局部点、线仿射不变性约束的近景影像直线段匹配

doi:10.12082/dqxxkx.2019.180339

地球信息科学学报 ›› 2019, Vol. 21 ›› Issue (2): 137-146.doi: 10.12082/dqxxkx.2019.180339

• 地球信息科学理论与方法 • 下一篇

局部点、线仿射不变性约束的近景影像直线段匹配

王竞雪^1,²(), 崔昊^1,^*()

1. 辽宁工程技术大学测绘与地理科学学院,阜新 123000
2. 西南交通大学地球科学与环境工程学院,成都 611756

收稿日期:2018-07-25 修回日期:2018-12-06 出版日期:2019-02-20 发布日期:2019-01-30
通讯作者: 崔昊 E-mail:xiaoxue1861@163.com;921260976@qq.com
作者简介:
作者简介：王竞雪(1981-),女,河南淮阳人,博士,副教授,研究方向为影像匹配与三维建模。E-mail: xiaoxue1861@163.com
基金资助:
国家自然科学基金项目（41871379）;地球观测与时空信息科学国家测绘地理信息局重点实验室经费资助项目（201801）

Line Segment Matching based on Local Point-Line Affine Invariance Constraints for Close-Range Image

Jingxue WANG^1,²(), Hao CUI^1,^*()

1. School of Geomatics, Liaoning Technical University, Fuxin 123000, China
2. Faculty of Geosciences and Environmental Engineering, Southwest Jiaotong University, Chengdu 611756, China

Received:2018-07-25 Revised:2018-12-06 Online:2019-02-20 Published:2019-01-30
Contact: Hao CUI E-mail:xiaoxue1861@163.com;921260976@qq.com
Supported by:
National Natural Science Foundation of China No.41871379;Key Laboratory of Earth Observation and Geospatial Information Science of NASG, No.201801

摘要/Abstract

摘要：

针对直线匹配过程中存在直线提取断裂、影像尺度不一、纹理断裂处灰度相似性约束可靠性弱的问题,本文提出了一种基于局部点、线仿射不变性约束的直线段匹配算法。该算法首先利用SIFT匹配得到的同名点构建参考影像、搜索影像同名三角网,并采用三角网约束直线匹配的搜索范围获得初始候选直线;然后利用方向约束对候选直线进行二次筛选,滤掉明显的错误候选直线;最后分别建立参考直线与候选直线的支持区域,搜索并确定位于直线支持区域内的匹配点并以直线为基准对其进行区域划分,并根据点、线仿射不变性原理分区域约束确定同名直线。通过选取网上公开影像数据库中典型影像对进行直线匹配实验,结果表明本文算法具有较好的鲁棒性,并能获取可靠的直线匹配结果。

关键词: 直线匹配, 三角网约束, 方向约束, 支持区域, 仿射不变

Abstract:

We proposed the line-segment-matching approach with the constraint of local point-line affine invariance, to seek the solution to the fracture in straight lines extraction, the inconsistency of image scale, and the weakness of the gray similarity constraint in the texture fracture. Firstly, the corresponding triangulation network is established by the corresponding points which are obtained using SIFT(Scale-Invariant Feature Transform) matching algorithm in the references and searching images, at the same time, the candidate straight lines are obtained by triangulation network which searching range is constrained in the process of straight lines matching; Secondly, the direction constraint is used to perform secondary screening for the candidate straight lines in order to filter the candidate straight lines with obvious error. It can not only get further filter results of triangulation network constraint, but also provide a solution for angle transformation which caused by image rotation in the process of straight lines matching. The direction angles of each characteristic point of the reference image and the searching image are calculated separately, and the angle histogram is established according to the statistical results. Angle difference corresponding to the maximum peak of two histograms is called rotation angle. Finally, the support regions with the center of target straight line segment in the reference image and the corresponding support region with the center of candidate straight line segment in the searching image are both determined, and then the matching points in the support region are determined, after that the matching points are divided based on the straight line, meanwhile the corresponding straight line is determined according to subregional constraint by the principle of point-straight line affine invariance. Using proposed algorithm to perform straight line matching experiments in the typical image pairs which are selected from the online public image database, and the experiment results show that the proposed algorithm has better robustness and it can obtain reliable straight line matching results. What's more, instability problems caused by many factors exist in other algorithms of straight lines matching are improved by our algorithm.

Key words: straight line matching, triangulation network constraint, direction constraint, support region, affine invariance

王竞雪, 崔昊. 局部点、线仿射不变性约束的近景影像直线段匹配[J]. 地球信息科学学报, 2019, 21(2): 137-146.DOI:10.12082/dqxxkx.2019.180339

Jingxue WANG, Hao CUI. Line Segment Matching based on Local Point-Line Affine Invariance Constraints for Close-Range Image[J]. Journal of Geo-information Science, 2019, 21(2): 137-146.DOI:10.12082/dqxxkx.2019.180339

图/表 10

图1

图2

表1

图3

图4

图5

表2

图6

图7

表3

参考文献 24

[1]	王思洁,方莉娜,陈崇成,等.基于结构化场景的单幅图像建筑物三维重建[J].地球信息科学学报,2016,18(8):1022-1029. doi: 10.3724/SP.J.1047.2016.01022
	[ Wang S J, Fang L N, Chen C C, et al.A single view type 3D reconstructive method for architecture based on structured scene[J]. Journal of Geo-information Science, 2016,18(8):1022-1029. ] doi: 10.3724/SP.J.1047.2016.01022
[2]	李畅,刘亚文,胡敏,等.面向街景立面三维重建的近景影像直线匹配方法研究[J].武汉大学学报·信息科学版,2010,35(12):1461-1465.
	[ Li C, Liu Y W, Hu M, et al.Study on street elevation 3D reconstruction-oriented straight line matching for close-range images[J]. Geomatics and Information Science of Wuhan University, 2010,35(12):1461-1465. ]
[3]	王建敏,刁寅午,娄安颖,等.改进的同名直线匹配及三维重建技术[J].海洋测绘,2011,31(2):68-71. doi: 10.3969/j.issn.1671-3044.2011.02.020
	[ Wang J M, Diao Y W, Lou A Y, et al.Improved matching of homonymous line and the technology of three-dimensional reconstruction[J]. Hydrographic Surveying and Charting, 2011,31(2):68-71. ] doi: 10.3969/j.issn.1671-3044.2011.02.020
[4]	娄安颖. 遥感影像直线提取、匹配及三维重建[D].阜新:辽宁工程技术大学,2011.
	[ Lou A Y.Line extraction, matching and three-dimensional reconstruction in satellite images[D]. Fuxin: School of Geomatics, Liaoning Technical University, 2011. ]
[5]	高新凯. 基于几何不变量的直线匹配与三维建模[D].大连:大连理工大学,2017.
	[ Gao X K.Line matching and 3D modeling using geometric invariants[D]. Dalian: Dalian University of Technology, 2017. ]
[6]	邓刘洋,沈占锋,柯映明.城市建成区遥感影像边界提取与扩张分析[J].地球信息科学学报,2018,20(7):996-1003.
	[ Deng L Y, Shen Z F.Built-up area extraction and urban expansion analysis based on remote sensing images[J]. Journal of Geo-information Science, 2018,20(7):996-1003. ]
[7]	张云生,朱庆,吴波,等.一种基于三角网约束的立体影像线特征多级匹配方法[J].武汉大学学报·信息科学版, 2013,38(5):522-527.
	[ Zhang Y S, Zhu Q, Wu B, et al.A hierarchical stereo line matching method based on a triangle constraint[J]. Geomatics and Information Science of Wuhan University, 2013,38(5):522-527. ]
[8]	刘亚文. 基于TIN的半自动多影像同名线段匹配算法研究[J].武汉大学学报·信息科学版, 2004,29(4):342-345. doi: 10.3321/j.issn:1671-8860.2004.04.014
	[ Liu Y W,. A semi-automatic algorithm for line matching based on delaunay triangulation[J]. Geomatics and Information Science of Wuhan University, 2004,29(4):342-345. ] doi: 10.3321/j.issn:1671-8860.2004.04.014
[9]	娄安颖,宋伟东,刘薇.基于单应矩阵的直线匹配[J].遥感信息,2011(3):9-13. doi: 10.3969/j.issn.1000-3177.2011.03.002
	[ Lou A Y, Song W D, Liu W.Matching straight lines on the basis of homography[J]. Remote Sensing Information,2011(3):9-13. ] doi: 10.3969/j.issn.1000-3177.2011.03.002
[10]	黄杰,于瑞鹏,丁翠,等.直线特征的多层次仿射不变匹配方法研究[J].测绘科学,2016,41(7):28-32. doi: 10.16251/j.cnki.1009-2307.2016.07.006
	[ Huang J, Yu R P, Ding C, et al.Study on line matching based on multi-level and affine invariant[J]. Science of Surveying and Mapping, 2016,41(7):28-32. ] doi: 10.16251/j.cnki.1009-2307.2016.07.006
[11]	王志衡,吴福朝.均值-标准差描述子与直线匹配[J].模式识别与人工智能,2009,22(1):32-39. doi: 10.3969/j.issn.1003-6059.2009.01.006
	[ Wang Z H, Wu F C.Mean-standard deviation descriptor and line matching[J]. Pattern Recognition and Artificial Intelligence, 2009,22(1):32-39. ] doi: 10.3969/j.issn.1003-6059.2009.01.006
[12]	Mcintosh J H, Mutch K M.Matching straight lines[J]. Computer Vision Graphics & Image Processing, 1988,43(3):386-408.
[13]	Burns J B, Hanson A R, Riseman E M. Extracting straight lines[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2009,PAMI-8(4):425-455.
[14]	陈宁江,李介谷.基于支持区域的直线段匹配[J].红外与激光工程,2000,29(5):10-14. doi: 10.3969/j.issn.1007-2276.2000.05.003
	[ Chen N J, Li J G.Match straight line based on line support region[J]. Infrared and Laser Engineering, 2000,29(5):10-14. ] doi: 10.3969/j.issn.1007-2276.2000.05.003
[15]	Wang Z, Liu H, Wu F.MSLD: A robust descriptor for line matching[J]. Pattern Recognition, 2009,42(5):941-953. doi: 10.1016/j.patcog.2008.08.035
[16]	Zhang L, Koch R.An efficient and robust line segment matching approach based on LBD descriptor and pairwise geometric consistency[J]. Journal of Visual Communication & Image Representation, 2013,24(7):794-805. doi: 10.1016/j.jvcir.2013.05.006
[17]	王竞雪,张雪,朱红,等.结合区域仿射变换的MSLD描述子与直线段匹配[J].信号处理,2018,34(2):183-191.
	[ Wang J X, Zhang X, Zhu H, et al.MSLD descriptor sombined regional affine transformation and straight line matching[J]. Journal of Signal Processing, 2018,34(2):183-191. ]
[18]	武盟盟,焦伟利,龙腾飞,等.基于描述子与几何约束的直线段匹配[J].计算机工程与设计,2014,35(6):1983-1987. doi: 10.3969/j.issn.1000-7024.2014.06.021
	[ Wu M M, Jiao W L, Long T F, et al.Line segment matching based on descriptor and geometric constraints[J]. Computer Engineering and Design, 2014,35(6):1983-1987. ] doi: 10.3969/j.issn.1000-7024.2014.06.021
[19]	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. doi: 10.3969/j.issn.0372-2112.2015.12.024
	[ Miao J, Chu J, Zhang J M.An affine invariant line descriptor and line matching[J]. Acta Electronica Sinica, 2015,43(12):2505-2512. ] doi: 10.3969/j.issn.0372-2112.2015.12.024
[20]	林意,李进明.基于几何不变量的直线匹配方法[J].计算机工程与设计,2011,32(10):3465-3469.
	[ Lin Y, Li J M.Match method of straight line based on geometric invariance[J]. Computer Engineering and Design, 2011,32(10):3465-3469. ]
[21]	Fan B, Wu F, Hu Z.Robust line matching through line-point invariants[J]. Pattern Recognition, 2012,45(2):794-805. doi: 10.1016/j.patcog.2011.08.004
[22]	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 J X, Song W D, Wang W X.Line matching algorithm for 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
[23]	梁艳,盛业华,张卡,等.利用局部仿射不变及核线约束的近景影像直线特征匹配[J].武汉大学学报·信息科学版,2014,39(2):229-233. doi: 10.13203/j.whugis20120611
	[ Liang Y, Sheng Y H, Zhang K, et al.Linear feature matching method based on local affine invariant and epipolar constraint for close-range image[J]. Geomatics and Information Science of Wuhan University, 2014,39(2):229-233. ] doi: 10.13203/j.whugis20120611
[24]	Lowe D G.Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004,60(2):91-110. doi: 10.1023/B:VISI.0000029664.99615.94

参数	第1组	第2组	第3组	第4组
α	0.5	0.5	0.75	0.75
β	0.5	0.75	0.5	0.75

实验影像	两影像上线提取数目/条	α、β	MN/对	MC/对	MR/%
图5(a)	(1011, 948)	0.50、0.50	529	526	99.43
		0.50、0.75	598	594	99.33
		0.75、0.50	567	563	99.29
		0.75、0.75	641	635	99.06
图5(b)	(874, 686)	0.50、0.50	213	207	97.18
		0.50、0.75	238	232	97.48
		0.75、0.50	250	244	97.60
		0.75、0.75	270	262	97.04
图5(c)	(488, 526)	0.50、0.50	143	142	99.30
		0.50、0.75	168	167	99.40
		0.75、0.50	161	161	100.00
		0.75、0.75	176	175	99.43
图5(d)	(572, 427)	0.50、0.50	194	194	100.00
		0.50、0.75	229	226	98.69
		0.75、0.50	221	218	98.64
		0.75、0.75	254	250	98.43
图5(e)	(996, 1017)	0.50、0.50	234	225	96.15
		0.50、0.75	296	286	96.62
		0.75、0.50	262	252	96.18
		0.75、0.75	323	307	95.05

实验影像	不同算法	MN/对	MP/对	MC/%
图5(a)	文献[15]	554	522	94.2
	文献[23]	223	220	98.7
	本文算法	567	563	99.3
图5(b)	文献[15]	24	9	37.5
	文献[23]	54	54	100
	本文算法	250	244	97.6
图5(c)	文献[15]	148	115	77.7
	文献[23]	101	99	98.1
	本文算法	161	161	100
图5(d)	文献[15]	271	250	92.2
	文献[23]	80	77	96.3
	本文算法	221	218	98.6

局部点、线仿射不变性约束的近景影像直线段匹配

Line Segment Matching based on Local Point-Line Affine Invariance Constraints for Close-Range Image

RichHTML

PDF (PC)

赞

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 24

相关文章 1

Metrics

本文评价

推荐阅读 0