艳伟,杨晶东,杨敬辉. 一种改进SIFT 算法[J]. 江南大学学报:自然科学版, 2014,13(4):403-410. SHI Y W, YANG J D, YANG J H. Research on an improved SIFT algorithm[J]. Journal of Jiangnan University:Natural Science Edition, 2014,13(4):403-410(in Chinese)

卢朝梁,马丽华,陈豪. 改进的SIFT特征匹配算法[J]. 空军工程大学学报:自然科学版, 2014,15(1):72-76. LU CH L, MA L H, CHEN H. An improved algorithm for SIFT feature matching[J]. Journal of Air Force Engineering University:Natural Science Edition,2014,15(1):72-76.(in Chinese)

LOWE D G. Distinctive image features from scale-invariant key points[J]. International Journal of Computer Vision,2004,60(2):91-110.

浏览量

406

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

特征融合和自适应权重更新相结合的运动模糊目标跟踪

基于增强拉东变换及稀疏先验的模糊星斑复原

匀速直线运动模糊图像的模糊参数鲁棒识别

双CMOS成像系统中运动模糊图像的复原

运动成像混合模糊的全变分图像复原