融入曲率尺度空间算法的图像配准方法  

Image registration method based on curvature scale space algorithm

作　　者：章盛 李培华 钱名思 刘玉莉 ZHANG Sheng;LI Pei-hua;QIAN Ming-si;LIU Yu-li(AVIC Huadong Photoelectric Co.,Ltd.,Wuhu 241002,China;Key Laboratory of Modern Display Technology,Wuhu 241002,China;National Special Display Engineering Research Center,Wuhu 241002,China;National Engineering Laboratory of Special Display Technology,Wuhu 241002,China)

机构地区：[1]中航华东光电有限公司,安徽芜湖241002 [2]安徽省现代显示技术重点实验室,安徽芜湖241002 [3]国家特种显示工程技术研究中心,安徽芜湖241002 [4]特种显示国家工程实验室,安徽芜湖241002

出　　处：《激光与红外》2021年第3期379-387,共9页Laser & Infrared

基　　金：安徽省科技重大专项项目(No.17030901053)资助。

摘　　要：为了满足图像配准对于实时性的要求,提出融入曲率尺度空间算法的图像配准方法。首先使用曲率尺度空间算法提取图像角点特征,然后使用改进的加速稳健特征算法生成64维角点特征描述子向量并将描述子向量降维到24维,最后使用改进的相似性距离算法和随机采样一致性算法进行匹配。仿真实验一表明:在图像配准准确度方面与传统尺度不变特征变换算法、传统加速稳健特征算法及其他改进的图像配准方法相当,但在图像配准实时性方面具有一定的优势,仿真实验二通过立体匹配库验证了该方法具有普遍有效性。In order to meet the real-time requirements of image registration,the image registration method based on the curvature scale space algorithm is proposed.Firstly of all,the image corner features are extracted by the curvature scale space algorithm.Then,the improved speeded up robust features algorithm is used to generate the 64-dimensional corner feature descriptor vectors and reduce the descriptor vectors to 24-dimensional.Finally,the improved similarity distance algorithm and the random sample consensus algorithm are used to match.The first simulation experiment shows that the image registration accuracy is equivalent to the traditional scale invariant feature transform algorithm,the traditional speeded up robust features algorithm,and other improved image registration methods,but it has certain advantages in real-time of image registration.The second simulation experiment verified the universal effectiveness of the method through the stereo matching library.

关 键 词：加速稳健特征算法 曲率尺度空间算法 图像配准 尺度不变特征变换算法 随机采样一致性算法 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]