计算机应用 ›› 2016, Vol. 36 ›› Issue (10): 2870-2874.DOI: 10.11772/j.issn.1001-9081.2016.10.2870

• 虚拟现实与数字媒体 • 上一篇    下一篇

基于异常区域感知的多时相高分辨率遥感图像配准

吴伟1, 丁香乾2, 闫明3   

  1. 1. 青岛工学院 信息工程学院, 山东 青岛 266300;
    2. 中国海洋大学 信息工程中心, 山东 青岛 266071;
    3. 中国民用航空青岛空中交通管理站, 山东 青岛 266108
  • 收稿日期:2016-02-19 修回日期:2016-03-31 发布日期:2016-10-10
  • 通讯作者: 闫明,E-mail:yanming_qd@163.com
  • 作者简介:吴伟(1981—),女,山东临沂人,讲师,硕士研究生,CCF会员,主要研究方向:图像处理、无线通信、网络安全;丁香乾(1962—),男,山东荣成人,教授,博士生导师,主要研究方向:计算智能、软件工程、数字家庭、制造业信息化;闫明(1981—),男,山东青岛人,高级工程师,硕士,主要研究方向:嵌入式应用、通信导航。
  • 基金资助:
    国家科技支撑计划项目(2012BAF12B06);青岛市重大专项(13-7-1-ZDZX4-GX)。

Registration for multi-temporal high resolution remote sensing images based on abnormal region sensing

WU Wei1, DING Xiangqian2, YAN Ming3   

  1. 1. College of Information Engineering, Qingdao University of Technology, Qingdao Shandong 266300, China;
    2. Center of Information Engineering, Ocean University of China, Qingdao Shandong 266071, China;
    3. Qingdao Air Traffic Management Station of China Civil Aviation, Qingdao Shandong 266108, China
  • Received:2016-02-19 Revised:2016-03-31 Published:2016-10-10
  • Supported by:
    BackgroundThis work is partially supported by the National Technology R&D Program of China (2012BAF12B06), the Major Projects of Qingdao (13-7-1-ZDZX4-GX).

摘要: 在对多时相高分辨遥感图像进行配准时,由于成像条件差异,图像间存在的地物变化与相对视差偏移两类典型异常区域会影响配准精度。针对上述配准中存在的问题,提出一种基于异常区域感知的多时相高分辨率遥感图像配准方法,包括粗匹配和精配准两个阶段。尺度不变特征变换(SIFT)算法考虑到尺度空间属性,不同尺度空间提取的特征点在图像中对应不同大小的斑块,高尺度空间提取的特征点对应图像中的大斑点,其对应地物相对稳定、不易发生变化。首先,利用SIFT算法提取高尺度空间特征点完成图像快速粗匹配;其次,利用灰度相关性度量对图像块进行相对偏移量统计分类以感知视差偏移区域,同时结合空间约束条件,确定低尺度空间特征点的有效提取区域以及匹配点搜索范围,完成图像精配准。实验结果表明,将该方法用于多时相高分辨遥感图像配准,可有效抑制异常区域对特征点提取的影响进而提高配准精度。

关键词: 图像配准, 多时相, 高分辨率遥感图像, 尺度空间, 尺度不变特征变换, 灰度相关性度量

Abstract: In the processing of registration for multi-temporal high resolution remote sensing images, the phenomena of surface features change and relative parallax displacement caused by differences in acquisition conditions degrades the accuracy of registration. To resolve the aforementioned issue, a registration algorithm for multi-temporal high resolution remote sensing images based on abnormal region sensing was proposed, which consists of coarse and fine registration. The algorithm of Scale-Invariant Feature Transform (SIFT) has a better performance on scale space, the feature points from different scale space indicates the various size of spot. The high scale space points represent the objects which have a stable condition, the coarse registration can be executed depending on those points. For the fine registration, intensity correlation measurement and spatial constraint were used to decide the regions which were used to extract the efficacious points from low scale space, the areas for searching matching points were limited as well. Finally, the accuracy of the proposed method was evaluated from subjective and objective aspects. Experimental results demonstrate that the proposed method can effectively restrain the influence of abnormal region and improve registration accuracy.

Key words: image registration, multi-temporal, high resolution remote sensing image, scale space, Scale-Invariant Feature Transform (SIFT), intensity correlation measurement

中图分类号: