结合优化梯度滤波与投影不变的航拍视频配准

易盟; 郭宝龙; 严春满

doi:10.3788/OPE.20122003.0651

您当前的位置：

首页 >

文章列表页 >

结合优化梯度滤波与投影不变的航拍视频配准

信息科学 | 更新时间：2020-08-12

- 结合优化梯度滤波与投影不变的航拍视频配准
- Aerial video registration combining optimal gradient filters and projective invariant
- 光学精密工程 2012年20卷第3期页码：651-660
- 作者机构：
  
  西安电子科技大学机电工程学院智能控制与图像工程研究所,陕西西安,710071
- 作者简介：
- 基金信息：
  
  国家自然科学基金资助项目(No. 60802077)();国家杰出青年科学基金资助项目(No.61003196)()
- DOI：10.3788/OPE.20122003.0651
  中图分类号： TP391.41
- 收稿日期：2011-06-10，
  
  修回日期：2011-07-19，
  
  网络出版日期：2012-03-22，
  
  纸质出版日期：2012-03-22
- 稿件说明：
移动端阅览
易盟, 郭宝龙, 严春满. 结合优化梯度滤波与投影不变的航拍视频配准[J]. 光学精密工程, 2012,(3): 651-660

YI Meng, GUO Bao-long, YAN Chun-man. Aerial video registration combining optimal gradient filters and projective invariant[J]. Editorial Office of Optics and Precision Engineering, 2012,(3): 651-660
易盟, 郭宝龙, 严春满. 结合优化梯度滤波与投影不变的航拍视频配准[J]. 光学精密工程, 2012,(3): 651-660 DOI： 10.3788/OPE.20122003.0651.

YI Meng, GUO Bao-long, YAN Chun-man. Aerial video registration combining optimal gradient filters and projective invariant[J]. Editorial Office of Optics and Precision Engineering, 2012,(3): 651-660 DOI： 10.3788/OPE.20122003.0651.

摘要

考虑航拍视频配准中Harris检测的角点位置易发生偏移和产生伪角点以及匹配点精度不一致等问题

提出一种基于优化梯度滤波和投影不变的航拍视频配准算法。首先

提出一种基于优化梯度滤波的Harris检测器来实现角点的精确定位

并选择在尺度变化下局部区域最稳定的角点作为待配准点。然后

利用Delaunay三角网对待配准点进行初始匹配。最后

提出利用交比不变性方法提取精确度最高的少数匹配点

并对模型参数进行估计

完成视频帧间的配准。实验结果表明

利用提出的方法可实现帧间的精确配准

对分辨率为320 pixel240 pixel的8组航拍序列的平均几何保真度误差仅为0.869

并能有效提取地面运动目标。

Abstract

As the Harris detector can produce false and unstable corners

and obtained matching points have different accuracies in aerial video registration

an aerial video registration algorithm using optimal gradient filters and projective invariant was proposed. Firstly

a Harris detector based on optimal gradient filters was presented to determine the location of corners

and the locally most stable points were selected to be matching points. Then

the Delaunay triangulation was used to perform the initial matching. Finally

the most "useful" matching points that best satisfied the cross-ratio invariant were presented to estimate the geometry transformation and finish the image registration. Experiment results show that the proposed method by the optimal gradient filters and cross-ratio invariant can realize the registration between the frames

and the average geometric fidelity error is 0.869 for 8 sets of the unmanned video sequences with a resolution of 320 pixel?240 pixel. The method can capture moving objects effectively.

关键词

Keywords

references

ALI S, REILLY V, SNEDDON S. Motion and appearance contexts for tracking and reacquiring targets in aerial videos. IEEE CVPR, 2007: 1-6.[2] 王梅,屠大维,周许超. SIFT特征匹配和差分相乘融合的运动目标检测 [J].光学精密工程,2011,19(4):892-899. WANG M, TU D W, ZHOU X CH. Moving object detedtion by combining SIFT and differential multiplication[J]. Opt. Precision Eng., 2011,19(4):892-899. (in Chinese)[3] CHEN L CH, LIN L J. Detection of building changes from aerial images and light detection and ranging (LIDAR) data[J]. Journal of Applied Remote Sensing, 2010, 4(1):1-19.[4] JAYABALAN E, KRISHNAN A. Target tracking in aerial videos using image registration techniques[J]. Communications in Computer and Information Science, 2011, 142(3): 475-477.[5] XAOO J J, YANG CH J, HAN F, et al.. Vehicle and person tracking in aerial videos[J]. Lecture Notes in Computer Science, 2008, 4625(1):203-124.[6] 王会峰,刘上乾,汪大宝,等. 基于序列图像特征配准的摄像机旋转补偿算法 [J].光学精密工程,2008,16(7):1330-1334. WANG H F, LIU SH Q,WANG D B,et al.. Video camera rotation compensation algorithm based on feature matching of sequence image frames[J]. Opt. Precision Eng., 2008,16(7):1330-1334. (in Chinese)[7] CLARK F O, ADNAN I A, CURTIS W. Robust registration of aerial image sequences[J]. Lecture Notes in Computer Science, 2009, 5(4): 325-334.[8] 凌志刚,梁彦,程咏梅,等. 一种稳健的多源遥感图像特征配准方法 [J].电子学报, 2010,38(12):2892-2897. LING ZH G, LIANG Y, CHENG Y M, et al.. A robust multi-source remote-sensing Image registration method based on feature matching[J]. Acta Electronica Sinica, 2010, 38(12):2892-2897. (in Chinese)[9] 葛永新, 杨丹, 雷明. 基于良分布的亚像素定位角点的图像配准[J].电子与信息学报, 2010,32(2): 427-432. GE Y X, YANG D, LEI M. Image registration based on well-distributed corners with sub-pixel localization[J].Journal of Electronics & Information Technology, 2010, 32(2): 427-432. (in Chinese)[10] SONG ZH L, LI SH, THOMAS F. Remote sensing image registration approach based on a retrofitted SIFT algorithm and Lissajous-curve trajectories[J]. Optics Express, 2010, 18(2): 513-522.[11] HANY F, EERO P. Differentiation of discrete multi-dimensional signals[J]. IEEE Transctions on Image Processing, 2004,13(4):496-508.[12] HARRIS C, STEPHENS M J. A combined corner and edge detector. Proc. Fourth Alvey Vision Conference, 1988: 147-152.[13] BROWN M, SZELISKI R, WINDER S. Multi-image matching using multi-scale oriented patches.Proceeding of the International Conference on Computer Vision and Pattern Recognition, San Diego, 2005:510-517.[14] FISCHLER M A, BOLLES R C. Random sample consensus: Aparadigm for model fitting with applications to image analysis and automated cartography. Communications of ACM, 1981, 24(6): 381-395.[15] MUNDY J L, HELLER A. Geometric Invariance in Computer Vision[M]. Cambridge, MA: MIT Press, 1992.

浏览量

381

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

变分近似解算KL散度红外可见光遥感图像配准

多光谱图像融合的IC器件表面缺陷检测

双层平板探测的双能成像检测系统

基于相位特征的可见光和SAR遥感图像自动配准

采用轮廓特征匹配的红外-可见光视频自动配准