基于平面运动约束的移动机器人位姿估计
|
摘要
针对大部分基于单目相机的位姿估计方法只适用于平面场景的问题,提出了一种同时适用于平面场景和立体场景的单目位姿估计方法.首先,将所有图像与参考帧进行特征匹配;然后,提取每帧图像中都出现的特征点的像素坐标,并结合地平面约束和相机内参矩阵构建出观测矩阵;其次,对观测矩阵进行奇异值分解得到各帧图像的位姿估计,并利用约束矩阵解决奇异值分解不唯一问题;最后,利用光束平差法优化图像位姿,得到机器人位姿的最优估计.实验结果表明:该方法能准确对移动机器人进行位姿估计.
This paper deals with a kind of pose estimation method which can be applied in planar scene and stereo scene simultaneously.Firstly,reference frame is chosen and matched with all pictures.The pixel coordinates of the feature points which appear in every frame are chosen for further calculations.After a series of transformation,the observation matrix is formed base on pixel coordinates of feature points,ground plane constraints and the internal parameters of camera.After that,the singular value decomposition(SVD)method is used to get the relative position of mobile robot,in the meanwhile,the constraint matrix is used to solve the problem of the result of SVD is not unique.At last,bundle adjustment is used to optimize the factorization results.The experimental results demonstrate the proposed method can realize the right pose estimation of mobile robot.
This paper deals with a kind of pose estimation method which can be applied in planar scene and stereo scene simultaneously.Firstly,reference frame is chosen and matched with all pictures.The pixel coordinates of the feature points which appear in every frame are chosen for further calculations.After a series of transformation,the observation matrix is formed base on pixel coordinates of feature points,ground plane constraints and the internal parameters of camera.After that,the singular value decomposition(SVD)method is used to get the relative position of mobile robot,in the meanwhile,the constraint matrix is used to solve the problem of the result of SVD is not unique.At last,bundle adjustment is used to optimize the factorization results.The experimental results demonstrate the proposed method can realize the right pose estimation of mobile robot.
引文
[1]刘玺,方勇纯,张雪波.基于单应矩阵的位姿估计方法及应用[C]//程代展,李川.第27届中国控制会议论文集.北京:北京航空航天大学出版社,2008.
[2]杨东勇,冯形松.采用形态学算子的运动目标检测跟踪方法研究及实现[J].浙江工业大学学报,2010,38(2):149-154.
[3]RAMBACH J R,TEWARI A,PAGANI A,et al.Learning to fuse:a deep learning approach to visual-inertial camera pose estimation[C]//Proceedings of IEEE International Symposium on Mixed and Augmented Reality.Piscataway:IEEE,2016:71-76.
[4]孙建辉,刘坤.基于序列图像特征识别实时反馈伺服跟踪研究[J].浙江工业大学学报,2015,43(2):185-189.
[5]KESHMIRI M,XIE W F,MOHEBBI A.Augmented image based visual servoing of a manipulator using acceleration command[J].IEEE transactions on industrial electronics,2014,61(10):5444-5452.
[6]GALVEZLOPEZ D,SALAS M,TARDOS J D,et al.Realtime monocular object SLAM[J].Robotics&autonomous systems,2016(75):435-449.
[7]管秋,金俊杰,张剑华,等.基于最优RANSAC算法的非增加式多视图三维重建[J].浙江工业大学学报,2015,43(5):473-478.
[8]TOMASI C,KANADE T.Shape and motion from image streams under orthography:a factorization method[J].International journal of computer vision,1992,9(2):137-154.
[9]DAI Yuchao,LI Hongdong,HE Mingyi.Projective multiview structure and motion from element-wise factorization[J].IEEE transactions on pattern analysis and machine intelligence,2013,35(9):2238-2251.
[10]WANG G,ZELEK J S,WU Q M J,et al.Robust rank-4affine factorization for structure from motion[C]//Proceedings of IEEE Workshop on Applications of Computer Vision.Piscataway:IEEE,2013:180-185.
[11]LI H.Multi-view structure computation without explicitly estimating motion[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE,2010:2777-2784.
[12]LU G.Image-based indoor localization system based on 3D SfM model[C]//Proceedings of the International Society for Optics and Photonics on IS&T/SPIE Electronic Imaging.San Francisco,USA:SPIE,2014.
[13]OLIENSIS J.Structure from linear or planar motions[C]//1996IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE,1996:335-342.
[14]VIDAL R,OLIENSIS J.Structure from planar motions with small baselines[C]//Proceeding of European Conference on Computer Vision.Berlin Heidelberg:Springer,2002:383-398.
[15]TAN T N,BAKER K D,SULLIVAN G D.3Dstructure and motion estimation from 2Dimage sequences[J].Image&vision computing,1993,11(4):203-210.
[16]LI J,CHELLAPPA R.Structure from planar motion[J].IEEE transactions on signal processing society,2006,15(11):3466-3477.
[17]KONOLIGE K,AGRAWAL M.FrameSLAM:from bundle adjustment to real-time visual mapping[J].IEEE transactions on robotics,2008,24(5):1066-1077.
[18]MOURAGNON E,LHUILLIER M,DHOME M,et al.Generic and real-time structure from motion using local bundle adjustment[J].Image&vision computing,2009,27(8):1178-1193.
[2]杨东勇,冯形松.采用形态学算子的运动目标检测跟踪方法研究及实现[J].浙江工业大学学报,2010,38(2):149-154.
[3]RAMBACH J R,TEWARI A,PAGANI A,et al.Learning to fuse:a deep learning approach to visual-inertial camera pose estimation[C]//Proceedings of IEEE International Symposium on Mixed and Augmented Reality.Piscataway:IEEE,2016:71-76.
[4]孙建辉,刘坤.基于序列图像特征识别实时反馈伺服跟踪研究[J].浙江工业大学学报,2015,43(2):185-189.
[5]KESHMIRI M,XIE W F,MOHEBBI A.Augmented image based visual servoing of a manipulator using acceleration command[J].IEEE transactions on industrial electronics,2014,61(10):5444-5452.
[6]GALVEZLOPEZ D,SALAS M,TARDOS J D,et al.Realtime monocular object SLAM[J].Robotics&autonomous systems,2016(75):435-449.
[7]管秋,金俊杰,张剑华,等.基于最优RANSAC算法的非增加式多视图三维重建[J].浙江工业大学学报,2015,43(5):473-478.
[8]TOMASI C,KANADE T.Shape and motion from image streams under orthography:a factorization method[J].International journal of computer vision,1992,9(2):137-154.
[9]DAI Yuchao,LI Hongdong,HE Mingyi.Projective multiview structure and motion from element-wise factorization[J].IEEE transactions on pattern analysis and machine intelligence,2013,35(9):2238-2251.
[10]WANG G,ZELEK J S,WU Q M J,et al.Robust rank-4affine factorization for structure from motion[C]//Proceedings of IEEE Workshop on Applications of Computer Vision.Piscataway:IEEE,2013:180-185.
[11]LI H.Multi-view structure computation without explicitly estimating motion[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE,2010:2777-2784.
[12]LU G.Image-based indoor localization system based on 3D SfM model[C]//Proceedings of the International Society for Optics and Photonics on IS&T/SPIE Electronic Imaging.San Francisco,USA:SPIE,2014.
[13]OLIENSIS J.Structure from linear or planar motions[C]//1996IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE,1996:335-342.
[14]VIDAL R,OLIENSIS J.Structure from planar motions with small baselines[C]//Proceeding of European Conference on Computer Vision.Berlin Heidelberg:Springer,2002:383-398.
[15]TAN T N,BAKER K D,SULLIVAN G D.3Dstructure and motion estimation from 2Dimage sequences[J].Image&vision computing,1993,11(4):203-210.
[16]LI J,CHELLAPPA R.Structure from planar motion[J].IEEE transactions on signal processing society,2006,15(11):3466-3477.
[17]KONOLIGE K,AGRAWAL M.FrameSLAM:from bundle adjustment to real-time visual mapping[J].IEEE transactions on robotics,2008,24(5):1066-1077.
[18]MOURAGNON E,LHUILLIER M,DHOME M,et al.Generic and real-time structure from motion using local bundle adjustment[J].Image&vision computing,2009,27(8):1178-1193.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |