A simple pose estimation method based on co-planar feature points
Authors:
- 1 May 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 134-137
Abstract
This paper presents a simple method to solve the P4P problem based on co-planar feature points. By enhancing the geometric constraints of the feature points which attached to the target previously, we obtain the three-dimensional camera coordinates of the feature points in two different formulas. Then the translation vector and three rotation angles describing the relationship between target coordinate system and camera coordinate system are computed using a closed-form solution directly. In order to improve the precision about the extraction of the image center coordinate of the feature point, we use the morphology expansion operation to achieve it. The experimental results and theoretical analysis which were compared with the previous method demonstrate that our method is more fast and effective.Keywords
This publication has 10 references indexed in Scilit:
- Classification of the perspective-three-point problem, discriminant variety and real solving polynomial systems of inequalities2008
- On the Probability of the Number of Solutions for the P4P ProblemJournal of Mathematical Imaging and Vision, 2006
- PnP Problem RevisitedJournal of Mathematical Imaging and Vision, 2005
- Multiple View Geometry in Computer Vision2004
- Complete solution classification for the perspective-three-point problemIEEE Transactions on Pattern Analysis and Machine Intelligence, 2003
- Fast pose estimation with parameter-sensitive hashing2003
- A note on the number of solutions of the noncoplanar P4P problemIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
- Linear N-point camera pose determinationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1999
- Camera pose and calibration from 4 or 5 known 3D points1999
- A new efficient and direct solution for pose estimation using quadrangular targets: algorithm and evaluationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1995