计算机科学 ›› 2016, Vol. 43 ›› Issue (Z6): 118-121.doi: 10.11896/j.issn.1002-137X.2016.6A.028

• 模式识别与图像处理 • 上一篇    下一篇

基于频率域信息的遥感图像数据库水体检索

李轶鲲,胡玉玺,杨萍   

  1. 兰州交通大学测绘与地理信息学院 兰州730070甘肃省地理国情监测工程实验室 兰州730070,兰州交通大学测绘与地理信息学院 兰州730070甘肃省地理国情监测工程实验室 兰州730070,兰州交通大学测绘与地理信息学院 兰州730070甘肃省地理国情监测工程实验室 兰州730070
  • 出版日期:2018-12-01 发布日期:2018-12-01
  • 基金资助:
    本文受甘肃省高等学校基本科研业务费项目:基于空间关系敏感的高分辨率卫星图像检索技术研究(213049),中国博士后科学基金资助

Frequency Domain Information Based Water Body Image Retrieval in High Resolution Satellite Image Databases

LI Yi-kun, HU Yu-xi and YANG Ping   

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

摘要: 如何快速、准确地在遥感图像数据库中找出目标图像,是遥感图像检索系统的核心所在。 因为综合区域匹配算法能够有效减少对图像的错误分割所造成的检索错误,所以使用综合区域匹配算法为图像相似度度量标准,提出了以平均高频信号强度升序为排序标准的遥感图像数据库水体区域检索方法。另外使用3种不同类型的频率域滤波器所得到的平均高频信号强度进行检索实验。实验结果表明,所提方法将检索查准率提高了18%,而理想型高通滤波器为最优滤波器。所提方法具有较高的查准率和检索效率,能够满足用户的需要。

关键词: 图像检索,水体,相似度度量,查准率,高通滤波器

Abstract: The core of a remote sensing image retrieval system is to quickly and accurately find target images from remote sensing image database.Since integrated region matching (IRM) algorithm can effectively reduce the retrieval mistakes which are caused by inaccurate segmentation of images,this paper used IRM as image similarity measurement standard,and proposed a novel approach to retrieve water body images from remote sensing image database,which sorts the retrieved images in ascending order according to their average high frequency strength (AHFSS).Additionally,this paper used three different types of filters in frequency domain to obtain the AHFSS values of images and conduct retrieval experiments.The experimental results show that the proposed approach increases the retrieval precision by 18% and the ideal high frequency filter is the optimal filter.Therefore,the proposed approach has higher retrieval precision and retrieval efficiency to meet users’ requirement.

Key words: Image retrieval,Water body,Similarity measurement,Precision ration,High-pass filter

[1] Li Yi-kun.Semantic-Sensitive Remote Sensing Imagery Retrie-val[M].北京:中国环境出版社,2014(8):1-7
[2] Wang J Z,Li J,Wiederhold G.SIMPLIcity:Semantics-sensitive integrated matching for picture libraries[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2001,23(9):947-963
[3] Tian Y,Wu Z,Meng L.A region-interactive retrieval modelbased on IRM algorithm[C]∥2005 5th International Confe-rence on Information Communications&Signal Processing.2005:692-695
[4] Zakariya S M,Ali R,Ahmad N.Combining visual features of an image at different precision value of unsupervised content based image retrieval[C]∥2010 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC).IEEE,2010:1-4
[5] Zhuang D,Wang S.Content-based image retrieval based on integrating region segmentation and relevance feedback[C]∥2010 International Conference on Multimedia Technology (ICMT).IEEE,2010:1-3
[6] 李轶鲲,闫浩文,孙建国.分步式卫星图像检索[J].测绘科学,2009,34(6):53-55
[7] 夏定元,付翩,刘丽端.一种综合区域匹配的图像检索改进算法[J].计算机工程与应用,2012,48(26):197-200
[8] 郭媛,毛琦,陈小天.干涉条纹快速加窗傅里叶滤波方法的研究[J].光学学报,2014,34(6):151-155
[9] 邓书斌.ENVI遥感图像处理方法(第1版)[M].北京:科学出版社,2010:120-127
[10] 李杰.基于内容的图像检索方法研究[D].合肥:中国科学技术大学,2008

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!