Particle swarm optimization based pose and correspondence estimation

doi:10.11834/jig.20110410

Views : 0 下载量: 229 CSCD: 0

PDF
Export
Share
Collection
Album

Particle swarm optimization based pose and correspondence estimation
Vol. 16, Issue 4, Pages: 640-646(2011)
Published Online：26 April 2011，

Published：2011
DOI： 10.11834/jig.20110410
稿件说明：

移动端阅览

DOI：

Particle swarm optimization based pose and correspondence estimation[J]. Journal of Image and Graphics, 2011, 16(4): 640-646. DOI： 10.11834/jig.20110410.

摘要

点模式匹配问题是机器视觉与模式识别领域中一个基础问题，在目标识别、医学图像配准、遥感图像匹配、姿态估计等方面都得到广泛应用。提出一种在仿射变换下利用粒子群优化算法进行图像点模式下的匹配与姿态估计的方法。算法首先把点集匹配问题转化为解空间为仿射参数空间下的目标函数优化问题，然后运用粒子群算法对相应的变换参数进行搜索，获得问题最优解。本文贡献如下：1)给出一种仿射参数的初始估计方法，提高了后续算法搜索效率；2)引入阈值和次近点规则，改进了最近点匹配搜索方法，能较好地拒绝出格点（outliers），并提高算法有效性；3)从两方面对PSO方法进行了改进，加强了原PSO的全局和局部搜索能力。实验结果表明，算法具有有效性和鲁棒性。

Abstract

Point Pattern Matching (PPM) is an important issue of computer vision and pattern recognition

which is widely used in target recognition

medical and remote image registration

pose estimation

etc. This paper proposes a particle swarm optimization (PSO) based approach for pose and correspondences estimation between the feature points of two images under affine transformation. In the method

the point sets matching problem is formulated as an objective function’s optimization problem in the affine transformation parameters solution space. The PSO is used to search for optimal transformation parameters. There are three contributions made in this paper. Firstly

we develop an initial transformation parameters estimation method for PSO

which greatly improve the algorithms efficiency and veracity. Secondly

we introduce a threshold to correspondence finding

which rejects outliers and enhances veracity while using “Nearest Neighbors Search”. Thirdly

we propose two approaches to improve the searching efficiency when using the original PSO. Experiments demonstrate the validity and robustness of the algorithm.