[an error occurred while processing this directive] [an error occurred while processing this directive] [an error occurred while processing this directive]
[an error occurred while processing this directive]

弹箭与制导学报 >

2022 , Vol. 42 >Issue 5: 20 - 26

DOI: https://doi.org/10.15892/j.cnki.djzdxb.2022.05.005

一种基于协方差矩阵的快速抗旋转景象匹配算法

  • 符艳军 1 ,
  • 孙开锋 2 ,
  • 刘军兰 1
展开
  • 1 西安外事学院工学院,西安 710077
  • 2 西安精密机械研究所,西安 710077

符艳军(1972—),女,陕西兴平人,副教授,博士,研究方向:图像处理、视觉导航。

收稿日期: 2021-11-17

  网络出版日期: 2025-01-16

基金资助

陕西省自然科学基金(2020JM-637)

西安外事学院高层次人才启动基金(XAIU2019011)

收起

A Fast Anti-rotation Scene Matching Algorithm Based on Covariance Matrix

  • FU Yanjun 1 ,
  • SUN Kaifeng 2 ,
  • LIU Junlan 1
Expand
  • 1 College of Engineering, Xi’an International University, Xi’an 710077, China
  • 2 Xi’an Precision Machinery Research Institute, Xi’an 710077, China

Received date: 2021-11-17

  Online published: 2025-01-16

Fold

摘要

针对无人机景象匹配导航系统对匹配算法的实时性和鲁棒性的要求,以协方差矩阵最小特征值为匹配算法的相似性测度,提出了一种改进的匹配算法。仿真结果表明,实时性方面,通过在离线方式下预先建立基于基准图的累加和矩阵,使协方差矩阵的在线计算量减少50%左右;抗旋转方面,对基准子图采用基于虚拟圆索引的快速圆形窗口定位算法,可以抵抗实测图5°~10°左右的旋转变化。该方法不仅在实时性、抗旋转方面有所改善,对实测图存在噪声干扰、小范围遮挡及小比例变化也有一定的鲁棒性。

关键词： 景象匹配; 协方差矩阵; 最小特征值; 实时性; 抗旋转

本文引用格式

符艳军 , 孙开锋 , 刘军兰 . 一种基于协方差矩阵的快速抗旋转景象匹配算法[J]. 弹箭与制导学报, 2022 , 42(5) : 20 -26 . DOI: 10.15892/j.cnki.djzdxb.2022.05.005

Abstract

Aiming at the real-time and robust requirements of UAV scene matching navigation system, an improved matching algorithm is proposed based on the minimum eigenvalue of covariance matrix. In terms of real-time performance, by pre-establishing the summation matrix based on the reference image in offline mode, the online calculation of covariance matrix is reduced by about 50% in the matching process. In the aspect of anti-rotation, the fast circle window positioning algorithm based on virtual circle index is used for the reference sub image, which can resist the real-time image with 5°~10° rotation. The simulation results show that the proposed method not only improves the real-time performance and anti-rotation, but also has certain robustness to the noise interference, small range occlusion and small scale transform of the actual image.

Key words： scene matching; covariance matrix; minimum eigenvalue; real-time; anti-rotation

[an error occurred while processing this directive]

参考文献

原文顺序 | 文献年度倒序 | 文中引用次数倒序
[1]
朱永松, 国澄明. 基于相关系数的相关匹配算法的研究[J]. 信号处理, 2003, 19(6):531-534.

[2]
宋文平, 张斌, 牛常领, 等. 一种融合最小二乘和相位相关的粗匹配纠正算法[J]. 遥感技术与应用, 2019, 34(6):1296-1304.

DOI

[3]
马永杰, 龚影, 陈敏. 基于归一化互相关匹配算法和Kalman预测器的目标跟踪[J]. 激光与光电子学进展, 2020, 57(18):241-248.

[4]
邹志远, 安博文, 曹芳. 基于红外面阵传感器的图像拼接算法[J]. 传感器与微系统, 2015, 34(1):128-130.

[5]
朱明, 姚强, 唐俊, 等. 超图约束和改进归一化互相关方法相结合的图像配准算法[J]. 国防科技大学学报, 2019, 41(3):50-55.

[6]
GAIDHANE V H, HOTE Y V, SINGH V. An efficient similarity measure technique for medical image registration[J]. Sadhana, 2012, 37(6): 709-721.

[7]
GAIDHANE V H, HOTE Y V, SINGH V. Nonrigid image registration using efficient similarity measure and Levenberg-Marquardt optimization[J]. Biomedical Engineering Letters, 2012(2): 118-123.

[8]
TSAI D M, YANG R H. An eigenvalue-based similarity measure and its application in defect detection[J]. Image & Vision Computing, 2005, 23(12): 1094-1101.

[9]
SUN T H, LIU C S, TIEN F C. Invariant 2D object recognition using eigenvalues of covariance matrices, re-sampling and autocorrelation[J]. Expert Systems with Applications, 2008, 35(4): 1966-1977.

[10]
LING J G, LIU E Q, LIANG H Y, et al. Infrared target tracking with kernel-based performance metric and eigenvalue-based similarity measure[J]. Applied Optics, 2007, 46(16): 3239-3252.

PMID

[11]
GAIDHANE V H, HOTE Y V, SINGH V. A computationally efficient approach for template matching-based image registration[J]. Sadhana, 2014, 39(2): 317-331.

[12]
陈彬, 陈和平, 李晓卉. 基于GPU的高效图像协方差矩阵算法与实现[J]. 计算机工程与设计, 2014, 35(12):4238-4242.

[13]
纪华, 王大伟, 赵建, 等. 协方差矩阵在目标二维姿态测量中的应用[J]. 光学精密工程, 2009, 17(11):2835-2841.

[14]
符艳军, 程咏梅, 潘泉, 等. 基于自适应极坐标变换的景象匹配算法[J]. 西北工业大学学报, 2011, 29(5):702-708.

Options
文章导航

/

〈 〉

[an error occurred while processing this directive]