Real-time full-frame digital image stabilization system by SURF

ZHANG Kun; XU Ting-fa; WANG Ping; FENG Liang

doi:10.3788/OPE.20111908.1964

您当前的位置：

首页 >

文章列表页 >

Real-time full-frame digital image stabilization system by SURF

Article | 更新时间：2020-08-12

- Real-time full-frame digital image stabilization system by SURF
- Optics and Precision Engineering Vol. 19, Issue 8, Pages: 1964-1972(2011)
- 作者机构：
  
  1. 北京理工大学光电学院,北京 10081
  2. 北京理工大学光电成像技术与系统教育部重点实验室,北京 100081
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20111908.1964
  CLC： TN941.1
- Received：09 June 2011，
  
  Revised：01 July 2011，
  
  Published Online：25 August 2011，
  
  Published：25 August 2011
- 稿件说明：
移动端阅览
张坤, 许廷发, 王平, 冯亮. 高精度实时全帧频SURF电子稳像方法[J]. 光学精密工程, 2011,19(8): 1964-1972

ZHANG Kun, XU Ting-fa, WANG Ping, FENG Liang. Real-time full-frame digital image stabilization system by SURF[J]. Editorial Office of Optics and Precision Engineering, 2011,19(8): 1964-1972
张坤, 许廷发, 王平, 冯亮. 高精度实时全帧频SURF电子稳像方法[J]. 光学精密工程, 2011,19(8): 1964-1972 DOI： 10.3788/OPE.20111908.1964.

ZHANG Kun, XU Ting-fa, WANG Ping, FENG Liang. Real-time full-frame digital image stabilization system by SURF[J]. Editorial Office of Optics and Precision Engineering, 2011,19(8): 1964-1972 DOI： 10.3788/OPE.20111908.1964.

摘要

针对视频抖动和电子稳像的实时性

提出了基于SURF的电子稳像算法。首先

采用SURF算法检测图像的兴趣点

建立了当前帧与参考帧的对应关系

得出高精度的运动估计矢量。然后

通过判定参考帧更新策略

获得平滑的帧间全局运动矢量

进而对原始视频序列进行运动补偿。最后

将参考帧对应区域像素填充到稳像帧丢失像素区域进行全帧频补偿

输出高精度的实时全帧频电子稳像视频。实验结果表明

采用SURF算法的实时电子稳像算法

运行时间<30 ms

精确度<1 pixel

对存在严重运动模糊的视频具有较强的鲁棒性

可以去除帧间高频抖动并有效改善视频质量。

Abstract

To overcome the undesirable shakes or jiggles of a camera and to implement the image stabilization in real time

a real-time full-frame video stabilization system based on the Speeded Up Robust Features(SURF) was proposed.Firstly

the SURF was employed to extract feature points

and the correspondence between the current and reference frame was established to get high precision local motion vector estimation. Secondly

by determining the reference frame update strategy

the smoothed interframe global motion vector was obtained. Finally

the corresponding pixels of the reference frame was filled with a stablized frame to compensate the unstable motion and to output an stablized full-frame video. Experimental results show that the real-time full-frame video stabilization system using SURF algorithm can provide the high accuracy (lower than 1 pixel) and short processing time (less than 30 ms). Moreover

it has a higher robustness on serious motion-blur and better image quality.

关键词

Keywords

references

王志民,徐晓刚. 电子稳像技术综述[J]. 中国图象图形学报,2010,15(3):470-480. WANG ZH M, XU X G. A survey on electronic image stabilization[J]. Journal of Image and Graphics, 2010,15(3):470-480. (in Chinese)[2] PO L M,NG K H,WONG K M, et al.. Multi-direction search algorithm for block-based motion estimation . Proceedings of IEEE Asia Pacific Conference on Circuits and Systems, 2008:1466-1469.[3] ZHANG Y X, WANG J, ZHANG W G, et al..An improved algorithm of electronic image stability based on block matching . Proceedings of 2010 the 5th IEEE Conference on Industrial Electronics and Applications (ICIEA), 2010:1924-1927.[4] TICO M. Adaptive block-based approach to image stabilization . Proceedings of 15th IEEE International Conference on Image Processing, 2008:521-524.[5] YIN B, DUAN H CH. Image stabilization by combining gray-scale projection and block matching algorithm . Proceedings of IEEE International Symposium on IT in Medicine & Education, 2009:1262-1266.[6] LIU Y K,DE J F,BO L, et al.. Real-time global motion vectors estimation based on phase correlation and gray projection algorithm . Proceedings of 2nd International Congress on Image and Signal Processing, 2009:1262-1266.[7] TIAN S Q, ZHAO P, WANG N H, et al.. Aims at moving objects' improvement based on gray projection of algorithm of the electronic image stabilization . Proceedings of 2010 3rd International Congress on Image and Signal Processing, 2010:2483-2487.[8] 王小鹏,阎国梁,裴建刚,等. 由形态学边缘模式匹配实现数字稳像[J]. 光学精密工程, 2009,17(3):683-689. WANG X P, YAN G L, PEI J G. Stabilization of digital image by morphological edge pattern matching[J]. Opt. Precision Eng., 2009,17(3):683-689. (in Chinese)[9] 张叶, 曲宏松, 王延杰. 运用旋转无关特征线实现景象匹配[J]. 光学精密工程, 2009,17(7):1759-1765. ZHANG Y, QU H S, WANG Y J. Implementation of scene matching based on rotation invariant keylines[J]. Opt. Precision Eng., 2009,17(7):1759-1765. (in Chinese)[10] 纪华,吴元昊,孙宏海,等. 结合全局信息的SIFT特征匹配算法[J]. 光学精密工程, 2009, 17(2):439-444. JI H,WU Y H, SUN H H, et al..SIFT feature matching algorithm with global information[J]. Opt. Precision Eng., 2009,17(2):439-444. (in Chinese)[11] HERBERT B, TINNE T, LUC VAN G. SURF: speeded up robust features . 9th European Conference on Computer Vision, Graz, Austria, ECCV, 2006:404-417.

Views

219

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Fast digital image stabilization based on characteristic peak of projection matching

Digital video stabilization for large-scale moving foreground object and rotation jitter

Binocular vision measurement method incorporating one-dimensional probabilistic Hough transform and local Zernike moment

Optimization of correlation algorithms for small array pixels tracking sensors

Sub-pixel image registration based on super resolution reconstruction

Related Author

ZHANG Yan-chao

SUN Qiang

WANG Fei

LIU Jian-zhuo

ZHAO Jian

WANG Fang

DI Xiao-guang

JIN Wan-xin

Related Institution

The First Engineer Scientific Research Institute of the General Armament Department

University of Chinese Academy of Sciences

Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences

Science and Technology Institute on Space Physics

Control and Simulation Center, Harbin Institute of 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