首页 > 论文 > 应用光学 > 36卷 > 6期(pp:893-899)

基于特征匹配的快速鲁棒数字稳像

Fast robust digital image stabilization based on feature matching

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对手持移动摄像装置拍摄视频序列相邻帧间存在平移、小角度旋转运动, 而且易受噪声、光照变化的影响等问题, 提出一种基于优化Oriented FAST and rotated BRIEF(ORB)特征匹配的实时鲁棒电子稳像算法。对相邻帧预处理后用Oriented FAST算子检测特征点, 再用Rotated BRIEF描述提取的特征点并采用近邻汉明距离匹配特征点对, 然后采用级联滤波去除误匹配点对, 最后使用迭代最小二乘法(ILSM)拟合模型参量进行运动补偿实现稳像。图像匹配测试和稳像实验结果表明: 基于改进的ORB算法的电子稳像方法补偿每一帧的时间均小于0.1 s, 定位精度可达亚像素级, 能有效补偿帧间平移旋转运动, 而且对噪声和光照变化有较强鲁棒性。经稳像处理后, 实拍视频质量明显提高, 峰值信噪比(PSNR)平均提高了10 db。

Abstract

In view of the problems that the translation and small angle rotation motion always exist between adjacent frames when the handheld mobile camera is filming video sequence, and it is easily affected by noise and illumination changes,we put forward a kind of real-time robust digital image algorithm based on optimized oriented features from accelerated segment test (FAST) and rotated binary robust independent elementary features (BRIEF) (ORB) feature matching algorithm.Firstly the adjacent frame images were preprocessed to enhance image clarity and to avoid noise interference;secondly the oriented FAST operator was used to detect feature points and the rotated BRIEF was used to describe feature points, then the neighbor hamming distance was adopted to match the ORB feature point pairs; thirdly the cascaded filter was used to remove the false matching points; finally the iterative least squares method(ILSM) was used to fit model parameters,then the motion compensation was done to achieve digital image stabilization. Standard image matching test and digital image stabilization experimental results show that the run time of compensation for each frame by the electric image stabilization method based on improved ORB algorithm is faster than 0.1 s, the positioning accuracy can reach sub-pixel level, this method can effectively compensate the translation and rotation movement between the adjacent frames, and is not sensitive to noise and illumination changes, has strong robustness. After image stabilization processing,the real scene shooting video quality obviously improves and the peak signal-to-noise ratio (PSNR) increases by an average of 10 db.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TN911.73;TP394.1

DOI:10.5768/jao201536.0602003

所属栏目:光电信息获取与处理

基金项目:军内科技创新项目(装司字[2012]665)

收稿日期:2015-04-28

修改稿日期:2015-08-10

网络出版日期:--

作者单位    点击查看

谢征:军械工程学院 导弹工程系, 河北 石家庄 050003
崔少辉:军械工程学院 导弹工程系, 河北 石家庄 050003
李金伦:军械工程学院 导弹工程系, 河北 石家庄 050003

联系人作者:谢征(xiezheng@mail.ustc.edu.cn)

备注:谢征(1991-), 男, 安徽亳州人, 硕士研究生, 主要从事捷联图像制导电子稳像技术研究。

【1】Wang Zhimin, Xu Xiaogang. A survey on electronic image stabilization[J].Journal of Image and Graphics, 2010, 15(3): 470-480.
王志民, 徐晓刚. 电子稳像技术综述[J]. 中国图像图形学报, 2010, 15(3): 470-479.

【2】Cuevas E, Zaldvara D, Pérez-Cisneros M, et.al. Block matching algorithm for motion estimation based on Artificial Bee Colony (ABC)[J].Applied Soft Computing, 2013,13(6): 3047-3059.

【3】Gu Guohua,Gu Xuehai, Wang Liping. Electric image stabilization based on improved gray projection[J].Journal of Applied Optics, 2013, 34(6):867-963.
顾国华, 顾学海, 王利平. 基于灰度投影改进的电子稳像[J]. 应用光学, 2013, 34(6): 867-963.

【4】Luo Jun, Dong Hongyan, Shen Zhenkang. Video stabilization based on bit-plane registration and Kalman filter[J]. Infrared and Laser Engineering, 2008, 37(2): 304-307.
罗军, 董鸿雁, 沈振康. 基于位平面匹配和卡尔曼滤波的视频稳定[J]. 红外与激光工程, 2008, 37(2): 304-307.

【5】Xing Hui, Yan Jinglong, Zhang Shujiang. Digital image stabilization algorithm based on phase correlation[J]. Opto-Electronic Engineering, 2007, 34(3): 37-41.
邢慧, 颜景龙, 张树江. 基于相位相关的数字稳像算法研究[J]. 光电工程, 2007, 34(3): 37-41.

【6】Zhang Yanning,Zhang Xingong,Zhu Yu,et.al. A stabilized Harris confidence based 3SS of digital video stabilizing method[J]. Acta Photonica Sinica,2010,39(2): 364-368.
张艳宁,张新功,朱宇,等. 基于稳定Harris置信度的三步搜索数字稳像方法[J]. 光子学报,2010,39(2): 364-368.

【7】Chu Shouyan, Xi Zhihong. Digital image stabilization based on SURF[J].Journal of Computer-Aided Design & Computer Graphics, 2014, 26(2),242-247.
初守艳, 席志红. 结合SURF的数字稳像技术[J]. 计算机辅助设计与图形学学报. 2014, 26(2),242-247.

【8】Schulze C, Liwicki M. Optimized SIFT feature matching for image retrieval[J]. Lecture Notes in Computer Science, 2014, 1(1): 102-115.

【9】Rublee E, Rabaud V, Konolige K, et al. ORB: An efficient alternative to SIFT or SURF[C]// ICCV.New York:IEEE, 2011: 2564-2571.

【10】Rosten E, Porter R,Drummond T. Faster and better: a machine learning approach to corner detection[J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 2010, 32(1): 105-119.

【11】Calonder M, Lepetit V, Strecha C, et al. BRIEF: binary robust independent elementary features[C]//ECCV.Berlin:Springer Berlin Heidelberg,2010: 778-792.

【12】Hou Yi, Zhou Shilin, Lei Lin,et.al. Fast fully affine invariant image matching based on ORB[J].Computer Engineering & Science, 2014, 36(2): 303-310.
候毅, 周石琳, 雷琳,等. 基于ORB的快速完全仿射不变图像匹配[J]. 计算机工程与科学, 2014, 36(2): 303-310.

【13】Wang Guodong, Wen Pengcheng, Chen Yue. A method for aerial image stitching using ORB feature points[J].Journal of Inner Mongolia University:Natural Science Edition, 2014, 43(4): 425-433.
王国东, 文鹏程, 程岳. 一种利用ORB特征进行航拍图像拼接的方法[J]. 内蒙古师范大学学报:自然科学汉文版, 2014, 43(4): 425-433.

【14】Chen Fuxin, Wang Runsheng. Fast RANSAC with preview model parameters evaluation[J]. Journal of Software,2005, 16(8): 1431-1437.
陈付幸, 王润生. 基于预检验的快速随机抽样一致性算法[J].软件学报, 2005, 16(8): 1431-1437.

引用该论文

Xie Zheng,Cui Shaohui,Li Jinlun. Fast robust digital image stabilization based on feature matching[J]. Journal of Applied Optics, 2015, 36(6): 893-899

谢征,崔少辉,李金伦. 基于特征匹配的快速鲁棒数字稳像[J]. 应用光学, 2015, 36(6): 893-899

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF