期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

基于掩模和俯仰角补偿的视觉自运动估计

Monocular Egomotion Estimation of Mobile Robot Based on Masked M-Estimator and Pitch-Compensated Algorithms
原文传递
导出
摘要 提出了一种基于掩模M估计和俯仰角补偿的移动机器人自运动的单目视觉估计方法。在6-DOF自运动模型的基础上,提出了一种适合于乡村道路环境的4-DOF自运动估计模型,以此为基础,采用一种多尺度的超复小波相位相干理论来鲁棒地估计缺乏规则纹理的路面图像的微小运动,设计了一种掩模M估计对运动向量进行优化估计,并提出了一种俯仰角补偿算法克服乡村路面颠簸有效地估计机器人偏航角、俯仰角增量和平移增量。在乡村道路环境下,利用某自主机器人采集的实际数据对算法进行了仿真试验,运动估计结果与车载GPS/INS捷联系统做了对照。实验结果表明了自运动估计算法的有效性。 Egomotion estimation based on masked M-estimator and pitch-compensated algorithms were proposed. A 4-DOF egomotion estimation model was designed for the mobile robot on country road, the image motion was estimated through an efficient hyper-complex wavelet phase coherent theory, which could robustly detect the multiscale image motions even if there are few regular textures in country road. Pitch-compensated and masked M-estimator algorithms were proposed to estimate the instantaneous steering angle, pitch angle and traveling distance efficiently. The algorithms were successfully validated on videos from an automotive platform on the country road, and the egomotion estimation results from our method were compared to the ground truth measured with a GPS/INS joint system. These experimental results indicate that the algorithms are effective.
作者 王彩玲 赵春霞
机构地区 南京邮电大学自动化学院 南京理工大学计算机科学与技术学院
出处 《系统仿真学报》 CAS CSCD 北大核心 2012年第11期2319-2323,2328,共6页 Journal of System Simulation
基金 国家自然科学基金重大研究计划重点项目(90820306) 国家自然科学基金重点项目(60632050) 国防基础技术研究项目(K1702020302)
关键词 单目视觉 自运动估计 俯仰角补偿 掩模M估计 monocular vision egomotion pitch-compensated masked M-estimator
分类号 V448.22 [航空宇航科学与技术—飞行器设计]
  • 相关文献

参考文献16

  • 1Borenstoin J, Everett H R, Feng L, Wehe D. Mobile Robot Positioning: Sensors and Techniques [J]. Journal of Robotic Systems, Special Issue on Mobile Robots (S0741-2223), 1997, 14(4): 231-249.
  • 2Jason C, Rahul S, Illah N, Aroon P. A Robust Visual Odometry and Precipice Detection System Using Consumer-grade Monocular Vision [C]// Proceeding of International Conference on Robotics and Automation. Barcelona, Spain: IEEE, 2005: 3421-3427.
  • 3Wilhelm B, Bir B. Estimating 3-D Egomotion from Perspective Image Sequences [J]. IEEE Trans. on Pattem analysis and machine intelligence (S0162-8828), 1990, 12(11): 1040-1058.
  • 4Badino H. Binocular Ego-Motion Estimation for automotive application [D]. Frankfurt am Main, Germany: Goethe Frankfurt University, 2008.
  • 5Clark F O, Larry H M, Marcel S, Mark W M. Rover navigation using stereo ego-motion [J]. Robotics and Autonomous Systems (S0921-8890), 2003, 43(4): 215-229.
  • 6David N R, Oleg N, James B. Visual odometry for ground vehicle applications [J]. Journal of Field Robotics (S1556-4959), 2006, 23(1) 3-20.
  • 7岳富占,崔平远,崔祜涛.基于视觉序列图像的月球车自运动估计技术[J].系统仿真学报,2007,19(13):3033-3037. 被引量：2
  • 8Davide S, Roland S. Appearance-Guided Monocular Omnidirectional Visual Odometry for Outdoor Ground Vehicles [J]. IEEE Trans. on Robotics (S1552-3098). 2008, 24(5): 1015-1026.
  • 9Michal I, Benny R, Shmuel P. Recovery of Egomotion Using Region Alignment [J]. IEEE Trans. on Pattern analysis and machine intelligence (S0162-8828). 1997, 19(3): 268-272.
  • 10Tardif J P, Pavlidis Y, Daniilidis K. Monocular Visual Odometry in Urban Environments Using an Omnidirectional Camera [C]// Proceeding of IEEE/RSJ International Conference on Intelligent Robots and Systems. Nice, France: IEEE, 2008:2531-2538.

二级参考文献48

  • 1Fintzel K, Bendahan R, Vestri C, etal. 3D Parking assistant system[A]. Proceedings of the IEEE Intelligent Vehicles Symposium[C]. Piscataway, NJ, USA: IEEE, 2004. 881-886.
  • 2Wybo S, Bendahan R, Bougnoux S, et al. Movement detection for safer backward maneuvers[A]. Proceedings of the IEEE Intelligent Vehicles Symposium[C]. Piscataway, NJ, USA: IEEE, 2006. 453-459.
  • 3Yamaguchi K, Kato T, Ninomiya Y. Moving obstacle detection using monocular vision[A]. Proceedings of the IEEE Intelligent Vehicles Symposium[C]. Piscataway, NJ, USA: IEEE, 2006. 288-293.
  • 4Suzuki T, Kanade T. Measurement of vehicle motion and orientation using optical flow[A]. Proceedings of the IEEE Conference on Intelligent Transportation Systems[C]. Piscataway, NJ, USA: IEEE, 1999. 25-30.
  • 5Hartiey R, Zisserman A. Multiple View Geometry in Computer Vision[M]. Cambridge, UK: Cambridge University Press, 2004.
  • 6Stein G, Mano O, Shashua A. A robust method for computing vehicle ego-motion[A]. Proceedings of the IEEE Intelligent Vehicles Symposium[C]. Piscataway, NJ, USA: IEEE, 2000. 362-368.
  • 7Scharer S, Baltes J, Anderson J. Practical ego-motion estimation for mobile robots[A]. Proceedings of the IEEE Conference on Robotics, Automation and Mechatronics[C]. Piscataway, NJ, USA: IEEE, 2004. 921-926.
  • 8Yamaguchi K, Kato T, Ninomiya Y. Vehicle ego-motion estimation and moving object detection using a monocular camera[A]. Proceedings of the International Conference on Pattern Recognition[C]. Piscataway, NJ, USA: IEEE, 2006. 610-613.
  • 9Ke Q, Kanade T. Transforming camera geometry to a virtual downward-looking camera: Robust ego-motion estimation and ground-layer detection[A]. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition[C]. Los Alamitos, CA, USA: IEEE Computer Society, 2003. 390-397.
  • 10Elnagar A, Basu A. Robust detection of moving objects by a moving observer on planar surfaces[A]. Proceedings of the IEEE International Conference on Robotics and Automation[C]. Piscataway, NJ, USA: IEEE, 1995. 2347-2352.

共引文献32

系统仿真学报
2012年 第11期

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部