Feature matching electronic image stabilization based on binary robust invariant scalable keypionts

CUI Shao-hui; XIE Zheng; WANG Gang; CHEN Peng

doi:10.3788/OPE.20152309.2715

您当前的位置：

首页 >

文章列表页 >

Feature matching electronic image stabilization based on binary robust invariant scalable keypionts

更新时间：2020-08-12

- Feature matching electronic image stabilization based on binary robust invariant scalable keypionts
- Optics and Precision Engineering Vol. 23, Issue 9, Pages: 2715-2723(2015)
- 作者机构：
  
  军械工程学院导弹工程系,河北石家庄,050003
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20152309.2715
  CLC： TP391.4
- Received：29 April 2015，
  
  Revised：25 June 2015，
  
  Published：25 September 2015
- 稿件说明：
移动端阅览
崔少辉, 谢征, 王刚等. 二进制鲁棒不变尺度特征匹配电子稳像[J]. 光学精密工程, 2015,23(9): 2715-2723

CUI Shao-hui, XIE Zheng, WANG Gang etc. Feature matching electronic image stabilization based on binary robust invariant scalable keypionts[J]. Editorial Office of Optics and Precision Engineering, 2015,23(9): 2715-2723
崔少辉, 谢征, 王刚等. 二进制鲁棒不变尺度特征匹配电子稳像[J]. 光学精密工程, 2015,23(9): 2715-2723 DOI： 10.3788/OPE.20152309.2715.

CUI Shao-hui, XIE Zheng, WANG Gang etc. Feature matching electronic image stabilization based on binary robust invariant scalable keypionts[J]. Editorial Office of Optics and Precision Engineering, 2015,23(9): 2715-2723 DOI： 10.3788/OPE.20152309.2715.

摘要

针对捷联图像制导系统中视频序列受弹体姿态变化和抖动而出现的不稳定现象

提出了一种基于二进制鲁棒不变尺度特征关键点(BRISK)的高精度快速鲁棒电子稳像算法。首先

用BRISK算法提取图像BRISK特征描述符;为了保证匹配精度和速度

采用引导互匹配策略实现BRISK特征点跟踪匹配;然后

利用改进的随机抽样一致方法(RANSAC)剔除误匹配点对;最后

利用最小二乘算法(LSA)估计全局运动参数进而实现稳像。对标准图片的匹配测试和实拍视频稳像的结果表明:结合BRISK算法的电子稳像技术

运行时间小于30 ms

定位精度达到0.1 pixel

对光照变化、噪声以及复杂环境遮挡具有较强的鲁棒性

能快速有效地补偿捷联制导图像的复杂随机抖动并提高视频质量。

Abstract

To overcome the instability of video sequences caused by attitude changes and jitters of a projectile in the strapdown image guidance system

a robust high-precision fast electronic image stabilization algorithm based on Binary Robust Invariant Salable Keypoints(BRISK) was proposed. Firstly

the BRISK algorithm was used to extract BRISK feature descriptors of the image. To improve the matching accuracy and speeds

the mutual matching strategy was adopted to realize BRISK matching feature point tracking. Then

the improved Random Sample Consensus (RANSAC) method was used to eliminate the false matching points.Finally

the Least Square Algorithm (LSA) was taken to estimate the global motion parameters to realize image stabilization. The standard image matching test and real video shoot image results show that the strapdown image guidance stabilization technology based on BRISK algorithm can provide short processing time less than 30 ms and high positioning accuracy of 0.1 pixel. Moreover

the technology has stronger robustness to changed illumination

noise and complex environment barrier and can quickly and effectively compensate complex random jitters and improve the quality of video images.

关键词

Keywords

references

张跃,储海荣. 全捷联图像导引头制导的技术特点[J]. 光学精密工程,2014,22(10):2825-2831. ZHANG Y,CHU H R. Technical characteristics of strapdown image seeker guidance [J]. Opt. Precision Eng., 2014, 22(10):2825-2831. (in Chinese)

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. WANG ZH M, XU X G. A survey on electronic image stabilization [J].Journal of Image and Graphics, 2010, 15(3):470-479. (in Chinese)

张永祥,卢岩,栾中,等. 视频图像运动补偿系统的设计与实现[J]. 液晶与显示,2013,28(3):424-428. ZHANG Y X, LU Y, LUAN ZH, et al.. Design and implementation of motion compensation system based on FPGA[J]. Chinese Journal of Liquid Crystals and Displays, 2013, 28(3):424-428. (in Chinese)

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 [C]. Proceedings of 2010 3rd International Congress on Image and Signal Processing, 2010:2483-2487.

遆晓光,靳万鑫,余颖. 大运动前景和旋转抖动视频的快速数字稳定[J]. 光学精密工程. 2014,22(1):177-184. DI X G,JIN W X,YU Y. Digital video stabilization for large-scale moving foreground object and rotation jitter [J]. Opt. Precision Eng., 2014, 22(1):177-184. (in Chinese)

WEN D H, JIANG Y S, ZHANG Y D, et al.. Modified block-matching 3-D filter in Laplacian pyramid domain for speckle reduction [J]. Optics Communications,2014, 332(2):150-154.

AOYAMA S, ITO K, AOKI T. A finger knuckle print recognition algorithm using phase-based local block matching [J]. Information Sciences, 2014, 268(12):53-64.

ALAN A, HARIN S. Stego quality enhancement by message size reduction and fibonacci bit-plane mapping [J]. Lecture Notes in Computer Science, 2014, 8893(1):151-166.

AGRAWAL P,KHURSHID A. DWT and GA-PSO based novel watermarking for videos using audio watermark [J].Lecture Notes in Computer Science,2014,8795(1):212-220.

SCHULZE C, LIWICKI M. Optimized SIFT feature matching for image retrieval [J]. Lecture Notes in Computer Science, 2014, 1(1):102-115.

HERBERT B, ANDREAS E, TINNE T, et al..Speeded Up Robust Feature(SURF) [J].Computer Vision and Image Understanding(CVIU), 2008,110(3):346-359.

张从鹏,魏学光. 基于Harris角点的矩形检测[J]. 光学精密工程, 2014, 22(8):2259-2266. ZHANG C P, WEI X G. Rectangle detection based on Harris corner[J]. Opt. Precision Eng., 2014, 22(8):2259-2266. (in Chinese)

BIADGIE Y, SOHN K A. Feature detector using adaptive accelerated segment test [C]. International Conference on Information Science & Applications (ICISA), 2014:1537-1541.

FOTEINI P, NIKIFOROS M, OLGA P. A study on the use of a binary local descriptor and color extensions of local descriptors for video concept detection[J]. Lecture Notes in Computer Science, 2015, 8935(1):282-293.

LEUTENEGGER S, CHLI M, SIEGWART R Y. BRISK:Binary robust invariant scalable keypoints [C]. Proceedings of the 2011 IEEE International Conference on Computer Vision (ICCV), 2012:1589-1596.

林森,苑玮琦,宋辉. 二进制鲁棒不变尺度特征在非接触掌纹识别中的应用[J]. 仪器仪表学报. 2013,34(12):2785-2792. LIN S, YUAN W Q, SONG H. Application of binary robust invariant scalable keypoints in non-contact palmprint recognition [J].Chinese Journal of Scientific Instrument, 2013, 34(12):2785-2792. (in Chinese)

许允喜,蒋云良, 陈方. 惯性组合导航系统中基于BRISK的快速景象匹配算法[J]. 光电子·激光,2013,23(8):1589-1596. XU Y X, JIANG Y L, CHEN F. Rapid scene matching algorithm based on BRISK for inertial integrated navigation system [J]. Journal of Optoelectronics Laser, 2013, 23(8):1589-1596. (in Chinese)

张勇,王新赛,李明明,等. 鲁棒的车载红外视频电子稳像算法[J]. 强激光与粒子束,2013,25(4):853-857 ZHANG Y, WANG X S, LI M M, et al.. Robust infrared video electronic stabilization algorithm for vehicle [J]. High Power Laser and Particle Beams, 2013, 25(4):853-857. (in Chinese)

李刚,王赫. 机载光电平台实时图像消旋[J]. 液晶与显示,2014,29(2):304-309. LI G, WANG H. Real-time image rotation-elimination for airborne photoelectric platform [J]. Chinese Journal of Liquid Crystals and Displays, 2014, 29(2):304-309. (in Chinese)

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. CHEN F X, WANG R SH. Fast RANSAC with preview model parameters evaluation [J]. Journal of Software, 2005, 16(8):1431-1437. (in Chinese)

Views

327

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Binocular vision SLAM with fused point and line features in weak texture environment

Adaptive feature matching network for object occlusion

A visual SLAM algorithm based on adaptive inertial navigation assistant feature matching

Camera pose estimation based on 2D image and 3D point cloud fusion

Infrared-visible video automatic registration with contour feature matching

Related Author

GONG Kun

XU Xin

CHEN Xiaoqing

XU Yuelei

ZHANG Zhaoxiang

MAO Lin

SU Hongyang

YANG Dawei

Related Institution

National Innovation Institute of Defense Technology， Academy of Military Science

Unmanned System Research Institute， Northwestern Polytechnical University

School of Electromechanical Engineering， Dalian Minzu University

Geography Space Information Institute， Information Engineering University

College of Electronic and Information Engineering， 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