混合视觉系统中共同视场的确定与3维重建方法

摘要
图/表
参考文献
相关文章 (2)

全文: PDF (6066 KB) HTML ( ) 输出: BibTeX \| EndNote (RIS)
引用本文:
何炳蔚, 陈志鹏. 混合视觉系统中共同视场的确定与3维重建方法[J]. 机器人, 2011, 33(5): 614-620.. HE Bingwei, CHEN Zhipeng. Determination of the Common View Field in Hybrid Vision System and 3D Reconstruction Method. ROBOT, 2011, 33(5): 614-620..

摘要利用一个单目摄像机和一个全景摄像机搭建了相应的混合视觉系统，通过分析两者的对极几何关系，提出该系统共同视场的确定方法．在此基础上完成共同视场中场景SIFT特征的提取，并以SIFT描述器向量之间的夹角为约束条件进行特征点间的初次匹配，然后利用外极线约束消除初次匹配中的误匹配，从而获得正确的特征匹配关系，由此完成局部场景的3维重建．最后，通过实验验证了重建方法的可行性和有效性．

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	何炳蔚
	陈志鹏

关键词 ：混合视觉, SIFT特征, 共同视场, 场景重建

Abstract：A hybrid vision system is constructed by a monocular camera and an omnidirectional camera.The epipolar geometry of this system is analyzed and a method to determine the common view filed of this system is proposed.Scale invariant feature transform(SIFT) features are extracted in the common view field.During the feature points' initial matching process,the angle between the SIFT descriptor vectors is considered as the constraint condition.In order to eliminate the error matching in initial results,the epipolar constraint is used to obtain the correct feature matching.Finally,3D reconstruction of the local scene is realized.Experimental results show that the reconstruction method is feasible and practical.

Key words： hybrid vision SIFT(scale invariant feature transform) feature common view field scene reconstruction

收稿日期: 2011-01-21 录用日期: 2011-04-13

TP242.6+2

基金资助:国家自然科学基金资助项目（50605007）；天津大学精密测试技术及仪器国家重点实验室开放基金资助项目；福建省高校新世纪优秀人才支持计划资助项目（XSJRC2007-07）

通讯作者: 何炳蔚 E-mail: mebwhe@fzu.edu.cn

作者简介: 何炳蔚（1973- ），男，博士，副教授．研究领域：机器视觉，逆向工程，快速原型．
陈志鹏（1987- ），男，硕士生．研究领域：机器视觉．

链接本文:

https://robot.sia.cn/CN/ 或 https://robot.sia.cn/CN/Y2011/V33/I5/614

[1] 卢惠民,王祥科,刘斐,等.基全向视觉和前向视觉的足球机器人目标识别[J].中国图象图形学报,2006,11(11):1686-1689.Lu H M,Wang X K,Liu F,et al.Omni-vision and front vision based object recognition for soccer robots[J].Journal of Image and Graphics,2006,11(11):1686-1689.
[2] 杨鹏,高晶,刘作军,等.基于全景与前向视觉的足球机器人定位方法研究[J].控制与决策,2008,23(1):75-78,83.Yang P,Gao J,Liu Z J,et al.Localization for robot soccer based on omni-vision and front-vision[J].Control and Decision,2008,23(1):75-78,83.
[3] 张学习,杨宜民,刘润丹,等.全自主足球机器人混合视觉系统的设计与实现[J].机器人,2010,32(3):375-383.Zhang X X,Yang Y M,Liu R D,et al.Design and realization of the hybrid vision system for autonomous soccer robot[J].Robot,2010,32(3):375-383.
[4] Neves A J R,Martins D A,Pinho A J.A hybrid vision system for soccer robots using radial search lines[C]//8th Conference on Autonomous Robot Systems and Competitions.Piscataway,NJ,USA:IEEE,2008:51-55.
[5] Kaeppeler U P,Hoeferlin M,Levi P.3D object localization via stereo vision using an omnidirectional and a perspective camera[C]//IEEE International Conference on Robotics and Automation.Piscataway,NJ,USA:IEEE,2010:7-12.
[6] Voigtlander A,Lange S,Lauer M,et al.Real-time 3D ball recognition using perspective and catadioptric cameras[C]//3rd European Conference on Mobile Robots.2007.
[7] Lauer M,Schonboin M,Lange S,et al.3D-object tracking with a mixed omnidirectional stereo camera system[J].Mochatronics,2011,21(2):390-398.

[8] Svoboda T,Pajdla T,Hlavac V.Epipolar geometry for panoramic cameras[C]//5th European Conference on Computer Vision.Berlin,Germany:Springer,1998:218-231.
[9] Roberti F,Vassallo R F,Toibero J M,et al.Geometry of a hybrid stereo vision system for robotics applications[C]//V Jornadas Argentinas de Robotics.2008.
[10] Menem M,Pajdla T.Constraints on perspective images and circular panoramas[C]//British Machine Vision Conference.2004.
[11] Lowe D G.Object recognition from local scale-invariant features[C]//IEEE International Conference on Computer Vision.Piseataway,NJ,USA:IEEE,1999:1150-1157.
[12] 徐德,谭民,李原,等.机器人视觉测量与控制[M].北京:国防工业出版社,2008:130-132.Xu D,Tan M,Li Y,et al.Visual measurement and control for robots[M].Beijing:National Defense Industry Press,2008:130-132.