Vision pose estimation from planar dual circles in a single image

Abstract A novel vision based pose estimation method for a single image with planar dual circles is addressed. We present a very simple formula to solve camera pose with a single circle, and then develop a fusion method to integrate solved poses of dual circles by using space geometry constraints. After that, a new definition of the difference quantity between two ellipses is proposed to evaluate reprojection errors of dual circles and determine the optimal and unique pose solution. Experiments with synthetic data and real images are carried out to validate the proposed method, and results show that the method has a high accuracy and good robustness.

[1]  Sheng Nan Zhang,et al.  A Method of Determining the Pose of Planar Target in Vision Detection System , 2013 .

[2]  Wei Zhenzhong,et al.  Estimation of projected circle centers from array circles and its application in camera calibration , 2009, 2009 Asia-Pacific Conference on Computational Intelligence and Industrial Applications (PACIIA).

[3]  Yubin Kuang,et al.  Revisiting the PnP Problem: A Fast, General and Optimal Solution , 2013, 2013 IEEE International Conference on Computer Vision.

[4]  Xu Chen,et al.  The projected circle centres and polar line for camera self-calibration , 2015 .

[5]  Stefan Rahmann,et al.  Relative Pose Estimation from Two Circles , 2008, DAGM-Symposium.

[6]  Tao Zhang,et al.  Vision-Based Pose Estimation From Points With Unknown Correspondences , 2014, IEEE Transactions on Image Processing.

[7]  Adrien Bartoli,et al.  Infinitesimal Plane-Based Pose Estimation , 2014, International Journal of Computer Vision.

[8]  Roland Siegwart,et al.  Vision Based Position Control for MAVs Using One Single Circular Landmark , 2011, J. Intell. Robotic Syst..

[9]  Zen Chen,et al.  A vision-based method for the circle pose determination with a direct geometric interpretation , 1999, IEEE Trans. Robotics Autom..

[10]  Yinqiang Zheng,et al.  Camera calibration using one perspective view of two arbitrary coplanar circles , 2008 .

[11]  Xu Chen,et al.  A linear approach for determining camera intrinsic parameters using tangent circles , 2014, Multimedia Tools and Applications.

[12]  Zhanyi Hu,et al.  Camera Calibration from the Quasi-affine Invariance of Two Parallel Circles , 2004, ECCV.

[13]  Yifan Zhou,et al.  A novel absolute localization estimation of a target with monocular vision , 2013 .

[14]  Yuncai Liu,et al.  Applications of projected circle centers in camera calibration , 2010, Machine Vision and Applications.

[15]  Wencheng Wang,et al.  Measurement System of Gear Parameters Based on Machine Vision , 2015 .

[16]  Hongdong Li,et al.  UPnP: An Optimal O(n) Solution to the Absolute Pose Problem with Universal Applicability , 2014, ECCV.

[17]  Min Xia,et al.  3-D location estimation of underwater circular features by monocular vision , 2013 .

[18]  Jin Yu Song,et al.  Circle Pose Estimation Based on Stereo Vision , 2012 .

[19]  Ji Zhao,et al.  Circle recognition and parameter measurement methods with the similarity constraint on the slope curve of the tangent lines to a contour , 2013 .

[20]  Pierre Gurdjos,et al.  Euclidean Structure from N geq 2 Parallel Circles: Theory and Algorithms , 2006, ECCV.

[21]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[22]  Helder Araújo,et al.  Pose Estimation for General Cameras Using Lines , 2015, IEEE Transactions on Cybernetics.

[23]  Yong Chen,et al.  Parallel vision-based pose estimation for non-cooperative spacecraft , 2015 .

[24]  Qian Chen,et al.  Camera Calibration with Two Arbitrary Coplanar Circles , 2004, ECCV.