基于几何约束及0-1规划的视频帧间线段特征匹配算法

doi:10.11772/j.issn.1001-9081.2017.08.2292

计算机应用 ›› 2017, Vol. 37 ›› Issue (8): 2292-2297.DOI: 10.11772/j.issn.1001-9081.2017.08.2292

• 计算机视觉与虚拟现实 • 上一篇下一篇

基于几何约束及0-1规划的视频帧间线段特征匹配算法

李海丰^1,2, 胡遵河¹, 范龙飞¹, 姜子政¹, 陈新伟²

1. 中国民航大学计算机科学与技术学院, 天津 300300;
2. 福建省信息处理与智能控制重点实验室(闽江学院), 福州 350121

收稿日期:2017-01-16 修回日期:2017-03-03 出版日期:2017-08-10 发布日期:2017-08-12
通讯作者: 陈新伟
作者简介:李海丰(1984-),男,内蒙古通辽人,讲师,博士,CCF会员,主要研究方向:计算机视觉、机器人导航;胡遵河(1989-),男,山东菏泽人,硕士研究生,主要研究方向:视觉导航;范龙飞(1989-),男,河北邢台人,助理实验师,硕士,主要研究方向:模式识别;姜子政(1990-),男,辽宁本溪人,硕士研究生,主要研究方向:计算机视觉;陈新伟(1984-),男,福建龙岩人,讲师,博士,主要研究方向:机器学习。
基金资助:
国家自然科学基金资助项目（61305107）；天津市应用基础与前沿技术研究计划重点项目（14JCZDJC32500）；福建省信息处理与智能控制重点实验室开放课题项目（MJUKF201732）；中央高校基本科研业务费资助项目（3122016B006）。

Line segment feature matching algorithm across video frames based on geometric constraints and 0-1 programming

LI Haifeng^1,2, HU Zunhe¹, FAN Longfei¹, JIANG Zizheng¹, CHEN Xinwei²

1. College of Computer Science and Technology, Civil Aviation University of China, Tianjin 300300, China;
2. Fujian Provincial Key Laboratory of Information Processing and Intelligent Control(Minjiang University), Fuzhou Fujian 350121, China

Received:2017-01-16 Revised:2017-03-03 Online:2017-08-10 Published:2017-08-12
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61305107),the Tianjin Key Research Program of Application Foundation and Advanced Technology (14JCZDJC32500),the Open Fund Project of Fujian Provincial Key Laboratory of Information Processing and Intelligent Control (MJUKF201732),the Fundamental Research Funds for the Central Universities (3122016B006).

摘要/Abstract

摘要： 针对线段因遮挡、断裂以及端点提取不准确等原因造成的线段特征匹配困难问题，特别是现有匹配算法在匹配过程中出现"多配多"时直接采取"最相似匹配"而导致丢失大量真实匹配的问题，提出了一种基于多重几何约束及0-1规划的线段特征匹配算法。首先，基于校正后视频帧间线段特征的空间相邻性计算线段匹配的初始候选集；然后，基于极线约束、单应矩阵模型约束以及点-线相邻性约束等多重几何约束，对候选集进行筛选从而剔除部分错误匹配；其次，将线段匹配问题建模为一个大规模0-1规划问题；最后，设计了一种基于分组策略的两阶段求解算法对该问题进行求解，从而实现线段特征的"一配一"精确匹配。实验结果表明，该算法与LS（Line Sigature）、LJL（Line-Junction-Line）方法相比，匹配正确率接近，但匹配线段数量分别提高了60%和11%。所提算法可以实现视频帧间的线段特征匹配，为基于线特征的视觉SLAM（Simultaneously Localization and Mapping）奠定基础。

关键词: 线段匹配, 几何约束, 0-1规划, 特征匹配, 视觉SLAM

Abstract: To deal with the problems in line segment matching due to occlusion, fragmentation and inaccurate extraction of line segment endpoints, especially when the criteria of "most similar matching" was taken in "multiple-to-multiple" matching which may lead to fateful true correspondences lost, a line segment matching algorithm based on geometric constraints and 0-1 programming was proposed. Firstly, a candidate matching set was initially computed based on the spatial adjacency after correcting the vedio frames. Secondly, the multiple geometric constraints, such as epipolar constraint, homography matrix and point-to-line adjacency, were employed to remove the false positive correspondences. Then, the matching problem was modeled into a large scale 0-1 programming. Finally, a two-stage method based on grouping strategy was designed to solve this problem, so as to realize the "one to one" exact matching of line segment feature. The experimental results show that, compared with LS (Line Sigature) and LJL (Line-Junction-Line) methods, the propsed method has a similar performance in correct matching ratio but a larger matching amount over 60% and 11%, respectively. The proposed method can fulfill the line segment matching across vedio frames, which lays the foundation for line-based visual SLAM (Simultaneously Localization and Mapping).

Key words: line segment matching, geometric constraint, 0-1 programming, feature matching, visual SLAM (Simultaneously Localization and Mapping)

中图分类号:

TP242

李海丰, 胡遵河, 范龙飞, 姜子政, 陈新伟. 基于几何约束及0-1规划的视频帧间线段特征匹配算法[J]. 计算机应用, 2017, 37(8): 2292-2297.

LI Haifeng, HU Zunhe, FAN Longfei, JIANG Zizheng, CHEN Xinwei. Line segment feature matching algorithm across video frames based on geometric constraints and 0-1 programming[J]. Journal of Computer Applications, 2017, 37(8): 2292-2297.

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[C]//ECCV 2006:Proceedings of the 20069th Equopean Conference on Computer Vision, LNCS 3951. Berlin:Springer-Verlag, 2006:404-417.
[3] 武涛,孙凤池,苑晶,等.一种基于线段特征的室内环境主动SLAM方法[J].机器人,2009,31(2):166-170,178. (WU T, SUN F C, YUAN J, et al. An active SLAM approach based on line segment feature in indoor environment[J]. Robot, 2009, 31(2):166-170, 178.)
[4] WANG Z, WU F, HU Z. MSLD:a robust descriptor for line matching[J]. Pattern Recognition, 2009, 42(5):941-953.
[5] ZHANG L, KOCH R. An efficient and robust line segment matching approach based on LBD descriptor and pairwise genometric consistency[J]. Journal of Visual Communication and Image Representation, 2013, 24(7):794-850.
[6] WANG Z-H, ZHI S-S, LIU H-M. MSHS:the mean-standard deviation curve matching algorithm in HSV space[C]//ICMLC 2012:Proceedings of the 2012 International Conference on Machine Learning and Cybernetics. Piscataway, NJ:IEEE, 2012:1064-1069
[7] CUI X, KAN J, LI W. A new line matching method based on color invariantsin the RGB orthogonal color space[J]. Journal of Computational Information Systems, 2015, 11(9):3265-3273.
[8] 王伟玺,安菲佳,王竞雪.多重约束条件下的影像直线匹配算法研究[J].测绘科学,2014,39(11):15-19. (WANG W X, AN F J, WANG J X. Line matching algorithm for imagery under multiple constraint conditions[J]. Science of Surveying and Mapping, 2014, 39(11):15-19.).
[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. (LOU A Y, SONG W D, LIU W. Matching straight lines on the basic of homography[J]. Remote Sensing Information, 2011(2):9-13.)
[10] 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):299-233. (LIANG Y, SHENG Y H, ZHANG K, et al. Linear feature matching method based on local affine invariant and epiolar constraint close-range images[J]. Geomatics and Information Science of Wuhan University,2014, 39(2):299-233.)
[11] 李俊瑶,顾宏斌,孙瑾,等.基于多重约束条件的线特征多级匹配方法[J].计算机科学,2014,41(S2):83-87. (LI J Y, GU H B, SUN J, et al. Multi-lever line matching method based on multiple constraints[J]. Computer Science, 2014, 41(S2):83-87.)
[12] FAN B, WU F, HU Z. Robust line matching through line-point invariants[J]. Pattern Recognition, 2012, 45(2):794-805.
[13] 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.
[14] LU W, ULRICH N,SUYA Y. Wide-baseline image matching using line signatures[C]//ICCV 2009:Proceedings of the 2009 IEEE International Conference on Computer Vision. Washington, DC:IEEE Computer Society, 2009:1311-1318.
[15] LI K, YAO J, LU X H. Hierarchical line matching based on Line-Junction-Line structure descriptor and local homography estimation[J]. Neurcomputing, 2016, 184(C):207-220.
[16] 文贡坚.一种基于特征编组的直线立体匹配全局算法[J].软件学报,2006,16(12):2471-2484. (WEN G J. A global algorithm for straight line stereo matching based on feature grouping[J]. Journal of Software, 2006, 16(12): 2471-2484.)
[17] FU K-P, SHEN S-H, HU Z-Y. Line matching across views based on multiple view stereo[J]. Acta Automatica Sinica, 2014, 40(8): 1680-1689.
[18] VON G, JAKUBOWICZ J, MOREL J-M, et al. LSD: A fast line segment detector with a false detection control[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(4): 722-732.
[19] HARTLEY R, ZISSERMAN A. Multiple View Geometry in Computer Vision[M]. 2nd ed. New York: Cambridge University Press, 2004: 1-206.
[20] LU Y, SONG D. Visual navigation using heterogeneous landmarks and unsupervised geometric constraints[J]. IEEE Transactions on Robotics, 2015, 31(3): 1-14.

基于几何约束及0-1规划的视频帧间线段特征匹配算法

Line segment feature matching algorithm across video frames based on geometric constraints and 0-1 programming

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

[1]	欧莉莉, 邵峰晶, 孙仁诚, 隋毅. 基于半监督方法的脑梗死图像识别[J]. 计算机应用, 2021, 41(4): 1221-1226.
[2]	王彬溶, 谭代伦, 郑伯川. 基于旅行商问题转化和遗传算法求解汽配件喷涂顺序[J]. 计算机应用, 2021, 41(3): 881-886.
[3]	胡立华, 左威健, 聂瑶瑶. 基于加权相似性度量的特征匹配方法[J]. 计算机应用, 2021, 41(2): 511-516.
[4]	管皓, 秦小林, 饶永生, 曹晟. 基于Web的动态几何软件领域模型及其应用[J]. 计算机应用, 2020, 40(4): 1127-1132.
[5]	薄单, 李宗春, 王晓南, 乔涵文. 适用于倾斜影像的加速KAZE-SIFT特征提取算法[J]. 计算机应用, 2019, 39(7): 2093-2097.
[6]	李南云, 王旭光, 吴华强, 何青林. 基于灰度塔评分的匹配模型构建在无人机网络视频拼接中的应用[J]. 计算机应用, 2019, 39(5): 1480-1484.
[7]	马兰, 王京杰, 陈焕. 基于内容挖掘的广域信息管理系统业务数据安全[J]. 计算机应用, 2019, 39(2): 488-493.
[8]	陆明炽, 王守华, 李云柯, 纪元法, 孙希延, 邓桂辉. 基于特征匹配和距离加权的蓝牙定位算法[J]. 计算机应用, 2018, 38(8): 2359-2364.
[9]	叶峰, 洪峥, 赖乙宗, 赵雨亭, 谢先治. 基于匹配质量提纯的改进D-Nets算法[J]. 计算机应用, 2018, 38(4): 1121-1126.
[10]	李维鹏, 曾静, 张国良. 基于改进Markov邻域的非线性0-1规划智能算法加速策略[J]. 计算机应用, 2016, 36(9): 2416-2421.
[11]	阮峰, 张辉, 李宣伦. 大输液异物检测图像快速位移补偿方法[J]. 计算机应用, 2016, 36(12): 3442-3447.
[12]	肖衡吕绍和. 认知网络融合干扰消除的高效频谱感知机制[J]. 计算机应用, 2014, 34(5): 1243-1246.
[13]	李志华李秋峦. 连续跟踪状态下基于可分性特征的目标优化分类[J]. 计算机应用, 2014, 34(5): 1275-1278.
[14]	王晋疆刘阳吴明云. 基于快速鲁棒特征的CamShift跟踪算法[J]. 计算机应用, 2013, 33(02): 499-502.
[15]	孟勃韩广良. 基于改进的尺度不变特征变换特征点匹配的电子稳像算法[J]. 计算机应用, 2012, 32(10): 2817-2820.