电动VTOL飞行器双目立体视觉导航方法

张博翰; 蔡志浩; 王英勋

电动VTOL飞行器双目立体视觉导航方法

北京航空航天大学无人驾驶飞行器设计研究所, 北京 100191

基金项目: 中央高校基本科研业务费专项资金资助项目(YWF-10-02-074)

详细信息

作者简介:
张博翰(1987-), 男, 山西运城人, 硕士生, han872004@163.com.

中图分类号: V 249.31
计量
- 文章访问数: 3148
- HTML全文浏览量: 142
- PDF下载量: 1172
- 被引次数: 0
出版历程
- 收稿日期: 2010-09-10
- 网络出版日期: 2011-07-30

Binocular stereo vision navigation for electric VTOL aircraft

Research Institute of Unmanned Aerial Vehicle, Beijing University of Aeronautics and Astronautics, Beijing 100191, China

摘要

摘要: 研究了在未知的、动态的室内走廊环境中,采用双目立体视觉引导电动VTOL(Vertical Take-Off and Landing)飞行器安全飞行的方法.使用安装在飞机上的两个微型摄像头从不同的位置获取图像,由双目立体视觉理论恢复其周围环境特征点的三维坐标.采用角点匹配方法计算视差,实现无人机在走廊中的横向坐标定位.采用区域灰度相关算法进行立体匹配获取视差图,从视差图上检测出障碍物,并给出避障导航点.初步实验验证表明,该方法可行性较高,可以作为进一步研究的基础.
- 电动VTOL飞行器 /
- 视觉导航 /
- 双目立体视觉 /
- 障碍物检测和躲避
Abstract: A stereo vision-based navigation method for the electric vertical take-off and landing(VTOL) aircraft to wander safely through an unknown dynamic indoor corridor was researched. The aircraft uses two cameras to obtain images from different locations, and then the theory of binocular stereo vision was used to restore the 3-D coordinates of the feature points in front of the aircraft. Corner matching method was applied to calculate the disparity of the detected corners on the wall. Thus, the horizontal position of unmanned aerial vehicle(UAV) in the corridor was revealed. The area-based stereo matching algorithm was presented to get the dense disparity map of the original image pair, then obstacles were extracted from the disparity map and the navigation points were generated for the UAV to avoid obstacles. Preliminary experiment shows that the method is feasible and can be used as a basis for further research.
- electric VTOL aircraft /
- visual navigation /
- binocular stereo vision /
- obstacle detect and avoid

HTML全文

参考文献(1)

[1] Yoko Watanabe,Anthony J Calise,Eric N Johnson.Vision-based obstacle avoidance for UAVs //AIAA Guidance,Navigation and Control Conference and Exhibit.South Carolina:American Institute of Aeronautics and Astronautics Press,2007:20-23 [2] Bachrach A G.Autonomous flight in unstructured and unknown indoor enviornments .Dept of Electrical Engineering and Computer Science,Massachusetts Institute of Technology.2009:119-126 [3] Koray C,Chung S J,Matthew C,et al.Monocular vision SLAM for indoor aerial vehicles //The 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.USA St Louis:IEEE Computer Society Press,2009:1566-1573 [4] Gary Bradski,Adrian Kaebler.学习OpenCV(中文版)[M].于仕琪,刘瑞祯,译.北京:清华大学出版社,2009:178-254 Gary Bradski,Adrian Kaebler.Learning OpenCV(Chinese version)[M].Translated by Yu Shiqi,Liu Ruizhen.Beijng:Tsinghua University Perss,2009:178-254(in Chinese) [5] Kanade T,Okutomi M.A stereo matching algorithm with an adaptive window:theory and experiment[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1994,6(9):920-932 [6] 杜歆.用于导航的立体视觉系统 .杭州:浙江大学信息学院,2003 Du Xin.Stereovision used for navigation .Hangzhou:School of Information,Zhejiang University ,2003(in Chinese) [7] Harris C,Stephens M.A combined corner and edge detector //Proceedings of the 4th Alvey Vision Conference.Manchester:Manchester University Press,1988:147-151 [8] 谢凤英,赵丹培.Visual C+ +数字图像处理[M].北京:电子工业出版社,2008:278-367 Xie Fengying,Zhao Danpei.Visual C+ + digital image processing[M].Beijing:Electronic Industry Press,2008:278-367(in Chinese) [9] Nedevschi S,Danescu R,Frentiu D,et al.High accuracy stereovision approach for obstacle detection on non-planar roads //IEEE INES.Romania:IEEE Computer Society Press,2004:211-216 [10] Lemonde T,Devy N.Obstacle detection with stereovision //Proc MECHROB.Germany:IEEE Computer Society Press,2004(3):919-924 [11] Dang T,Hoffmann C.Fast object hypotheses generation using 3D position and 3D motion //Int IEEE Workshop Mach Vis Intell Vehicles.San Diego:IEEE Computer Society Press,2005:56 [12] Claudio Caraffi,Stefano Cattani,Paolo Grisleri.Off-road path and obstacle detection using decision networks and stereo vision[J].IEEE Transactions on Intelligent Transportion Systems,2007(8):607-618

施引文献

资源附件(0)

访问统计