| 一种用于红外与微光图像配准的改进型SURF算法 |
| 投稿时间：2016-11-17 最后修改时间：2017-02-03 点此下载全文 |
| 引用本文：杨欢,石俊生,字崇德,李希才.一种用于红外与微光图像配准的改进型SURF算法[J].红外,2017,38(4):34~43 |
| 摘要点击次数: 116 |
| 全文下载次数: 113 |
|
| 基金项目:国家自然科学基金项目(61178054)；云南省教育厅重大专项(ZD2014004)；云南省高校科技创新团队支持计划资助项目 |
|
| 中文摘要:针对红外与微光图像配准的特殊性，
为了减少配准计算量，提出了一种从主方向确定和特征点描述
两方面加以改进的加速鲁棒特征(Speeded Up Robust Feature, SURF)配
准算法。首先检测微光图像和红外图
像的边缘，然后用改进型SURF算法提取两种图像边缘上的特征
点，并采用最近邻距离法对原始特征点进行筛选。在得到较高精
度的特征点后进行粗匹配。接着用随机抽样一致
性(RANdom SAmple Consensus, RANSAC)算法对一次筛选后的
特征点进行精匹配。最后利用精确的特征点建立变换模型，并
将重采样后的待配准图像与参考图像实现配准。实验结果表明，
该算法不仅可以解决红外与微光图像的配准问题，而且在匹配精度和
算法运算时间等方面的表现均优于原始SURF算法。 |
| 中文关键词:图像配准 微光图像 红外图像 SURF算法 边缘提取 |
| |
| An Improved SURF Algorithm for IR and Low Light Image Registration |
|
|
| Abstract:According to the particularity
of infrared and low light image registration, to reduce
the amount of registration, an Speeded Up Robust
Feature (SURF) registration algorithm improved both in
determination of main direction and in description of
feature points is proposed. Firstly, the edges of low
light images and infrared images are detected
respectively. Then, the improved SURF algorithm is used
to extract the feature points of two kinds of image edges.
Secondly, a nearest neighbor method is used to screen out
the original feature points. After the feature points with
higher accuracy are obtained, rough matching is carried out
on them. Then, the RANdom Sample Consensus (RANSAC) algorithm
is used to carry out precise matching on the feature points
screened out one time. Finally, the precise feature points
are used to establish a transform model and the images to be
registered after resampling are registered with the reference
images. The experiment results show that this improved algorithm
not only can solve the registration problem of infrared and low
light images, but also has better performance than the
original SURF algorithm. |
| keywords:image registration low light image infrared image SURF algorithm edge extraction |
| 查看全文 查看/发表评论 下载PDF阅读器 |