结合离散化描述与同名点约束的线特征匹配

doi:10.11947/j.AGCS.2018.20170231

测绘学报 ›› 2018, Vol. 47 ›› Issue (10): 1363-1371.doi: 10.11947/j.AGCS.2018.20170231

结合离散化描述与同名点约束的线特征匹配

欧阳欢, 范大昭, 纪松, 雷蓉

信息工程大学地理空间信息学院, 河南郑州 450001

收稿日期:2017-05-03 修回日期:2017-11-23 出版日期:2018-10-20 发布日期:2018-10-24
通讯作者: 范大昭 E-mail:fdzcehui@163.com
作者简介:欧阳欢(1992-),男,硕士生,研究方向为数字摄影测量。E-mail:ouyanghuan@whu.edu.cn
基金资助:
国家自然科学基金（41401534）；地理信息工程国家重点实验室开放基金（SKLGIE2013-M-3-1）

Line Matching Based on Discrete Description and Conjugate Point Constraint

OUYANG Huan, FAN Dazhao, JI Song, LEI Rong

Institute of Geospatial Information, Information Engineering University, Zhengzhou 450001, China

Received:2017-05-03 Revised:2017-11-23 Online:2018-10-20 Published:2018-10-24
Supported by:
The National Natural Science Foundation of China (No. 41401534);The Open Foundation of the State Key Laboratory of Geographic Information Engineering(No. SKLGIE2013-M-3-1)

摘要/Abstract

摘要： 由于受到多重因素的影响，影像中提取的线特征经常出现断裂、变形、遮挡等问题。为克服上述问题对线特征匹配的影响，本文提出一种结合离散化描述与同名点约束的航空影像线特征匹配算法。算法首先利用单应性约束结合核线约束精简候选线特征数量；然后采用“以点代线”的方式，通过统计线上同名点的分布情况确定线特征初匹配结果；最后根据线特征与其邻域内同名点间的距离关系对匹配结果进行核验，以保证匹配的可靠性。选取AMC580相机系统所获得的航空影像进行线特征匹配试验，结果表明，本文算法匹配正确率高，匹配速度相对较快，并可实现曲线匹配及断裂线特征的多对多匹配。与已有匹配算法进行比较，本文算法在影像间存在有尺度、亮度、旋转变换等复杂条件下的匹配正确率均高于90%，具有较好的匹配稳定性。

关键词: 航空影像, 线特征匹配, 离散化描述, 同名点约束, 曲线匹配

Abstract: Many unfavorable factors may hinder the line matching, such as fracture, deformation or occlusion occurred in line extraction. In order to overcome these problems, a novel method for line matching based on discrete description and conjugate point constraint is proposed. Firstly, the method employs the homography constraint together with epipolar constraint to determine candidate lines. Then, the initial line matching results are obtained by the distribution statistics of the conjugate points on the line. Finally, the mismatching in matched line pairs is eliminated by the similarity verification of line-point affine invariant. Extensive experiments on AMC580 aerial image set demonstrate the better performance of the proposed method as well as its superiority in curve matching and many-to-many matching. Compared with existing line matching methods, the proposed method can obtain more accurate line matching results under changes of image scale, brightness, occlusion, rotation, and achieves a performance of 90% higher matching correctness.

Key words: aerial image, line matching, discrete description, conjugate point constraint, curve matching

中图分类号:

P237

欧阳欢, 范大昭, 纪松, 雷蓉. 结合离散化描述与同名点约束的线特征匹配[J]. 测绘学报, 2018, 47(10): 1363-1371.

OUYANG Huan, FAN Dazhao, JI Song, LEI Rong. Line Matching Based on Discrete Description and Conjugate Point Constraint[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(10): 1363-1371.

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] BAY H, TUYTELAARS T, VAN GOOL L. SURF:Speeded up Robust Features[M]//LEONARDIS A, BISCHOF H, PINZ A. Computer Vision. Berlin, Heidelberg:Springer, 2006.
[3] TOLA E, LEPETIT V, FUA P. DAISY:An Efficient Dense Descriptor Applied to Wide-baseline Stereo[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(5):815-830.
[4] RUBLEE E, RABAUD V, KONOLIGE K, et al. ORB:An Efficient Alternative to SIFT or SURF[C]//Proceedings of 2011 IEEE International Conference on Computer Vision. Barcelona:IEEE, 2011:2564-2571.
[5] REVAUD J, WEINZAEPFEL P, HARCHAOUI Z, et al. Deep Matching:Hierarchical Deformable Dense Matching[J]. International Journal of Computer Vision, 2016, 120(3):300-323.
[6] WANG Zhiheng, WU Fuchao, HU Zhanyi. MSLD:A Robust Descriptor for Line Matching[J]. Pattern Recognition, 2009, 42(5):941-953.
[7] 黄良明, 彭立中, 程民德. 利用几何代数进行线段模型匹配和运动估计[J]. 中国图象图形学报, 2001, 6(3):270-274. HUANG Liangming, PENG Lizhong, CHENG Minde. Matching and Estimating Motion of Line Model Using Geometric Algebra[J]. Journal of Image and Graphics, 2001, 6(3):270-274.
[8] SUN Yanbiao, ZHAO Liang, HUANG Soudong, et al. Line Matching Based on Planar Homography for Stereo Aerial Images[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2015(104):1-17.
[9] BAILLARD C, SCHMID C, ZISSERMAN A, et al. Automatic Line Matching and 3D Reconstruction of Buildings from Multiple Views[C]//ISPRS Conference on Automatic Extraction of GIS Objects from Digital Imagery. Munich:International Archives of Photogrammetry and Remote Sensing, 1999:69-80.
[10] BAY H, FERRARI V, VAN GOOL L. Wide-baseline Stereo Matching with Line Segments[C]//Proceedings of 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego:IEEE, 2005:329-336.
[11] 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.
[12] LI Kai, YAO Jian, LU Xiaohu, et al. Hierarchical Line Matching Based on Line-junction-line Structure Descriptor and Local Homography Estimation[J]. Neurocomputing, 2016, 184:207-220.
[13] JIA Qi, GAO Xinkai, FAN Xin, et al. Novel Coplanar Line-points Invariants for Robust Line Matching Across Views[C]//Proceedings of the 14th European Conference on Computer Vision. Amsterdam:Springer, 2016:599-611.
[14] FAN Bin, WU Fuchao, HU Zhanyi. Robust Line Matching Through Line-point Invariants[J]. Pattern Recognition, 2012, 45(2):794-805.
[15] RAMALINGAM S, ANTUNES M, SNOW D, et al. Line-sweep:Cross-ratio for Wide-baseline Matching and 3D Reconstruction[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Boston:IEEE, 2015:1238-1246.
[16] 张跃强, 苏昂, 朱遵尚, 等. 结合局部描述和拓扑约束的直线段匹配算法[J]. 国防科技大学学报, 2014, 36(6):25-30. ZHANG Yueqiang, SU Ang, ZHU Zunshang, et al. A Line Matching Algorithm Combining Local Description with Topological Constraint[J]. Journal of National University of Defense Technology, 2014, 36(6):25-30.
[17] 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.
[18] ZHANG Li, GRUEN A. Multi-image Matching for DSM Generation from IKONOS Imagery[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2006, 60(3):195-211.
[19] 胡海霞. 视觉运动分析中的线特征提取与匹配方法研究[D]. 南昌:南昌航空大学, 2009:53-68. HU Haixia. Research on Extraction and Matching of Linear and Curvilinear Features in Vision Motion Analysis[D]. Nanchang:Nanchang Hangkong University, 2009:53-68.
[20] 张桂梅, 熊逸文, 马珂. 基于仿射不变性的轮廓曲线局部描述符[J]. 模式识别与人工智能, 2012, 25(6):972-978. ZHANG Guimei, XIONG Yiwen, MA Ke. Contour Curve Descriptor Based on Affine Invariance[J]. Pattern Recognition and Artificial Intelligence, 2012, 25(6):972-978.
[21] 王志衡, 智珊珊, 刘红敏. 基于亮度序的均值标准差描述子[J]. 模式识别与人工智能, 2013, 26(4):409-416. WANG Zhiheng, ZHI Shanshan, LIU Hongmin. Intensity Order Based Mean-standard Deviation Descriptor[J]. Pattern Recognition and Artificial Intelligence, 2013, 26(4):409-416.
[22] 彭科举. 基于序列图像的三维重建算法研究[D]. 长沙:国防科学技术大学, 2012:34-37. PENG Keju. 3D Reconstruction Using Image Sequences[D]. Changsha:National University of Defense Technology, 2012:34-37.
[23] 缪君, 储珺, 张桂梅. 一种仿射不变的直线描述子与直线匹配[J]. 电子学报, 2015, 43(12):2505-2512. MIAO Jun, CHU Jun, ZHANG Guimei. An Affine Invariant Line Descriptor and Line Matching[J]. Acta Electronica Sinica, 2015, 43(12):2505-2512.
[24] VON GIOI R G, JAKUBOWICZ J, MOREL J M, et al. LSD:A Line Segment Detector[J]. Image Processing on Line, 2012, 2(4):35-55.
[25] CANNY J. A Computational Approach to Edge Detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8(6):679-698.

结合离散化描述与同名点约束的线特征匹配

Line Matching Based on Discrete Description and Conjugate Point Constraint

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 10

编辑推荐

Metrics

本文评价

[1]	金飞, 官恺, 刘智, 韩佳容, 芮杰, 李庆高. 无监督密集匹配特征提取网络性能分析[J]. 测绘学报, 2022, 51(3): 426-436.
[2]	刘瑾, 季顺平. 基于深度学习的航空遥感影像密集匹配[J]. 测绘学报, 2019, 48(9): 1141-1150.
[3]	伍广明, 陈奇, Ryosuke SHIBASAKI, 郭直灵, 邵肖伟, 许永伟. 基于U型卷积神经网络的航空影像建筑物检测[J]. 测绘学报, 2018, 47(6): 864-872.
[4]	何曼芸, 程英蕾, 邱浪波, 赵中阳. 一种改进顶帽变换与LBP高程纹理的城区建筑物提取算法[J]. 测绘学报, 2017, 46(9): 1116-1122.
[5]	赵爽, 李学军, 刘涛, 谢剑薇. 基于大比例尺航空影像共面约束条件的相机自检校方法[J]. 测绘学报, 2017, 46(1): 98-106.
[6]	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.
[7]	张永军熊小东王梦秋鲁一慧. 机载激光雷达点云与定位定姿系统数据辅助的航空影像自动匹配方法[J]. 测绘学报, 2014, 43(4): 380-388.
[8]	孙颖张新长康停军赵小阳张维. 改进GAC模型在点云和影像自动提取建筑物边界中的应用[J]. , 2013, 42(3): 0-0.
[9]	程亮,龚健雅,李满春. 集成多视航空影像与LiDAR数据重建三维建筑物模型[J]. 测绘学报, 2009, 38(6): 0-501.
[10]	虞欣. 贝叶斯网络在航空影像纹理分类中的应用研究[J]. 测绘学报, 2009, 38(4): 0-310.