[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]
导弹与制导技术

一种新的基于SIFT算法的景象匹配制导方法

  • 薛鹏 ,
  • 陆晓飞 ,
  • 董文锋 ,
  • 罗威 ,
  • 王良斯
展开
  • 空军预警学院,武汉 430019

薛鹏(1993-),男,陕西宝鸡人,硕士研究生,研究方向:电子对抗装备与技术。

收稿日期: 2017-06-21

  网络出版日期: 2025-05-30

A Novel Scene Matching Guidance Method Based on SIFT Algorithm

  • XUE Peng ,
  • LU Xiaofei ,
  • DONG Wenfeng ,
  • LUO Wei ,
  • WANG Liangsi
Expand
  • Air Force Early Warning Academy, Wuhan 430019, China

Received date: 2017-06-21

  Online published: 2025-05-30

摘要

为有效提高景象匹配制导的性能,在SIFT算法的基础上,结合Canny算子边缘特征检测对其进行改进,提出了一种新的Canny-SIFT算法。先利用Canny算子获取图像的边缘特征,再用SIFT算法对边缘特征图像进行匹配。仿真结果表明,Canny-SIFT算法对亮度、旋转和尺度变化不敏感,有效克服了SIFT算法匹配时间较长的弊端,在大幅提升匹配速度的同时可以提取到更多匹配特征点,提高了匹配正确率,改善了整个景象匹配制导系统的性能。

本文引用格式

薛鹏 , 陆晓飞 , 董文锋 , 罗威 , 王良斯 . 一种新的基于SIFT算法的景象匹配制导方法[J]. 弹箭与制导学报, 2018 , 38(3) : 55 -57,66 . DOI: 10.15892/j.cnki.djzdxb.2018.03.013

Abstract

In order to improve the performance of scene matching guidance a novel Canny-SIFT algorithm is proposed based on Scale Invariant Feature Transform (SIFT) algorithm. The edge feature of the image is obtained by Canny operator, and the edge feature image is matched by SIFT algorithm. The Canny operator is used to extract the edge feature of image at first. Then, the edge feature image is utilized to realize matching. The simulation results indicate that the Canny-SIFT algorithm is insensitive to the change of brightness, rotation and scale, which effectively overcomes the long matching time of SIFT algorithm. More matching feature points can be extracted when the matching speed is greatly improved, and thus the matching accuracy is improved and the performance of the whole scene matching guidance system is improved.

[an error occurred while processing this directive]

参考文献

[1]
孙继银, 孙向东, 王忠,等. 前视红外景象匹配技术[M]. 北京: 科学出版社, 2011: 1-4.
[2]
李言俊, 张科. 景象匹配与目标识别技术[M]. 西安: 西北工业大学出版社, 2009: 166-167.
[3]
LOWED G. Object recognition from local scale-inwariant features[C] //EICC. Proceedings of Seventh IEEE International Conference on Computer Vision. Los Alamitos: IEEE, 1999: 1150.
[4]
MIKOLAJCZY K, SCHMID C. A perfomance evaluation of local descriptors[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1615-4630.
[5]
DUAN C, MENG X, TU C, et al. How to make local image features more efficient and distinctive[J]. IET Computer Vision, 2008, 2(3): 178-189.
[6]
KE Yan, SUKTHANKAR R. PCA - SIFT: a more distinctive representation for local image descriptors[C] // IEEE Computer Society. Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEEE, 2004: 506-513.
[7]
CANNY J. A Computational Approach to Edge Detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, DAMI-8(6): 679-698.
[8]
吴翔, 于微波, 马艳辉,等. 一种新的改进 Canny 图像边缘检测算法[J]. 影像科学与光化学, 2016, 34(1): 116-121.
[9]
DAVID G. LOWE. Distinctive Image Features from Scale-Invariant Keypoints[J]. Journal of Computer Vision, 2004 60(2): 91-110.
[10]
苏培峰, 黄世奇, 王艺婷,等. 用图像矩特征描述的SIFT 特征 SAR图像配准[J]. 电光与控制, 2016, 23(8): 89-91.
文章导航

/

[an error occurred while processing this directive]