计算机应用 ›› 2015, Vol. 35 ›› Issue (6): 1720-1725.DOI: 10.11772/j.issn.1001-9081.2015.06.1720

• 虚拟现实与数字媒体 • 上一篇    下一篇

基于同形变换的航空倾斜影像自动匹配方法

赵霞1, 朱庆1,2,3, 肖雄武1,3, 李德仁1,3, 郭丙轩1,3, 张鹏1,4, 胡翰1,2, 丁雨淋1,5   

  1. 1. 武汉大学 测绘遥感信息工程国家重点实验室, 武汉 430079;
    2. 西南交通大学 地球科学与环境工程学院, 成都 611756;
    3. 地球空间信息技术协同创新中心, 武汉 430079;
    4. 水利部中国科学院 水工程生态研究所, 武汉 430079;
    5. 香港中文大学 霍英东遥感所, 香港 999077
  • 收稿日期:2014-12-31 修回日期:2015-03-27 发布日期:2015-06-12
  • 通讯作者: 肖雄武(1988-),男,湖北天门人,博士研究生,主要研究方向:倾斜摄影三维重建、计算机视觉;xwxiao@whu.edu.cn
  • 作者简介:赵霞(1991-),女,河南商丘人,硕士研究生,主要研究方向:数字摄影测量、地理信息系统;朱庆(1966-),男,四川仁寿人,教授,博士生导师,博士,主要研究方向:数字摄影测量、地理信息系统、虚拟地理环境;李德仁(1939-),男,江苏泰州人,教授,博士生导师,中国科学院院士,中国工程院院士,博士,主要研究方向:空间信息科学、多媒体通信;郭丙轩(1970-),男,河北衡水人,教授,博士生导师,博士,主要研究方向:数字摄影测量、图形图像处理;张鹏(1986-),男,湖北孝感人,博士,主要研究方向:数字摄影测量、水环境遥感;胡翰(1986-),男,湖北武汉人,博士研究生,主要研究方向:数字摄影测量;丁雨淋(1987-),女,湖北咸宁人,博士,主要研究方向:三维GIS、灾害动态模拟、数字摄影测量。
  • 基金资助:

    国家973计划项目(2010CB731801);国家863计划项目(2012AA121305);国家自然科学基金资助项目(41171311);湖北省电力勘测设计院资助项目(20120008)。

Automatic matching method for aviation oblique images based on homography transformation

ZHAO Xia1, ZHU Qing1,2,3, XIAO Xiongwu1,3, LI Deren1,3, GUO Bingxuan1,3, ZHANG Peng1,4, HU Han1,2, DING Yulin1,5   

  1. 1. Wuhan University, State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan Hubei 430079, China;
    2. Faculty of Geosciences and Environmental Engineering, Southwest Jiaotong University, Chengdu Sichuan 611756, China;
    3. Collaborative Innovation Center for Geospatial Technology, Wuhan Hubei 430079, China;
    4. Institute of Hydroecology, Ministry of Water Resource and Chinese Academy of Sciences, Wuhan Hubei 430079, China;
    5. Fok Ying Tung Remote Sensing Science Building, Chinese University of Hong Kong, Hongkong 999077, China
  • Received:2014-12-31 Revised:2015-03-27 Published:2015-06-12

摘要:

针对仿射尺度不变变换提取(ASIFT)算法计算效率低的问题,提出了一种大倾角航空倾斜影像自动匹配方法H-SIFT。该方法利用影像粗略外方位元素计算两幅待匹配影像之间的单应变换矩阵,对左影像进行二维射影变换得到其纠正影像以消除两幅影像之间的几何变形、尺度和旋转问题,再对左影像的纠正影像和右影像进行尺度不变特征变换(SIFT)。匹配时,为了适当提高正确匹配点对的数量,利用不严格的比值提纯法和左右一致性检验得到粗匹配点对,并利用随机一致性检验剔除误匹配。最后将左影像其纠正影像上的匹配点反算到左影像上。通过对国产五倾斜相机平台(SWDC-5)获取的三组典型城区航空倾斜影像数据进行实验,对于三组数据,该算法获得的正确匹配点对数量分别为ASIFT算法的2.18、1.31、1.70倍,该算法匹配耗时分别为ASIFT算法的0.93%、0.88%、0.97%。实验结果表明,与ASIFT算法相比,该算法获得的匹配点对在计算效率、数量和分布情况上都得到了显著提高。

关键词: 倾斜影像匹配, 仿射尺度不变特征变换, 同形变换, 尺度不变特征变换算法, 匹配策略

Abstract:

In order to reduce the high computing complexity of Affine Scale Invariant Feature Transform (ASIFT) algorithm, a robust and rapid matching method for large angle aviation oblique images based on homography transformation was proposed, which was named H-SIFT. Firstly, the homography matrix between the two oblique images was calculated by making full use of the rough Exterior Orientation (EO) elements of the images, then a homography transformation was made to the left image to get its rectified image for eliminating geometric distortion, scale and rotation. Secondly, the matches between the rectified image and the right image were got by using Scale Invariant Feature Transform (SIFT) algorithm. During the matching process, the coarse matches were got by using two matching constraints, Nearest Neighbor Distance Ratio (NNDR) and consistency checking, then the false matches in them were eliminated by using the RANdom SAmple Consensus (RANSAC) algorithm. Finally, as the matching points on the rectified image were got, the corresponding matching points on the left image were calculated by using the homography matrix. The experiments on three pairs of typical oblique images obtained by Si Wei Digital Camera 5 (SWDC-5) demonstrate that the matching points obtained by the proposed algorithm are significantly improved in the computation efficiency, quantity and distribution than ASIFT algorithm, as the proposed algorithm not only takes just about 0.93%, 0.88%, 0.97% time of ASIFT algorithm, but also gets the correct matching points about 2.18, 1.31, 1.70 times of ASIFT algorithm.

Key words: oblique images matching, Affine Scale Invariant Feature Transform (ASIFT), homography transformation, Scale Invariant Feature Transform (SIFT) algorithm, matching strategy

中图分类号: