激光与光电子学进展, 2018, 55 (9): 091501, 网络出版: 2018-09-08  

基于软指派算法的相机位姿估计研究

Camera Pose Estimation Based on Softassign Algorithm
作者单位
大连理工大学机械工程学院, 辽宁 大连 116024
摘要
针对未知特征点匹配关系下的单目相机位姿估计问题, 提出了一种基于软指派算法的相机位姿估计算法。结合了正交迭代算法和软指派算法, 以三维(3D)和二维(2D)特征点的物方空间共线性误差作为确定特征点之间匹配关系的指派依据和计算相机位姿的目标函数值, 通过迭代方式确定特征点的匹配关系和相机的位姿。其不仅能处理3D/2D特征点一一对应的情况, 而且能够处理同时存在遮挡的3D特征点和错误的2D特征点的情况。合成图像的实验结果表明:在含有图像噪声、遮挡的3D特征点和错误的2D特征点情况下, 该算法的成功率>82%, 真实图像实验对算法的性能进行了验证。
Abstract
Aiming at the problem of monocular camera pose estimation under the matching relations of unknown feature points, a new camera pose estimation algorithm is proposed based on the Softassign algorithm. Based on the advantages of orthogonal iteration and Softassign algorithm, the collinear error of the object space in three-dimensional (3D) feature points and two-dimensional (2D) feature points is used as the basis for determining the matching relationship between feature points and the objective function value for calculating the camera pose. A iteratively way determines the matching relationship of feature points and the pose of the camera. It can handle the case where the 3D/2D feature points are in one-to-one correspondence, and the case which occlude 3D feature points and erroneous 2D features. The results of the synthetic image experiments show that the success rate of this algorithm is over 82% in one case with image noise, occlusion and clutter. The experiment of real image can verify the property of algorithm.
参考文献

[1] Vincenl L, Francesc M N, Pascal F. EPnP: an accurate O(n) solution to the PnP problem[J]. International Journal of Computer Vision. 2009, 81(2): 155-166.

[2] Hesch J A, Roumeliotis S I. A direct least-squares (DLS) method for PnP[C]∥ Proceedings of IEEE International Conference on Computer Vision, 2011: 383-390.

[3] 戴东凯, 王省书, 胡春生, 等. 基于天文观测的相机标定及姿态测量技术研究[J]. 光学学报, 2012, 32(3): 0312005.

    Dai D K, Wang X S, Hu C S, et al. Camera calibration and attitude measurement technology based on astronomical observation[J]. Acta Optica Sinica, 2012, 32(3): 0312005.

[4] Oberkampf D, DeMenthon D F, Davis L S. Iterative pose estimation using coplanar feature points[J]. Computer Vision and Image Understanding, 1996, 63(3): 495-511.

[5] Lu C P, Hager G D, Mjolsness E. Fast and globally convergent pose estimation from video images[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(6): 610-622.

[6] Kahl F, Henrion D. Globally optimal estimates for geometric reconstruction problems[J]. International Journal of Computer Vision, 2007, 74(1): 3-15.

[7] 岳晓奎, 武媛媛, 吴侃之. 基于视觉信息的航天器位姿估计迭代算法[J]. 西北工业大学学报, 2011, 29(4): 559-563.

    Yue X K, Wu Y Y, Wu K Z. A novel binocular OI (orthogonal iteration) fusion algorithm better for estimation of spacecraft position and attitude[J]. Journal of Northwestern Polytechnical University, 2011, 29(4): 559-563.

[8] Yang H W, Wang F, Li Z, et al. Simultaneous pose and correspondence estimation based on genetic algorithm[J]. International Journal of Distributed Sensor Networks, 2015, 11(11): 828241.

[9] Fischler M A, Bolles R C. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography[J]. Readings in Computer Vision, 1987: 726-740.

[10] David P, DeMenthon D, Duraiswami R, et al. SoftPOSIT: simultaneous pose and correspondence determination[J]. International Journal of Computer Vision, 2004, 59(3): 259-284.

[11] Shi J F, Ulrich S. Soft POSIT enhancements for monocular camera spacecraft pose estimation[C]∥Proceedings of IEEE 21st International Conference on Methods and Models in Automation and Robotics, 2016: 30-35.

[12] Gold S, Rangarajan A. A graduated assignment algorithm for graph matching[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996, 18(4): 377-388.

[13] Zhou H Y, Zhang T, Lu W N. Vision-based pose estimation from points with unknown correspondences[J]. IEEE Transactions on Image Processing, 2014, 23(8): 3468-3477.

[14] 陈鹏, 胡广大, 闫桂荣. 基于质点系运动原理的像机位姿估计算法[J]. 光学学报, 2014, 34(1): 0112002.

    Chen P, Hu G D, Yan G R. Camera pose estimation algorithm based on particle system kinematics[J]. Acta Optica Sinica, 2014, 34(1): 0112002.

[15] Ugurdag H F, Gren S, Canbay F. Gravitational pose estimation[J]. Computers & Electrical Engineering, 2010, 36(6): 1165-1180.

[16] Ugurdag H F, Goren S, Canbay F. Correspondenceless pose estimation from a single 2D image using classical mechanics[C]∥Proceedings of IEEE 23rd International Symposium on Computer and Information Sciences, 2008: 1-6.

[17] 何斐彦, 林嘉睿, 高扬, 等. 单目视觉与倾角仪组合优化的位姿测量系统[J]. 光学学报, 2016, 36(12): 1215002.

    He F Y, Lin J R, Gao Y, et al. Optimized pose measurement system combining monocular vision with inclinometer sensors[J]. Acta Optica Sinica, 2016, 36(12): 1215002.

[18] 关瑞芬, 杨凌辉, 王丽君, 等. 基于正交柱面成像的空间物体位姿精密测量[J]. 光学学报, 2016, 36(11): 1112003.

    Guan R F, Yang L H, Wang L J, et al. Position and attitude precision measurement of spatial objects based on orthogonal cylindrical imaging [J]. Acta Optica Sinica, 2016, 36(11): 1112003.

[19] 张林龙, 张伟, 胡昌华, 等. 基于传递像机的移动摄像测量方法[J]. 光学学报, 2017, 37(4): 0412001.

    Zhang L L, Zhang W, Hu C H, et al. Mobile videometrics method based on relay camera[J]. Acta Optica Sinica, 2017, 37(4): 0412001.

杜广胜, 丛明, 刘毅, 刘冬. 基于软指派算法的相机位姿估计研究[J]. 激光与光电子学进展, 2018, 55(9): 091501. Du Guangsheng, Cong Ming, Liu Yi, Liu Dong. Camera Pose Estimation Based on Softassign Algorithm[J]. Laser & Optoelectronics Progress, 2018, 55(9): 091501.

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!