视觉导航中陀螺仪辅助特征点匹配算法

徐超; 范耀祖; 沈晓蓉

视觉导航中陀螺仪辅助特征点匹配算法

北京航空航天大学自动化科学与电气工程学院, 北京 100191

基金项目: 国家863高技术计划资助项目(2007AA12Z328)

详细信息

中图分类号: V 249.32⁺5
计量
- 文章访问数: 3338
- HTML全文浏览量: 287
- PDF下载量: 1460
- 被引次数: 0
出版历程
- 收稿日期: 2009-08-13
- 网络出版日期: 2010-10-31

Gyroscope aided feature matching method in vision navigation

School of Automation Science and Electrical Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100191, China

摘要

摘要: 为了解决视觉导航中无摄像平台条件下特征点匹配不准确的问题,提出了一种利用导航系统中陀螺仪输出辅助进行特征点匹配的方法.构建了陀螺仪角速度输出与特征点坐标变化之间的关系,分别采用相关系数匹配和双向匹配进行特征点匹配和匹配检验,通过插值计算得到亚像素精度的匹配结果;分析了该方法的各种误差来源,并对陀螺仪输出误差和摄像机焦距误差的影响大小进行了分析.实验表明:相对于SIFT (Scale Invariant Feature Transform)方法,此处提出的匹配方法准确性有了较大提高,并且在原系统基础上不需要增加额外设备,具有较好的实用性.
- 视觉导航 /
- 特征点匹配 /
- 陀螺仪 /
- 亚像素 /
- 线性插值
Abstract: In order to solve the problem of feature points mismatching when there is no camera platform in vision navigation, a gyroscope aided points matching method was proposed. The relationship between the output of gyroscope and the coordinate changes of features was built. The nearest cross-correlation method and bidirectional matching algorithm was adopted to perform the point matching and matching result verification respectively. The sub-pixel matching result was obtained by interpolation. The error sources of the matching method were analyzed. The effect of the gyroscope output and the focus length calculation errors among them was calculated. The experiment of real scene proved that, the proposed method has much improvement in accuracy over scale invariant feature transform (SIFT), and it also has a better practicability for it does not need any other equipment except the existing ones.
- vision navigation /
- feature match /
- gyroscope /
- sub-pixel /
- interpolation

HTML全文

参考文献(1)

[1] Harris C,Stephens M.A combined corner and edge detector //4th Alvey Vision Conference.Manchester:IEEE Press,1988:147-151 [2] 黄锡山,陈慧津,陈哲.景像匹配误匹配点的剔除算法[J].中国图象图形学报,2002,7(A)(8):783-787 Huang Xishan,Chen Huijin,Chen Zhe.Algorithms of eliminating the mismatching points in scene matching guidance system[J].Journal of Image and Graphics,2002,7(A)(8):783-787(in Chinese) [3] Xu Chao,Fan Yaozu,Zhou Yanli.A strong local invariant descriptor and mismatched points eliminating method in vision navigation // Wang Jixin.Proceedings of IEEE International Symposium on Knowledge Acquisition and Modeling Workshop.Wuhan,China:IEEE Press,2008:470-473 [4] Lowe D G.Distinctive image feature from scale-invariant keypoints[J].International Journal of Computer Vision,2004,40(2):91-110 [5] 张少辉,沈晓蓉,范耀祖.一种基于图像特征点提取及匹配的方法[J].北京航空航天大学学报,2008,34(5):516-519 Zhang Shaohui,Shen Xiaorong,Fan Yaozu.Method in image-s feature extraction and matching[J].Journal of Beijing University of Aeronautics and Astronautics,2008,34(5):516-519(in Chinese) [6] 张广军.机器视觉[M].北京:科学出版社,2005:273-276 Zhang Guangjun.Machine vision[M].Beijing:Science Press,2005:273-276(in Chinese) [7] 袁信,俞济祥,陈哲.导航系统[M].北京:航空工业出版社,1993:30-48 Yuan Xin,Yu Jixiang,Chen Zhe.Navigation system[M].Beijing:Aviation Industry Press,1993:30-48(in Chinese) [8] Jean-Yves B.Camera calibration toolbox for matlab .Coimbra:Jorge Lobo,2008.http://www.vision.caltech.edu/bouguetj /calib _doc/index.html [9] Zhang Zhengyou.Flexible camera calibration by viewing a plane from unknown orientations //IEEE.Proceedings of the Seventh International Conference on Computer Vision.Kerkyra,Greece:IEEE Press,1999:666-673 [10] Lobo J,Dias J.Relative pose calibration between visual and inertial sensors[J].The International Journal of Robotics Research,2007,26(6):561-575

施引文献

资源附件(0)

访问统计