异源高分辨率卫星遥感影像配准新方法

›› 2012, Vol. ›› Issue (06): 1576-1580.

异源高分辨率卫星遥感影像配准新方法

宋伟东¹, 戴激光¹, 李建军², 李健³

1. 辽宁工程技术大学测绘与地理科学学院, 辽宁阜新 123000;
2. 辽宁工程技术大学理学院, 辽宁阜新 123000;
3. 吉林农业大学信息技术学院长春130118

收稿日期:2012-02-15 出版日期:2012-11-01
基金资助:
国家自然科学基金项目(40771159);吉林农业大学青年启动基金项目(201040).

New automatic registration method for multi-source high resolution satellite images

SONG Wei-dong¹, DAI Ji-guang¹, LI Jian-jun², LI Jian³

1. School of Geomatics, Liaoning Technical University, Fuxin 123000, China;
2. School of Science, Liaoning Technical University, Fuxin 123000, China;
3. College of Information and Technology Jilin Agricultural University, Changchun 130118, China

Received:2012-02-15 Online:2012-11-01

摘要/Abstract

摘要： 首先建立了粗配准模型。然后对影像进行边缘提取,采用Hough变换提取同名直线。利用同名直线交点构建虚拟点集并进行特征描述,通过几何约束和互信息方法提取初始同名点。最后采用RANSAC算法获取最终的匹配结果,并利用获取的同名点对构建三角网进行小面元纠正。实验结果表明:相对于传统的SIFT匹配算法,本文方法可提取更多的同名点,均方根误差(RMSE)可以控制在1个像素以内。

关键词: 遥感技术, 配准, 异源, 高分辨率卫星影像

Abstract: First, a coarse registration model was built. Second, after image edge extraction, Hough transform was employed to extract matched line. Virtual corner dataset was constructed on the basis of the matched lines, description of the dataset was performed, the initial homonymous points are extracted according to the constraint geometry and mutual information. Finally, RANSAC algorithm was used to obtain the final results of the matching, a great amount of high precision control point pairs are used to construct TIN for tiny facet primitive rectification. Experiment results demonstrate that the presented method can extract more matching points than that SIFT matching method can. The Root of Mean Square Error of the matching points obtained by this method is lower than 1 pixel.

Key words: remote sensing technology, registration, multi-source, high resolution satellite images

中图分类号:

P237

宋伟东, 戴激光, 李建军, 李健. 异源高分辨率卫星遥感影像配准新方法[J]. , 2012, (06): 1576-1580.

SONG Wei-dong, DAI Ji-guang, LI Jian-jun, LI Jian. New automatic registration method for multi-source high resolution satellite images[J]. , 2012, (06): 1576-1580.

参考文献

[1] 王瑞瑞,马建文,陈雪. 多源遥感影像自动配准技术的研究进展[J]. 遥感信息,2011(3):121-127. Wang Rui-rui,Ma Jian-wen,Chen Xue. The research state of the automatic registration techniques of multi-sensor remote sensing imagery[J]. Remote Sensing Information,2011(3):121-127.
[2] An R, Gong P, Wang H,et al. A modified PSO algorithm for remote sensing image temp-late matching[J]. Photogrammetric Engineering and Remote Sensing, 2010,76(4): 379-389.
[3] Shekhar C,Govindu V, Chellapa R. Multisensor image registration by feature consensus[J].Pattern Recognition,1999 (32): 39-52.
[4] 李牧,闫继红,李戈,等. 自适应Canny算子边缘检测技术[J]. 哈尔滨工程大学学报,2007,28(9):1002-1007. Li Mu,Yan Ji-hong,Li Ge,et al. Self-adaptive Canny operator edge detection technique[J]. Journal of Harbin Engineering University,2007,28(9):1002-1007.
[5] 苏娟,林行刚,刘代志.一种基于结构特征边缘的多传感器图像配准方法[J].自动化学报,2009,35(3):251-257. Su Juan, Lin Xing-gang, Liu Dai-zhi. A multi-sensor image registration algorithm based on structure feature edges[J].Acta Automatica Sinica,2009,35(3):251-257.
[6] Hartley R I, Zisserman A. Multiple View Geometry in Computer Vision[M].(2nd edition).Cambridge:Cambridge University Press,2004.
[7] 吴佳奇,徐爱功. Delaunay 三角网生长法的一种改进方法[J].测绘科学,2012,37(2):103-104. Wu Jia-qi,Xu Ai-gong. An improve method of Delaunay triangulated net growth algorithm[J]. Science of Surveying and Mapping. 2012,37(2):103-104.

相关文章 13

[1]	董强, 刘晶红, 周前飞. 用于遥感图像拼接的改进SURF算法[J]. 吉林大学学报(工学版), 2017, 47(5): 1644-1652.
[2]	王雪松, 李躬军, 赵寿经, 安岩, 曲庆玲, 卢超. 人参DS和D12H基因的异源共表达[J]. 吉林大学学报(工学版), 2016, 46(4): 1368-1372.
[3]	姜超, 耿则勋, 刘立勇, 潘映峰. 结合噪声去除的极大似然图像复原[J]. 吉林大学学报(工学版), 2015, 45(4): 1360-1366.
[4]	李晖晖, 滑立, 杨宁, 刘坤. 基于MSA特征和模拟退火优化的遥感图像多目标关联算法[J]. 吉林大学学报(工学版), 2015, 45(4): 1353-1359.
[5]	王京萌, 张爱武, 赵宁宁, 孟宪刚. 斜采样的倾斜角度对采样产生混叠的影响及其与分辨率的关系[J]. 吉林大学学报(工学版), 2015, 45(3): 953-960.
[6]	邱春玲, 陶强, 范润龙, 王培智. 基于局部二进制描述SIFT特征的锆石图像配准方法[J]. 吉林大学学报(工学版), 2014, 44(6): 1793-1798.
[7]	曹建农, 郭佳, 王蓓, 董昱威, 王平禄. 高分辨率影像中城区树冠多尺度聚类识别方法[J]. 吉林大学学报(工学版), 2014, 44(4): 1215-1224.
[8]	王卓峥, 贾克斌. 矩阵填充与主元分析在受损图像配准中的应用[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 78-83.
[9]	夏英杰, 李金屏, 陈瑞. 基于变电站多模图像的自动集成配准方法[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 47-50.
[10]	贾晓未, 魏嵬, 贾克斌. 一种基于GPU的图元网状结构DRR并行加速算法[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 34-38.
[11]	刘刚, 赵红毅, 胡臻龙. 基于带有权值混合泛函的盲超分辨率[J]. , 2012, 42(04): 1054-1058.
[12]	何凯, 何海龙, 邹刚, 远中文, 牟聪翀. 基于相关约束匹配和射影约束的最优匹配点提取 [J]. , 2012, (03): 749-753.
[13]	杨金宝, 刘常春, 胡顺波. 基于算术调和均值距离测度的弹性图像配准[J]. 吉林大学学报(工学版), 2009, 39(05): 1390-1394.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed