期刊文献+

基于局部哈希学习的大面阵CCD航拍图像匹配方法 预览

Matching method of large array CCD aerial images based on local hashing learning
在线阅读 下载PDF
分享 导出
摘要 为实现大面阵CCD航拍图像准确快速匹配,提出一种局部多特征哈希学习LMFH(local multi-feature hashing)方法。依据航向重叠率构建预测区域,在预测区域内检测特征点并进行多特征描述,以现有上万幅航拍图像为训练样本,通过哈希函数将高维的特征描述向量映射为紧凑的二进制哈希编码,在汉明空间通过汉明距离实现特征点的快速匹配。实验结果表明,相对于SURF算子,LMFH算法在准确度上提高了10%,匹配时间上减少了0.2s。LMFH算法可更快更准确地实现CCD航拍图像的匹配。 In order to realize the fast and accurate matching of large array charge coupled-device(CDD)aerial images,a local multi-feature hashing(LMFH)method is proposed.Firstly,the prediction area is constructed according to the course overlap rate,and the feature points detected in the area are described by multi-feature.Then,the hash functions are learned by tens of thousands of existing aerial images.Finally,the high-dimensional feature description vectors are mapped to compact binary hash codes by the learned hash functions.Fast hashing matching is achieved according to the Hamming distance in the Hamming space.Experiments show that compared to the classical speeded up robust features(SURF)algorithm,accuracy is improved about 10%,meanwhile,the matching time is decreased 0.2 s.The proposed LMFH algorithm for aerial images matching is much more efficient.
作者 陈苏婷 郭子烨 张艳艳 CHEN Suting;GUO Ziye;ZHANG Yanyan(Jiangsu Key Laboratory of Meteorological Detection and Information Processing,Nanjing university of Information Science and Technology,Nanjing 210044,China)
出处 《应用光学》 CAS CSCD 北大核心 2019年第2期259-264,共6页 Journal of Applied Optics
基金 国家自然科学基金(61705109).
关键词 CCD航拍图像 特征匹配 局部哈希学习 快速匹配 CCD aerial images feature matching local hash learning fast matching
作者简介 陈苏婷(1980-),女,博士,教授,主要从事图像处理与机器学习研究。E-mail:sutingchen@nuist.edu.cn.
  • 相关文献

参考文献7

二级参考文献62

  • 1焦李成,谭山.图像的多尺度几何分析:回顾和展望[J].电子学报,2003(z1):1975-1981. 被引量:195
  • 2闫乐乐,李辉,邱聚能,梁平,.基于区域对比度和SSIM的图像质量评价方法[J].应用光学,2015,0(1):58-63. 被引量:6
  • 3陈昕,向健勇.不变性理论用于空中目标的识别[J].红外与毫米波学报,1997,16(1):39-44. 被引量:16
  • 4Zitova B, Flusser J. Image registration methods: a survey [J ]. Image and Vision Computing, 2003,21 : 977-1000. 被引量:1
  • 5De Maesschalck R,Jouan - Rimbaud D, Massart D L, et al. The mahalanobis distance[J ]. Chemometrics and Intelligent Laboratory Systems, 2000,50(1 ) : 1-18. 被引量:1
  • 6Harris C,Stephens M. A combined comer and edge detector [ C] //Proceedings of the Fourth Alvey Vision Conference. Manchester: the University of Sheffield Printing Unit, 1988:147-151. 被引量:1
  • 7Smith S, Susan J B. A New Approach to low-level Image Processing [J]. International Journal of Computer Vision (S0920-5691), 1997, 23(1): 45-78. 被引量:1
  • 8FARZIN M, RIKU S. Robust image comer detection through curvature scale space [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1998, 20(12): 1376-1381. 被引量:1
  • 9Chris Harris, Mike Stephens. A combined comer and edge detector [C]//Matthews M. Proceedings of the Fourth Alvey Vision Conference, Manchester: the University of Sheffield Printing Unit, 1988: 147-151. 被引量:1
  • 10Shi J, Tomasi C. Good features to Track [C]// Computer Vision and Pattern Recognition, Seattle, USA, Jun 21-23, 1994: 593-600. 被引量:1

共引文献30

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部 意见反馈