[1]张磊,张兴国.基于李群代数表达帧间位姿变化矩阵的3D视觉跟踪研究[J].江西师范大学学报(自然科学版),2012,(05):466-471.
　ZHANG Lei,ZHANG Xing-guo.3D Visual Tracking Based on the SE(3) Group Representation of Interframe Pose Transform Matrix[J].Journal of Jiangxi Normal University:Natural Science Edition,2012,(05):466-471.
点击复制

基于李群代数表达帧间位姿变化矩阵的3D视觉跟踪研究()
分享到：

《江西师范大学学报》（自然科学版）[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2012年05期
页码:
466-471
栏目:
出版日期:
2012-10-01

文章信息/Info

Title:
3D Visual Tracking Based on the SE(3) Group Representation of Interframe Pose Transform Matrix
作者:
张磊;张兴国
南通大学机械工程学院, 江苏 南通 226019
Author(s):
ZHANG Lei;  ZHANG Xing-guo
关键词:
视觉跟踪; 3维; 最小二乘问题; 位姿估计
Keywords:
visual tracking;  3D;  least square problem;  pose estimation
分类号:
TP391.41
文献标志码:
A
摘要:
基于 RAPiD 边缘跟踪方法的思想,采用以帧间位姿变化更新目标物绝对位姿值的办法,引入李群代数表达帧间位姿变化矩阵;然后将帧间位姿变化矩阵参数的求解问题转换为线性最小二乘的最优求解问题.在李群代数的表达方式下,最小二乘的最优问题可较容易获得线性化表达,方便了求解.实验显示了该算法的3D跟踪效果与目标物位姿值的估计结果.
Abstract:
The SE(3) group is introduced for representing the interframe pose transform which can be used for updating the absolute pose of the object. Then, the 3D tracking problem can be equivalent to the least square optimization problem on parameter solving of the interframe pose transform. Owe to the SE(3) group representation, simpler linear representation can be used in optimization process, which pave the way for parameter solving. Experiments show the 3D tracking results of an object and the related pose estimation.

参考文献/References:

[1] Gennery D B. Tracking known three-dimensional objects [EB/OL].
[2011-11-18]. http: //www. aaai. org/Papers/AAAI/ 1982/ AAAI82-004.pdf.
[2] Lowe D G. Fitting parameterized three-dimensional models to images [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1991, 3(5): 441-450.
[3] Lepetit V, Fua P. Monocular model-based 3d tracking of rigid objects: A survey [EB/OL].
[2012-01-09]. http: //cvlab. epfl. ch/~ lepetit/papers/lepetit_ftcgv05.pdf.
[4] Lowe D G. Robust model-based motion tracking through the integration of search and estimation [J]. International Journal of Computer Vision, 1992, 8(2): 113-122.
[5] Harris C. Tracking with rigid objects [M]. Massachusetts: MIT Press, 1992.
[6] Simon R, Fitzgibbon A, Zisserman A. Markerless tracking using planar structures in the scene [EB/OL].
[2012-02-16]. http: //www.robots.ox.ac. uk/~vgg/publications/papers/simon00. pdf.
[7] Simon G, Berger M O. Pose estimation from planar structures [J]. Computer Graphics and Applications, 2002, 22: 46 - 53.
[8] Changhyun Choi, Henrik I. Christensen robust 3D visual tracking using particle filtering on the SE(3) group [EB/OL].
[2012-03- 12]. http: //ieeexplore. ieee. org/stamp/stamp. jsp?arnumber= 0598 0245.
[9] Drummond T, Cipolla R. Real-time visual tracking of complex structures [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 27: 932-946.
[10] Changhyun C , Henrik I C. Real-time 3D model-based tracking using edge and keypoint features for robotic manipulation [EB/OL].
[2012-02-11]. http: //ieeexplore. ieee. org/stamp/ stamp. jsp?arnumber=05980245.
[11] Levenberg K. A method for the solution of certain problems in least squares [J]. Quarterly of Applied Mathematics, 1944, 2: 164-168.
[12] Marquardt D. An algorithm for least-squares estimation of nonlinear parameters [J]. SIAM Journal on Applied Mathematics, 1963, 11: 431-441.

更新日期/Last Update: 1900-01-01