高精度全景补偿电子稳像

吴威; 许廷发; 王亚伟; 闫辉; 徐磊

doi:10.3788/CO.20130603.0378

高精度全景补偿电子稳像

doi: 10.3788/CO.20130603.0378

北京理工大学光电学院光电成像技术与系统教育部重点实验室, 北京 100081

基金项目:

国家自然科学基金重点资助项目(科学仪器专项)(No.61027002);国家重点基础研究发展计划(973计划)资助项目(No.2009CB72400603);国家自然科学基金资助项目(No.60972100)

详细信息

作者简介:
吴威(1988-),男,安徽六安人,硕士研究生,2010年于中北大学获得学士学位,主要从事图像处理与电子稳像软件算法及硬件实现的研究。E-mail:wu3944387@163.com;许廷发(1968-),男,黑龙江肇东人,教授,博士生导师,1992年、2000年于东北师范大学分别获得学士、硕士学位,2004年于中国科学院长春光学精密机械与物理研究所获得博士学位,[JP2]主要从事光电成像探测与识别等方面的研究。E-mail:ciom_xtf1@bit.edu.cn

吴威(1988-),男,安徽六安人,硕士研究生,2010年于中北大学获得学士学位,主要从事图像处理与电子稳像软件算法及硬件实现的研究。E-mail:wu3944387@163.com;许廷发(1968-),男,黑龙江肇东人,教授,博士生导师,1992年、2000年于东北师范大学分别获得学士、硕士学位,2004年于中国科学院长春光学精密机械与物理研究所获得博士学位,[JP2]主要从事光电成像探测与识别等方面的研究。E-mail:ciom_xtf1@bit.edu.cn

通讯作者:
许廷发

中图分类号: TN941.1
计量
- 文章访问数: 2644
- HTML全文浏览量: 384
- PDF下载量: 919
- 被引次数: 0
出版历程
- 收稿日期: 2013-03-12
- 修回日期: 2013-05-17
- 刊出日期: 2013-06-10

High precision digital image stabilization with full frame compensation

Key Laboratory of Photo Electronic Imaging Technology and System of the Ministry of Education, School of Optics and Electronics, Beijing Institute of Technology, Beijing 100081, China

摘要

摘要: 针对摄像机拍摄目标过程中自身的随机抖动造成的视频序列不稳定,以及稳像补偿过程中边缘信息的丢失,提出了基于SURF(Speed-up Robust Feature)算法的全景电子稳像方法。首先,运用SURF算法提取当前帧图像和参考帧图像的兴趣点,将两幅图像的兴趣点进行匹配,建立两帧的对应关系。针对兴趣点数目较少及场景中部分区域特征相似的情况,引入了兴趣点位移一致性抑制策略,改进了RANSAC(RANdom SAmple Consensus)误匹配的剔除算法,使得运动矢量的精确度小于1 pixel。然后,判定参考帧的更新策略,获取平滑的运动变量。最后,进行运动补偿,运用图像镶嵌技术对丢失的边缘区域信息进行全景补偿,得到了高精度的全景稳像结果,实验得到的输出视频峰值信噪比(PSNR)提高了33.1%。
- 电子稳像 /
- SURF算法 /
- 全景补偿 /
- 兴趣点位移 /
- 峰值信噪比
Abstract: To overcome the instability of the video sequences caused by the undesirable shakes of a camera, and to reduce the missing of edge information in the process of compensation, a full-frame video stabilization system based on the Speed-Up Robust Feature(SURF) was proposed. Firstly, the SURF was employed to extract the features in the images of the current and the reference frames and to match the features between the two images, so that the correspondence could be established. As a few features were extracted and the features of some areas in the scene were similar, a method of consistency restrain of the features' displacement was proposed to ameliorate the RANSAC. The motion vector precision is less than 1 pixel. Secondly, by determining the reference frame update strategy, the smoothed inter-frame global motion vector was obtained. Finally, mosaic was used to implement the motion compensation, and the corresponding pixels of the reference frame were filled with a stabilized frame to compensate the unstable motion and to output a stabilized full frame video. The Peak Signal to Noise Ratio(PSNR) is improved by 33.1 percent.
- digital image stabilization /
- SURF algorithm /
- full frame compensation /
- feature displacement /
- Peak Signal to Noise Ratio(PSNR)

HTML全文

参考文献(1)

[1] 赵红颖,金宏,熊经武.电子稳像技术概述[J]. 光学精密工程,2001,9(4):353-359. ZHAO H Y,JIN H,XIONG J W. Overview of the electronic image stabilization technology[J]. Opt. Precision Eng.,2001,9(4):353-359.(in Chinese) [2] KIM J H,BYUN K Y,KO S J. Highly precise digital image stabilization scheme for a hybrid stabilizing system[J]. Opt. Eng.,2010,49(7):61-67. [3] LIU J,SHI C CH. Image stabilization based on BM-EMD [C]//Communication Software and Networks(ICCSN),2011 IEEE 3rd International Conference on,May 27-29,2011,Xi'an,China,2011:591-593. [4] 孙辉,李志强,孙丽娜,等. 基于相位相关的亚像素配准技术及其在电子稳像中的应[J]. 中国光学,2010,3(5):480-485. SUN H,LI ZH Q,SUN L N,et al.. Sub-pixel registration based on phase correlation and its application to electronic image stabilization\[J]. Chinese Optics,2010,3(5):480-485.(in Chinese) [5] 王鹏,赵跃进,孔令琴,等. 预测扫描提前跳转的电子稳像方法[J]. 光学精密工程,2012,20(10):2268-2274. WANG P,ZHAO Y J,KONG L Q,et al.. Scanning image stabilizing algorithm:predicting scanning motion and jumping in advance[J]. Opt. Precision Eng.,2012,20(10):2268-2274.(in Chinese) [6] DAVID G L. Distinctive image features from scale-Invariant keypoints[J]. International J. Computer Vision,2004,60(2):91-110. [7] BAY HE,TUYTELAARS T,GOOL L V. SURF:speeded up robust features [EB/OL].(2010-05-06) [2013-02-13].http://www.computerrobotvision.org/2010/tutorial-day/tam-surf-rev3.pdf. [8] 阳吉斌,胡访宇,朱高. 基于改进SURF算法的遥感图像配准[J]. 电子测量技术,2012,35(3):69-72. YANG J B,HU F Y,ZHU G. Remote sensing image registration based on improved SURF[J]. Electronic Measurement Technology,2012,35(3):69-72.(in Chinese) [9] 张淼,郭成娇,李向阳,等. 基于SIFT和卡尔曼滤波的电子稳像技术研究[J]. 信息技术,2012,3:60-64. ZHANG M,GUO CH J,LI X Y,et al.. Digital image stabilization based on SIFT and Kalman filtering[J]. Information Technology,2012,3:60-64.(in Chinese) [10] 丁南南,刘艳滢,朱明.尺度相互作用墨西哥帽小波提取图像特征点[J]. 液晶与显示,2012,27(1):125-129. DING N N,LIU Y Y,ZHU M. Extracting image feature points using scale-unteraction of mexican-Hat Wavelets[J]. Chinese J. Liquid Crystals and Display,2012,27(1):125-129.(in Chinese). [11] SONG CH H,ZHAO H,JING W,et al.. Robust video stabilization based on particle filtering with weighted feature points[J]. IEEE T. Consum. Electr.,2012,58(2):570-577. [12] 程明明,王贺,安平,等.基于特征点匹配的多视图像校正[J]. 液晶与显示,2010,25(4):593-597. CHENG M M,WANG H,AN P,et al.. Multi-view images rectification based on feature points matching[J]. Chinese J. Liquid Crystals and Display,2010,25(4):593-597. [13] PINTO B,ANURENJAN P R. Video stabilization using speeded up robust features [C]//Communications and Signal Processing(ICCSP), International Conference on,Feb.10-12,2011,Calicut,IND,2011:527-531. [14] 李英,李静宇,徐正平.结合SURF与聚类分析方法实现运动目标的快速跟踪[J]. 液晶与显示,2011,26(4):544-550. LI Y,LI J Y,Xu ZH P. Moving target fast tracking using SURF and cluster analysis method[J]. Chinese J. Liquid Crystals and Display,2011,26(4):544-550.(in Chinese) [15] 张坤,许廷发,王平,等. 高精度实时全帧频SURF电子稳像方法[J]. 光学精密工程,2011,8(19):1964-1970. ZHANG K,XU T F,WANG P,et al.. Real time full frame digital image stabilization system by SURF[J]. Opt. Precision Eng.,2011,8(19):1964-1970.(in Chinese) [16] 王智慧,王敬东,李鹏,等. 一种基于KLT-RANSAC全局运动估计的电子稳像算法研究[J]. 光电子技术,2012,32(1):46-51. WANG ZH H,WANG J D,LI P,et al.. Research on electronic image stabilization based on KLT-RANSAC global motion estimation[J]. Optoelectronic Technology,2012,32(1):46-51. [17] MATSUSHITA Y,OFEK E,GE W N,et al.. Full-frame video stabilization with motion inpainting[J]. IEEE T. Pattern Anal.,2006,7(28):1150-1163. [18] 王思珺,赵建,韩希珍.基于仿射变换的快速全局运动估计算法[J]. 液晶与显示,2012,27(2):263-266. WANG S J,ZHAO J,HAN X ZH. Fast global motion estimation algorithm based on affine transformation[J]. Chinese J. Liquid Crystals and Display,2012,27(2):263-266 [19] 邱家涛,李玉山,初秀琴,等..稳定运动物体视频的特征方法[J]. 光学精密工程,2012,20(10):2300-2307. QIU J T,LI Y SH,CHU X Q,et al.. Feature-based approach for stabilizing videos with moving objects[J]. Opt. Precision Eng.,2012,20(10):2300-2307.(in Chinese)

施引文献

附加信息(0)

访问统计