DocumentCode :
476251
Title :
Recovery of camera poses and 3D reconstruction based on image sequence
Author :
Zhang, Wei-zhong ; Pan, Zhen-Kuan ; Wang, Yu
Author_Institution :
Coll. of Inf. Eng., Qingdao Univ., Qingdao
Volume :
5
fYear :
2008
fDate :
12-15 July 2008
Firstpage :
3011
Lastpage :
3016
Abstract :
A novel algorithm for recovery of camera poses and 3D reconstruction of reference points is presented and realized. A good initial value is estimated for the projective reconstruction by the matrix factorization method using coded targets as original input. The coordinates of the non-coded targets in 3D projective space is then recovered using the stereo triangulation. The coordinates of the non-coded targets and camera motion matrices are further optimized by using the bundle adjustment. Finally, the projective reconstruction is upgraded into Euclidean one by making use of the homography. Compared to the existing method, the reprojection error is greatly reduced by the proposed one. The proposed method has been applied in multi-view point cloud registration.
Keywords :
cameras; image reconstruction; image registration; image sequences; matrix decomposition; pose estimation; 3D projective space; 3D reconstruction; bundle adjustment; camera motion matrices; camera poses recovery; coded targets; image sequence; matrix factorization method; multiview point cloud registration; reference points; stereo triangulation; Cameras; Clouds; Cybernetics; Educational institutions; Image reconstruction; Image sequences; Machine learning; Motion estimation; Size measurement; Surface reconstruction; 3D reconstruction; Bundle adjustment; Camera poses; Point cloud registration; reprojection error;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Machine Learning and Cybernetics, 2008 International Conference on
Conference_Location :
Kunming
Print_ISBN :
978-1-4244-2095-7
Electronic_ISBN :
978-1-4244-2096-4
Type :
conf
DOI :
10.1109/ICMLC.2008.4620923
Filename :
4620923
Link To Document :
بازگشت