计算机科学 ›› 2016, Vol. 43 ›› Issue (8): 313-317.doi: 10.11896/j.issn.1002-137X.2016.08.064

• 图形图像与模式识别 • 上一篇    下一篇

基于仿射不变约束与快速EKF滤波的航拍图像稳像

易盟,楚岩   

  1. 长安大学电子与控制工程学院 西安710064,长安大学电子与控制工程学院 西安710064
  • 出版日期:2018-12-01 发布日期:2018-12-01
  • 基金资助:
    本文受国家自然科学基金(41372330),中央高校基本科研业务费专项资金(310832151097)资助

Aerial Video Image Stabilization Based on Affine Invariant Constraint and Fast EKF Adaptive Filter

YI Meng and CHU Yan   

  • Online:2018-12-01 Published:2018-12-01

摘要: 考虑到航拍机载成像平台抖动严重、视频稳像匹配环节精度不一致的特点以及航拍图像稳像技术快速、准确的要求,提出了一种结合仿射不变约束与快速扩展卡尔曼(Extend Kalman Filter,EKF)滤波的图像稳像算法。该算法首先以视频参考帧中的角点量作为特征点,通过Harris检测器选择出稳定角点;然后对待配准点构建Delaunay三角网进行初始匹配,提出利用仿射不变约束方法筛选出精确匹配点;最后利用快速EKF运动滤波方法实时估计和修正噪声的统计特性,从而解决摄像机扫描运动中存在的抖动问题。在对大量分辨率为640×480pixel的航拍图像的仿真实验中,可通过仿射不变约束实现精确的模型估计,采用的快速运动补偿方法在补偿过程中耗时为5.054ms,比传统的运动补偿方法节约了69.5%的时间。实验结果表明,该算法能够实时稳定航拍视频帧间的抖动现象,并能有效跟随场景的真实扫描。

关键词: 航拍图像,电子稳像,特征点,仿射不变约束,EKF运动滤波

Abstract: In view of serious jitter of aerial airborne imaging,different accuracies of obtained matching points in aerial video stabilization,and requirements of fast and precise aerial image stabilization technology,an image stabilization algorithm was proposed combining affine invariant constraint and Extend Kalman Filter (EKF) adaptive filter.Firstly,corners are detected from reference frame as feature points,the locally stable points are selected by the Harris detector.Then Delaunay triangulation is used to find initial matching,and the most accurate matching points which best satisfy the affine invariant constraint are filtered.Finally,EKF motion filter method is used to estimate and correct the statistical property of noise,so jitter of the camera can be removed but scanning motion can be retained simultaneously.As to a large number of simulation experiment of aerial images with a resolution of 640 pixel ×480 pixel,accurate model can be estimated by affine invariant constraints,the rapid motion compensation method takes 5.054 ms in the process of compensation,and saves for 69.5% than traditional motion compensation method.The experimental results illustrate that the proposed algorithm can stabilize the inter-frame jitter and track the real scene effectively.

Key words: Aerial video,Electronic image stabilization,Feature point,Affine invariant constraint,EKF motion filter

[1] Ratakonda K.Real-time digital video stabilization for multi-media applications[C]∥IEEE International Symposium on Circuits and Systems.1998:69-72
[2] Aysun A,Ertfürk S.Fast digital image stabilization using one bit transform based sub-image motion estimation[J].IEEE Tran-sactions on Consumer Electronics,2005,1(3):917-921
[3] Byrne J.Nested motion descriptors[C]∥2015 IEEE Conference on Computer Vision and Pattern Recogniton(CVPR).2015:502-510
[4] Yeong K,Chulwoo L,Chang K.Video stabilization based onfeauture trajectory augmentation and selection and robust mesh grid warping[J].IEEE Transactions on Image Processing,2015,24(12):5260-5273
[5] Chen Y,Lin H.Full-frame video stabilization via SIFT feature matching[C]∥2014 Tenth International Conference on Intelligent Information Hiding and Multimedia Signal Processing.2014:361-364
[6] Sung K,Lee S,Seung J.Fast digital image stabilizer based ongray-coded bit-plane matching[J].IEEE Transactions on Consumer Electronics,2009,5(3):598-603
[7] Shih Y Y,Su S F,Rudas I.Fuzzy based hand-shake compensation for image stabilization[C]∥2012 International Conference on System Science and Engineering.2012:1511-1521
[8] Jiang J G,Niu J J,Qi M B.Rotational video stablization algorithm based on SURF and trajectory smothing[J].Chinese Journal of Scientific Instrument,2014,4(13):743-748(in Chinese) 蒋建国,牛杰杰,齐美彬.基于SURF和轨迹滤波的旋转视频稳像算法[J].仪器仪表学报,2014,24(13):743-748
[9] Zhu J,Guo B.Electronic image stabilization system based on global feature tracking[J].Journal of Systems Engineering and Electronics,2008,9(2):228-233
[10] Dong K,Hong R.New image quality metric using the Harris response[J].IEEE Signal Processing Letters,2009,6(7):616-619
[11] Ming Z.A robust Delaunay triangulation matching for multispectral/multidate remote sensing image registration[J].IEEE Geoscience and Romote Sensing Letters,2015,2(4):711-715
[12] Hongsheng L.Object matching using a locally affine invariant and linear programming techniques.[J] IEEE Transactions on Pattern Analysis & Machine Intelligence,2013,5(2):411-424
[13] Houtekamer P,Herschel L.Ensemble kalman filtering[J].Quar-terly Journal of the Royal Meteorological Society,2006,131(613):3269-3289
[14] Lynn R,Alireza M K.Robust adaptive Kalman Filtering for systems with unknown step inputs and non-Gaussian measurement errors [J].IEEE Transactions on Acoustrics,1986,34(2):252-263
[15] Xu J S,Qin Y Y,Peng R.Adaptive kalman filter fading factor selection method research [J].Journal of Systems Engineering and Electronics,2004,26(11):1152-1154(in Chinese) 徐景硕,秦永元,彭蓉.自适应卡尔曼滤波器渐消因子选取方法研究[J].系统工程与电子技术,2004,26(11):1152-1154

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!