DocumentCode
3136611
Title
A simple algorithm for camera pose estimation
Author
Chen, Peng ; Hu, Guang-Da
Author_Institution
Autom. & Electr. Eng. Sch., Univ. of Sci. & Technol. Beijing, Beijing, China
fYear
2012
fDate
5-8 Aug. 2012
Firstpage
2181
Lastpage
2186
Abstract
In this paper, we present a simple algorithm for calibrated camera pose estimation. The algorithm is based on the object space error, and capable of iteratively determining the pose by solving a group of linear equations from the correspondences of arbitrary n reference points and their image projections. Experimental results show that our algorithm is more likely to converge to correct pose than currently accepted iterative algorithms, and suitable for both centered and uncentered reference points. Furthermore, our algorithm can maintain high estimation accuracy in a short runtime, which makes it more applicable for real time applications.
Keywords
calibration; cameras; estimation theory; iterative methods; pose estimation; calibrated camera pose estimation; estimation accuracy; image projections; iterative algorithms; linear equations; object space error; simple algorithm; uncentered reference points; Accuracy; Cameras; Equations; Estimation; Mathematical model; Noise; Vectors; Monocular vision; PnP; Pose estimation; Robotics;
fLanguage
English
Publisher
ieee
Conference_Titel
Mechatronics and Automation (ICMA), 2012 International Conference on
Conference_Location
Chengdu
Print_ISBN
978-1-4673-1275-2
Type
conf
DOI
10.1109/ICMA.2012.6285681
Filename
6285681
Link To Document