A direct least squares method for camera pose estimation based on straight line segment correspondences

被引：0
|
作者：
Li, Xin [1 ,2 ]
Zhang, Yueqiang [1 ,2 ]
Liu, Jinbo [1 ,2 ]
Zhang, Xiaohu [1 ,2 ]
Yu, Qifeng [1 ,2 ]
机构：
[1] College of Aerospace Science and Engineering, National University of Defense Technology, Changsha, 410073, Hunan
[2] Hunan Key Laboratory of Videometrics and Vision Navigation, National University of Defense Technology, Changsha, 410073, Hunan
来源：
Guangxue Xuebao/Acta Optica Sinica | 2015年 / 35卷 / 06期
关键词：
Camera pose estimation; Globally optimal solution; Machine vision; Polynomial equations; Straight line segment correspondence;
D O I：
10.3788/AOS201535.0615003
中图分类号：
学科分类号：
摘要：
In order to estimate the camera pose from straight line segment correspondences in high precision, a direct least squares solution is proposed. A straight line segment distance measurement which integrates distance between endpoints, midpoints, angle and lengths of two line segments is proposed and used to transform the original problem into minimize a quadratic cost function of pose rotation matrix. A modified cost function based on the CGR parameters of rotation matrix is minimized, which the optimality conditions form a system of three third-order polynomial equations. Algebraic method is used to solve this system directly without requiring iterations, and the globally optimal solution of rotation matris is obtained. The complexity of proposed method is O(n). The efficiency and high precision are demonstrated by synthesized and real data experiments. ©, 2015, Chinese Optical Society. All right reserved.
引用
收藏
页数：11
相关论文
共 26 条
  • [1] Hartley R., Zisserman A., Multiple View Geometry in Computer Vision, (2004)
  • [2] Li S., Xu C., Xie M., A robust O(n) solution to the perspective-n-point problem, IEEE Transactions on Pattern Analysis and Machine Intelligence, 34, 7, pp. 1444-1450, (2012)
  • [3] Zheng Y., Kuang Y., Sugimoto S., Et al., Revisiting the PnP problem: A fast, general and optimal solution, ICCV, pp. 2344-2351, (2013)
  • [4] Hesch J.A., Roumeliotis S.I., A direct least-squares (DLS) method for PnP, ICCV, pp. 383-390, (2011)
  • [5] Lu C.P., Hager G.D., Mjolsness E., Fast and globally convergent pose estimation from video images, IEEE Transactions on Pattern Analysis and Machine Intelligence, 22, 6, pp. 610-622, (2000)
  • [6] Schweighofer G., Pinz A., Globally optimal O(n) solution to the PnP problem for general camera models, BMVC, pp. 1-10, (2008)
  • [7] Dhome M., Richetin M., Lapreste J.T., Et al., Determination of the attitude of 3D objects from a single perspective view, IEEE Transactions on Pattern Analysis and Machine Intelligence, 11, 12, pp. 1265-1278, (1989)
  • [8] Chen H.H., Pose determination from line-to-plane correspondences: Existence condition and closed-form solutions, IEEE Transactions on Pattern Analysis and Machine Intelligence, 13, 6, pp. 530-541, (1991)
  • [9] Qin L.J., Zhu F., A new method for pose estimation from line correspondences, Acta Automatica Sinica, 34, 2, pp. 130-134, (2008)
  • [10] Zhang L., Xu C., Lee K.M., Et al., Robust and efficient pose estimation from line correspondences, ACCV, pp. 217-230, (2012)
123