近景影像的直线分层匹配

doi:10.13474/j.cnki.11-2246.2023.0065

测绘通报 ›› 2023, Vol. 0 ›› Issue (3): 16-21.doi: 10.13474/j.cnki.11-2246.2023.0065

近景影像的直线分层匹配

程飞¹, 张子文², 丛日盛³, 金泽林⁴

1. 山西工程职业学院, 山西太原 030000;
2. 广州航海学院, 广东广州 510725;
3. 辽宁省化工地质勘查院有限责任公司, 辽宁锦州 121007;
4. 辽宁电力勘测设计院有限公司, 辽宁沈阳 110000

收稿日期:2022-03-14 修回日期:2023-01-06 发布日期:2023-04-04
作者简介:程飞(1988-),男,硕士,讲师,从事工程测量教学工作。E-mail:546831858@qq.com
基金资助:
国家自然科学基金（61974035）

Hierarchical line matching of close range images

CHENG Fei¹, ZHANG Ziwen², CONG Risheng³, JIN Zelin⁴

1. Shanxi Enginerring Vocational College, Taiyuan 030000, China;
2. Guangzhou Maritime College, Guangzhou 510725, China;
3. Liaoning Chemical Geological Exploration Institute Co., Ltd., Jinzhou 121007, China;
4. Liaoning Electric Power Survey& Design Institute Co., Ltd., Shenyang 110000, China

Received:2022-03-14 Revised:2023-01-06 Published:2023-04-04

摘要/Abstract

摘要： 针对近景影像直线匹配过程中局部几何约束存在漏选和部分灰度描述符在某些场景变换下匹配无力等问题，本文提出了一种近景影像的直线分层匹配方案。该方案利用可靠同名点获取核线方程与透视变换矩阵，并进行目标直线候选直线的二次筛选。在进行检核方式的选取上，若存在相机投影矩阵则计算对应的重投影误差，否则计算优化后的MSLD描述符向量间的余弦相似度。设定合理阈值作为是否接受为同名直线的最终门限。使用网络公开数据集进行算法的分析验证，并与其他直线匹配算法进行对比。试验结果证明了本文方案的可行性与准确性，并对多种变换影像有着良好的适应性。

关键词: 近景影像, 分层匹配, 全局约束, 重投影误差, 描述符约束

Abstract: In view of the geometric local constraints in line matching of close range images, there are some problems, such as missing selection and weak matching of descriptors under certain scene transformation. In this paper, a line hierarchical matching scheme for close range image is proposed. In this scheme, the kernel equation and perspective transformation matrix are obtained with reliable homonymous points, the target line is screened twice, and whether there is a reliable camera projection matrix in close range image is selected as the check method. If there is a camera projection matrix, the corresponding re projection error is calculated, Otherwise, the cosine similarity between the optimized MSLD descriptor vectors is calculated, and their reasonable thresholds are set as the final threshold to accept the line with the same name. The algorithm is analyzed and verified by using the network public data set. The experimental results prove the feasibility of this scheme, and can obtain accurate and stable line matching results of the same name. At the same time, it has good adaptability to a variety of transformed images.

Key words: close range image, hierarchical matching, global constraint, reprojection error, descriptor constraint

中图分类号:

程飞, 张子文, 丛日盛, 金泽林. 近景影像的直线分层匹配[J]. 测绘通报, 2023, 0(3): 16-21.

CHENG Fei, ZHANG Ziwen, CONG Risheng, JIN Zelin. Hierarchical line matching of close range images[J]. Bulletin of Surveying and Mapping, 2023, 0(3): 16-21.

参考文献

[1] 刘肃艳, 王竞雪, 沈昭宇, 等.结合线对几何特征及单线描述符约束的直线匹配算法[J/OL].武汉大学学报(信息科学版):1-17[2022-01-16].-://ch.whu.edu.cn/cn/article/doi/10.13203/j.whugis20210147.
[2] 陆胜寒. 基于影像几何约束匹配策略的三维重建方法研究与实现[D]. 北京:清华大学, 2018.
[3] 张焱鑫. 基于直线特征的多视图几何三维重建算法研究与实现[D]. 秦皇岛:燕山大学, 2019.
[4] 刘肃艳, 王竞雪. 结合同名点及核线约束的近景影像直线匹配[J]. 测绘科学, 2019, 44(10):128-135.
[5] 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.
[6] 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.
[7] 李依泽, 宋伟东, 李淼. 三角网约束的航空影像直线匹配方法[J]. 遥感信息, 2018, 33(1):58-63.
[8] 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.
[9] WANG Zhiheng, WU Fuchao, HU Zhanyi. MSLD:a robust descriptor for line matching[J]. Pattern Recognition, 2009, 42(5):941-953.
[10] WANG Lu, NEUMANN U, YOU Suya. Wide-baseline image matching using Line Signatures[C]//Proceedings of the 12th IEEE International Conference on Computer Vision. Kyoto:IEEE, 2010:1311-1318.
[11] 高峰. 基于弹性特征编组的图像配准方法[J]. 计算机学报, 2018, 41(11):2467-2481.
[12] 韩丹, 宋伟东, 王竞雪. 自适应分区的相位编组直线提取算法[J]. 计算机应用, 2013, 33(6):1691-1694.
[13] LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110.
[14] FISCHLER M, BOLLES R. Random sample consensus:a paradigm for model fitting with applications to image analysis and automated cartography[J]. CACM, 1981, 24(6):381-395.
[15] AKINLAR C, TOPAL C. Edlines:Real-time line segment detection by Edge Drawing (ed)[C]//Proceedings of the 18th IEEE International Conference on Image Processing.Brussels:IEEE, 2011:2837-2840.
[16] 高翔, 张涛, 刘毅. 视觉SLAM十四讲:从理论到实践[M]. 北京:电子工业出版社, 2017.
[17] MORÉ J J. The Levenberg-Marquardt algorithm:implementation and theory[J].Numerical Analysis, 1978, 630:105-116.
[18] 张鑫, 王竞雪, 刘肃艳, 等. 基于可靠匹配点约束的遥感影像密集匹配[J]. 地球信息科学学报, 2021, 23(8):1508-1523.

近景影像的直线分层匹配

Hierarchical line matching of close range images

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价

[1]	秦育罗, 宋伟东, 张在岩, 孙小荣. 顾及几何特征和拓扑连续性的道路网匹配方法[J]. 测绘通报, 2021, 0(8): 55-60.
[2]	胡春梅李天烁王晏民. 基于深度图像的地面激光雷达与近景影像数据无缝纹理映射研究[J]. 测绘通报, 2015, 0(1): 66-69.
[3]	邹峥嵘邹小丹刘合凤张云生. 基于半全局多视近景影像匹配的三维建模方法[J]. 测绘通报, 2014, 0(2): 34-36.