基于背景特征点匹配的视频稳像

doi:10.13229/j.cnki.jdxbgxb201606048

吉林大学学报(工学版) ›› 2016, Vol. 46 ›› Issue (6): 2116-2122.doi: 10.13229/j.cnki.jdxbgxb201606048

基于背景特征点匹配的视频稳像

吉淑娇¹, 雷艳敏¹, 朱明²

1.长春大学电子信息工程学院,长春 130022;
2.中国科学院大学长春光学精密机械与物理研究所,长春 130033

收稿日期:2015-06-01 出版日期:2016-11-20 发布日期:2016-11-20
通讯作者: 朱明(1964-),男,研究员,博士生导师.研究方向:图像处理,光电检测技术及电视跟踪技术.
作者简介:吉淑娇(1978-),女,讲师,博士.研究方向:视频图像处理,电子稳像.E-mail:shujiaoji@163.com
基金资助:
吉林省教育厅项目(2015LY502L11); 吉林省科技发展计划项目(20140101084JC)

Video stabilization based on background feature points

JI Shu-jiao¹, LEI Yan-min¹, ZHU Ming²

1.College of Electronic Information and Engineering, Changchun University, Changchun 130022,China;
2.Changchun Institute of Optics, Fine Mechanics and Physics, University of Chinese Academy of Sciences, Changchun 130033,China

Received:2015-06-01 Online:2016-11-20 Published:2016-11-20

摘要/Abstract

摘要： 针对特征点在前景运动物体上会严重影响运行矢量准确性的问题,本文提出利用特征点分类的方法,通过计算KLT跟踪特征点,计算运动估计所得匹配点跟踪所得特征点之间的距离,并由MSAC算法不断更新前景特征点和背景特征点集,最后仅采用背景上的特征点进行全局运动估计,从而进行稳像。实验结果表明,本文方法稳像后视频平滑度更高,而且本算法的无定义区域明显减少,更利于人眼视觉感受。

关键词: 信息处理技术, 电子稳像, 背景特征, 运动补偿

Abstract: The objective of this paper is to stabilize electronic image for aerial video with dynamic background. When shooting, as the camera follows the target, the video sequence changes scenarios. This is due to the movement of the camera and the change of background, so the scene is complicated. The difficulties in stabilizing video image with dynamic background include: an accurate estimate motion vector of camera movement and background compensation. To overcome such difficulties, this paper uses KLT track operator in combination with the M-estimator Sample and Consensus (MSAC) algorithm to realize feature point classification. Then, only the feature points on the background are used for global motion estimation to perform image stabilization. Experimental results demonstrate the feasibility of the proposed method.

Key words: information processing technology, electronic image stabilization, background characteristics, motion compensation

中图分类号:

TN941.1

吉淑娇, 雷艳敏, 朱明. 基于背景特征点匹配的视频稳像[J]. 吉林大学学报(工学版), 2016, 46(6): 2116-2122.

JI Shu-jiao, LEI Yan-min, ZHU Ming. Video stabilization based on background feature points[J]. 吉林大学学报(工学版), 2016, 46(6): 2116-2122.

参考文献

[1] 吉淑娇,朱明,胡汉平. 基于特征点匹配的电子稳像算法综述[J].中国光学,2013,6(6):841-849.
Ji Shu-jiao, Zhu Ming, Hu Han-ping. Aero-borne electronic image stabilization based on feature point matching[J].Chinese Optics,2013, 6(6): 841-849.
[2] Ryu Y G, Chung M J. Robust online digital image stabilization based on point-feature trajectory without accumulative global motion estimation[J]. IEEE Signal Processing Letters, 2012,19(4):223-226.
[3] 吉淑娇,朱明,雷艳敏,等.基于改进运动矢量估计法的视频稳像[J]. 光学精密工程,2015,23(5):254-261.
Ji Shu-jiao, Zhu Ming, Lei Yan-min.et al. Video stabilization with improved motion vector estimation[J].Opt Precision Eng, 2015,23(5):254-261.
[4] Kim S K, Kang S J, Wang T S, et al. Feature point classification based global motion estimation for video stabilization[J]. IEEE Transactions on Consumer Electronics, 2013(3):267-272.
[5] 朱齐丹,徐从营,蔡成涛. 船载这反射全景试卷系统电子稳像算法[J].吉林大学学报:工学版,2015,45(4):1288-1296.
Zhu Qi-dan,Xu Cong-ying, Cai Cheng-tao. Electronic image stabilization algorithm for on board catadioptric omnidirectional vision system[J].Journal of Jilin University(Engineering and Technology Edition), 2015,45(4):1288-1296.
[6] Choi K S, Lee J S, Kim J W, et a1.An efficient digital image stabilizing technique for mobile video ommunications[C]∥International Conference on Consumer Electronics,Berlin,2000:246-247.
[7] 吉淑娇.基于特征匹配的机载电子稳像技术研究[D].长春:中国科学院大学长春光学精密机械与物理研究所,2015.
Ji Shu-Jiao.Airborne electronic image stabilization technology based on feature points[D].Changchun:Changchun Institute of Optics, Fine Mechanics and Physics, University of Chinese Academy of Sciences,2015.
[8] Torr P, Murray D. The development and comparison of robust methods for estimating the fundamental matrix[J]. International Journal of Computer Vision,1997, 24(3): 271-300.
[9] Torr P H S, Zisserman A. Robust computation and parametrization of multiple view relations[C]∥International Conference of Computer Vision,Bombay,1998:727-732.
[10] Torr P H S, Zisserman A. MLESAC: a new robust estimator with application to estimating image geometry[J].Computer Vision and Image Understanding,2000, 78(1): 138-156.
[11] Wang H, Gregory D M, Hager D. A generalized kernel consensus based robust estimator[J].IEEE Transactions on Analysis and Machine Intelligence, 2010,32(1):178-184.
[12] Subbarao R, Meer P. Beyond RANSAC: user independent robust regression[C]∥Conference on Computer Vision and Pattern Recognition Workshop, New York,2006:101-108.
[13] Ji Shu-jiao,Zhu Ming,Lei Yan-min. Video stabilization algorithm based on background feature points matching[C]∥International Conference on Sensors Measurement and Intelligent Materials,Shanghai,China,2015: 690-693.
[14] 严洁, 阮友田, 薛珮瑶. 主被动光学图像融合技术研究[J]. 中国光学, 2015,8(3): 378-385.
Yan Jie, Ruan You-tian, Xue Pei-yao. Active and passive optical image fusion technology[J]. Chinese Optics, 2015,8(3): 378-385.
[15] 孙寿健, 魏立线, 刘佳, 等. 一种基于权重融合的JPEG隐写分析方法[J]. 液晶与显示, 2015, 30(2): 326-332.
Sun Shou-jian, Wei Li-xian, Liu Jia, et al. A rights-based re-integration method for JPEG steganalysis[J]. Chinese Journal of Liquid Crystal and Displays, 2015, 30(2): 326-332.
[16] 朴永杰, 徐伟, 王绍举,等. 高动态范围视频的多曝光图像序列快速融合[J]. 液晶与显示, 2014, 29(6):1032-1041.
Piao Yong-jie, Xu Wei, Wang Shao-ju, et al. Fast multi-exposure image fusion for HDR video[J]. Chinese Journal of Liquid Crystal and Displays, 2014, 29(6):1032-1041.
[17] 柯洪昌, 孙宏彬,. 图像序列的显著性目标区域检测方法[J]. 中国光学, 2015,8(5): 768-774.
Ke Hong-chang, Sun Hong-bin. A saliency target area detection method of image sequence[J]. Chinese Optics, 2015,8(5): 768-774.

相关文章 15

[1]	苏寒松,代志涛,刘高华,张倩芳. 结合吸收Markov链和流行排序的显著性区域检测[J]. 吉林大学学报(工学版), 2018, 48(6): 1887-1894.
[2]	徐岩,孙美双. 基于卷积神经网络的水下图像增强方法[J]. 吉林大学学报(工学版), 2018, 48(6): 1895-1903.
[3]	黄勇,杨德运,乔赛,慕振国. 高分辨合成孔径雷达图像的耦合传统恒虚警目标检测[J]. 吉林大学学报(工学版), 2018, 48(6): 1904-1909.
[4]	李居朋,张祖成,李墨羽,缪德芳. 基于Kalman滤波的电容屏触控轨迹平滑算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1910-1916.
[5]	应欢,刘松华,唐博文,韩丽芳,周亮. 基于自适应释放策略的低开销确定性重放方法[J]. 吉林大学学报(工学版), 2018, 48(6): 1917-1924.
[6]	陆智俊,钟超,吴敬玉. 星载合成孔径雷达图像小特征的准确分割方法[J]. 吉林大学学报(工学版), 2018, 48(6): 1925-1930.
[7]	刘仲民,王阳,李战明,胡文瑾. 基于简单线性迭代聚类和快速最近邻区域合并的图像分割算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1931-1937.
[8]	单泽彪,刘小松,史红伟,王春阳,石要武. 动态压缩感知波达方向跟踪算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1938-1944.
[9]	姚海洋, 王海燕, 张之琛, 申晓红. 双Duffing振子逆向联合信号检测模型[J]. 吉林大学学报(工学版), 2018, 48(4): 1282-1290.
[10]	全薇, 郝晓明, 孙雅东, 柏葆华, 王禹亭. 基于实际眼结构的个性化投影式头盔物镜研制[J]. 吉林大学学报(工学版), 2018, 48(4): 1291-1297.
[11]	陈绵书, 苏越, 桑爱军, 李培鹏. 基于空间矢量模型的图像分类方法[J]. 吉林大学学报(工学版), 2018, 48(3): 943-951.
[12]	陈涛, 崔岳寒, 郭立民. 适用于单快拍的多重信号分类改进算法[J]. 吉林大学学报(工学版), 2018, 48(3): 952-956.
[13]	孟广伟, 李荣佳, 王欣, 周立明, 顾帅. 压电双材料界面裂纹的强度因子分析[J]. 吉林大学学报(工学版), 2018, 48(2): 500-506.
[14]	林金花, 王延杰, 孙宏海. 改进的自适应特征细分方法及其对Catmull-Clark曲面的实时绘制[J]. 吉林大学学报(工学版), 2018, 48(2): 625-632.
[15]	王柯, 刘富, 康冰, 霍彤彤, 周求湛. 基于沙蝎定位猎物的仿生震源定位方法[J]. 吉林大学学报(工学版), 2018, 48(2): 633-639.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于背景特征点匹配的视频稳像

Video stabilization based on background feature points

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 10