利用自由形状线特征的遥感影像分级匹配方法

doi:10.11947/j.AGCS.2017.20160282

测绘学报 ›› 2017, Vol. 46 ›› Issue (2): 208-217.doi: 10.11947/j.AGCS.2017.20160282

利用自由形状线特征的遥感影像分级匹配方法

陈小卫^1,2, 张保明¹, 郭海涛¹, 赵传^1,2, 徐俊峰^1,2

1. 信息工程大学地理空间信息学院, 河南郑州 450052;
2. 地理信息工程国家重点实验室, 陕西西安 710054

收稿日期:2016-06-12 修回日期:2016-12-30 出版日期:2017-02-20 发布日期:2017-03-07
作者简介:陈小卫(1989-),男,博士生,研究方向为卫星影像无控定位、影像线特征匹配。E-mail:chenxw_2007@aliyun.com
基金资助:
国家自然科学基金（41601507）；地理信息工程国家重点实验室开放基金（SKLGIE2015-M-3-3）

Hierarchical Remote Sensing Image Matching Method Based on Free-form Linear Features

CHEN Xiaowei^1,2, ZHANG Baoming¹, GUO Haitao¹, ZHAO Chuan^1,2, XU Junfeng^1,2

1. Institute of Surveying and Mapping, Information Engineering University, Zhengzhou 450052, China;
2. State Key Laboratory of Geo-information Engineering, Xi'an 710054, China

Received:2016-06-12 Revised:2016-12-30 Online:2017-02-20 Published:2017-03-07
Supported by:
The National Natural Science Foundation of China (No. 41601507),The Open Research Foundation of State Key Laboratory of Geo-information Engineering (No. SKLGIE2015-M-3-3)

摘要/Abstract

摘要： 为较好地解决自由形状线特征匹配研究中线特征丰富信息的充分利用与有效描述这对矛盾，提出一种利用分级匹配策略的遥感影像匹配方法。为保证方法具有较高的匹配精度，从影像中检测亚像素边缘并进行有效的跟踪以得到连续性较好的自由形状线特征；再从中提取闭合线特征、线特征交点和角点等较稳定的特征作为共轭实体进行粗匹配，在确定各类特征的待选同名特征后，根据面积、角度等几何信息以及模型参数的分布特点逐步剔除误匹配，进而利用同名特征确定精匹配的初始参数；精匹配时对线特征中的亚像素边缘点加以利用，采用多层次二维迭代最邻近点（ICP）法依次利用由低到高采样率的边缘点进行匹配。试验结果表明，粗匹配选取的特征性能稳定，具有较高的匹配正确率和精度，能为精匹配提供较准确的初始参数，精匹配能达到与最小二乘影像匹配相当的亚像素级匹配精度，并且对具有较小仿射变形的影像也能实现稳定、准确的匹配。

关键词: 自由形状线特征, 影像匹配, 分级匹配策略, 闭合线特征, 线特征角点, 线特征交点

Abstract: A remote sensing image matching method using the hierarchical matching strategy is proposed, with the purpose of resolving the conflict between the full use and effective description of the rich information of free-form linear feature (FFLF) in the study of FFLF matching. To ensure high matching precision, continuous FFLFs are extracted based on sub-pixel edge detection and tracing method. In the coarse matching process, closed linear features (CLF), linear feature intersection (LFI) and corner (LFC) were selected as conjugated entities. After determining candidate features, the false matching was gradually eliminated based on area, angle and other geometry information as well as the distribution characteristics of the model parameters determined by feature combinations, finally the initial value of accurate matching was determined by the conjugate features. In the accurate matching process, based on multi-level two-dimensional iterative closest point (ICP) method, sub-pixel edge points with the sampling rate from low to high were orderly used for matching. Experimental results show that the features selected for coarse matching have stable performance. Coarse matching is of high accuracy and precision and can provide high precision initial matching parameters for accurate matching. Accurate matching can reach sub-pixel level precision equal to the least square matching (LSM) and with good adaptability to small image affine transformation.

Key words: free-form linear feature (FFLF), image matching, hierarchical matching strategy, closed linear feature (CLF), linear feature corner (LFC), linear feature intersection (LFI)

中图分类号:

P237

陈小卫, 张保明, 郭海涛, 赵传, 徐俊峰. 利用自由形状线特征的遥感影像分级匹配方法[J]. 测绘学报, 2017, 46(2): 208-217.

CHEN Xiaowei, ZHANG Baoming, GUO Haitao, ZHAO Chuan, XU Junfeng. Hierarchical Remote Sensing Image Matching Method Based on Free-form Linear Features[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(2): 208-217.

参考文献

[1] LOWE D G. Distinctive Image Features from Scale-invariant Keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110.
[2] MOREL J M, YU Guoshen. ASIFT:A New Framework for Fully Affine Invariant Image Comparison[J]. SIAM Journal on Imaging Sciences, 2009, 2(2):438-469.
[3] MATAS J, CHUM O, URBAN M, et al. Robust Wide-baseline Stereo from Maximally Stable Extremal Regions[J]. Image and Vision Computing, 2004, 22(10):761-767.
[4] VASSILAKI D I, IOANNIDIS C C, STAMOS A A. Multitemporal Data Registration through Global Matching of Networks of Free-form Curves[C]//FIG Working Week 2009:Surveyors Key Role in Accelerated Development. Eilat, Israel:FIG, 2009:TS 6B 1-18.
[5] 王竞雪, 宋伟东, 王伟玺. 同名点及高程平面约束的航空影像直线匹配算法[J]. 测绘学报, 2016, 45(1):87-95. DOI:10.11947/j.AGCS.2016.20140527. WANG Jingxue, SONG Weidong, WANG Weixi. Line Matching Algorithm for Aerial Image Based on Corresponding Points and Z-plane Constraints[J]. Acta Geodaetica et Cartographica Sinica, 2016, 45(1):87-95. DOI:10.11947/j.AGCS.2016.20140527.
[6] KIM H, LEE S.Simultaneous Line Matching and Epipolar Geometry Estimation Based on the Intersection Context of Coplanar Line Pairs[J]. Pattern Recognition Letters, 2012, 33(10):1349-1363.
[7] ZHANG Li.Automatic Digital Surface Model (DSM) Generation from Linear Array Images[D]. Zurich, Switzerland:Institute of Geodesy and Photogrammetry, Swiss Federal Institute of Technology, ETH, 2005.
[8] SAEEDI P, MAO M. Two-edge-corner Image Features for Registration of Geospatial Images with Large View Variations[J]. International Journal of Geosciences, 2014, 5(11):1324-1344.
[9] VASSILAKI D I, IOANNIDIS C C, STAMOS A A. Automatic ICP-based Global Matching of Free-form Linear Features[J]. The Photogrammetric Record, 2012, 27(139):311-329.
[10] ZHANG Zhenyou.Iterative Point Matching for Registration of Free-form Curves and Surfaces[J]. International Journal of Computer Vision, 1994, 13(2):119-152.
[11] CHEN Zen, SUN Shukuo. A Zernike Moment Phase-based Descriptor for Local Image Representation and Matching[J]. IEEE Transactions on Image Processing, 2010, 19(1):205-219.
[12] EKOMBO P L E, ENNAHNAHI N, OUMSIS M, et al. Application of Affine Invariant Fourier Descriptor to Shape-based Image Retrieval[J]. International Journal of Computer Science and Network Security, 2009, 9(7):240-247.
[13] ZULIANI M, BERTELLI L, KENNEY C S, et al. Drums, Curve Descriptors and Affine Invariant Region Matching[J]. Image and Vision Computing, 2008, 26(3):347-360.
[14] 张桂梅, 马珂, 储珺. 基于薄膜振动模型的曲线匹配方法[J]. 电子学报, 2013, 41(10):1917-1925. ZHANG Guimei, MA Ke, CHU Jun. A New Curve Matching Method Based on Membrane Vibration Model[J]. Acta Electronica Sinica, 2013, 41(10):1917-1925.
[15] NG E S, KINGSBURY N G. Matching of Interest Point Groups with Pairwise Spatial Constraints[C]//Proceedings of the 17th IEEE International Conference on Image Processing. Hong Kong:IEEE, 2010:2693-2696.
[16] WU Bo, ZHANG Yunsheng, ZHU Qing. Integrated Point and Edge Matching on Poor Textural Images Constrained by Self-adaptive Triangulations[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2012, 68:40-55.
[17] DA Feipeng,ZHANG Hu. Sub-pixel Edge Detection Based on an Improved Moment[J]. Image and Vision Computing, 2010, 28(12):1645-1658.
[18] 陈小卫, 徐朝辉, 郭海涛, 等. 利用极值梯度的通用亚像素边缘检测方法[J]. 测绘学报, 2014, 43(5):500-507. DOI:10.13485/j.cnki.11-2089.2014.0073. CHEN Xiaowei, XU Zhaohui, GUO Haitao, et al. Universal Sub-pixel Edge Detection Algorithm Based on Extremal Gradient[J]. Acta Geodaetica et Cartographica Sinica, 2014, 43(5):500-507. DOI:10.13485/j.cnki.11-2089.2014.0073.
[19] 陈小卫, 张保明, 郭海涛, 等. 一种亚像素边缘提取方法[J]. 测绘科学技术学报, 2014, 31(6):624-629. CHEN Xiaowei, ZHANG Baoming, GUO Haitao, et al. An Edge Curve Extraction Method Based on Sub-pixel Edge[J]. Journal of Geomatics Science and Technology, 2014, 31(6):624-629.
[20] 李富裕, 李言俊, 张科. 链码技术在景象图像特征提取中的应用[J]. 中国图象图形学报, 2008, 13(1):114-118. LI Fuyu, LI Yanjun, ZHANG Ke. The Use of the Chain-code Technique in Extracting Feature Point in Scene Image[J]. Journal of Image and Graphics, 2008, 13(1):114-118.
[21] 季顺平, 袁修孝. 基于RFM的高分辨率卫星遥感影像自动匹配研究[J]. 测绘学报, 2010, 39(6):592-598. JI Shunping, YUAN Xiuxiao. Automatic Matching of High Resolution Satellite Images Based on RFM[J]. Acta Geodaetica et Cartographica Sinica, 2010, 39(6):592-598.

利用自由形状线特征的遥感影像分级匹配方法

Hierarchical Remote Sensing Image Matching Method Based on Free-form Linear Features

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	张传辉, 姚国标, 张力, 艾海滨, 满孝成, 黄鹏飞. 多分支网络联合的倾斜影像仿射不变特征匹配[J]. 测绘学报, 2021, 50(5): 641-651.
[2]	蓝朝桢, 卢万杰, 于君明, 徐青. 异源遥感影像特征匹配的深度学习算法[J]. 测绘学报, 2021, 50(2): 189-202.
[3]	姜三, 江万寿. Delaunay三角网约束下的影像稳健匹配方法[J]. 测绘学报, 2020, 49(3): 322-333.
[4]	张春森, 张奇源, 郭丙轩, 薛万唱. 倾斜影像自适应初始物方面元优化匹配算法[J]. 测绘学报, 2020, 49(1): 108-116.
[5]	南轲, 齐华, 叶沅鑫. 深度卷积特征表达的多模态遥感影像模板匹配方法[J]. 测绘学报, 2019, 48(6): 727-736.
[6]	袁修孝, 袁巍, 许殊, 纪艳华. 航摄影像密集匹配的研究进展与展望[J]. 测绘学报, 2019, 48(12): 1542-1550.
[7]	陈晓勇, 何海清, 周俊超, 安谱阳, 陈婷. 低空摄影测量立体影像匹配的现状与展望[J]. 测绘学报, 2019, 48(12): 1595-1603.
[8]	Yun ZHANG. 智能摄影测量和图像处理在高分辨率光学遥感影像处理中的应用——CRC-AGIP实验室的案例[J]. 测绘学报, 2018, 47(6): 722-729.
[9]	范大昭, 董杨, 张永生. 卫星影像匹配的深度卷积神经网络方法[J]. 测绘学报, 2018, 47(6): 844-853.
[10]	梁焕青, 谢意, 付四洲. 颜色不变量与AKAZE特征相结合的无人机影像匹配算法[J]. 测绘学报, 2017, 46(7): 900-909.
[11]	张力, 艾海滨, 许彪, 孙钰珊, 董友强. 基于多视影像匹配模型的倾斜航空影像自动连接点提取及区域网平差方法[J]. 测绘学报, 2017, 46(5): 554-564.
[12]	董杨, 范大昭, 纪松, 雷蓉. 主成分分析的匹配点对提纯方法[J]. 测绘学报, 2017, 46(2): 228-236.
[13]	陈敏, 朱庆, 朱军, 徐柱, 黄澜心. SAR影像与光学影像的高斯伽玛型边缘强度特征匹配法[J]. 测绘学报, 2016, 45(3): 318-325.
[14]	朱映, 王密, 潘俊, 胡芬. 利用多光谱影像检测资源三号卫星平台震颤[J]. 测绘学报, 2015, 44(4): 399-406.
[15]	肖雄武, 郭丙轩, 李德仁, 赵霞, 江万寿, 胡翰, 张春森. 一种具有仿射不变性的倾斜影像快速匹配方法[J]. 测绘学报, 2015, 44(4): 414-421.