摘要
针对SIFT、SURF等局部不变特征在大尺寸图像上匹配时过于耗时的问题,将FREAK算子应用于图像匹配中,并提出一种多线程并行加速方法。首先介绍FREAK描述子的特征点的检测、特征描述向量的生成和特征向量的匹配的过程,并分析其优势。其次提出并行处理的2种思路:一是对待匹配图像进行有重叠的分块,对于每一块子图像,开辟新的线程分别进行处理;二是对匹配过程的3个步骤,采用流水线技术进行并行处理,每检测出一个特征点,随即提取出该点的特征向量,然后和模板图像的特征向量集进行匹配。改写SIFT、SURF和FREAK算法进行实验验证,结果证明FREAK计算过程比SIFT和SURF快得多,而并行方法可以在保证匹配精度的同时明显缩短匹配时间。
Taking into account the problem that local invariant feature algorithms such as SIFT, SURF take too much time in large images registration, a fast descriptor named FREAK is introduced, and a speeding up method using multi-thread technology is proposed. The process of feature point detec- tion, descriptive characteristics vector generation and feature vector matching of FREAK are intro- duced and their advantages are analyzed. Then,two ideas of parallel processing are proposed. One is to divide large image into overlapping sub-blocks, and for each sub-image, a new thread is opened up. The other is to use pipelining technology for the three step of registration. Once a feature point is de- tected, its feature vector is extracted immediately, and soon it matches with the feature vector set of the template image. Rewriting SIFT, SURF and FREAK for experiment, the experimental result indi- cates that FREAK is faster than the other two algorithms,and our parallel method can greatly econo- mize matching time as well as guarantee the accuracy.
出处
《液晶与显示》
CAS
CSCD
北大核心
2014年第2期266-274,共9页
Chinese Journal of Liquid Crystals and Displays
基金
院地合作(长吉图专项基金)(No.2011CJT0006)
吉林科技发展计划项目(No.20126015)
关键词
FREAK算子
局部不变特征
图像匹配
并行
流水线技术
FREAK descriptor
local invariant feature
image registration
parallel
pipelining technology
