计算机应用 ›› 2016, Vol. 36 ›› Issue (12): 3402-3405.DOI: 10.11772/j.issn.1001-9081.2016.12.3402

• 虚拟现实与数字媒体 • 上一篇    下一篇

基于FREAK描述子的精确图像配准改进算法

房贻广1, 刘武2, 高梦珠3, 谭守标3, 张骥4   

  1. 1. 国网安徽省电力公司 安全监察质量部, 合肥 230022;
    2. 国网安庆供电公司 安全监察质量部, 安徽 安庆 246000;
    3. 安徽大学 电子信息工程学院, 合肥 230601;
    4. 安徽南瑞继远电网技术有限公司, 合肥 230088
  • 收稿日期:2016-06-06 修回日期:2016-07-20 出版日期:2016-12-10 发布日期:2016-12-08
  • 通讯作者: 谭守标
  • 作者简介:房贻广(1969-),男,安徽淮北人,高级工程师,硕士,主要研究方向:电力安全监察技术;刘武(1978-),男,安徽安庆人,工程师,硕士,主要研究方向:电力安全监察技术;高梦珠(1991-),女,安徽宿州人,硕士,主要研究方向:机器视觉;谭守标(1976-),男,湖北天门人,副教授,博士,主要研究方向:机器视觉;张骥(1982-),男,安徽铜陵人,硕士,主要研究方向:电力视频监控技术。
  • 基金资助:
    国家科技支撑计划项目(2014BAH27F01);国家电网公司科技项目(5212D01502DB)。

Improved accurate image registration algorithm based on FREAK descriptor

FANG Yiguang1, LIU Wu2, GAO Mengzhu3, TAN Shoubiao3, ZHANG Ji4   

  1. 1. Safety Supervision Quality Department, State Grid Anhui Electric Power Supply Corporation, Hefei Anhui 230022, China;
    2. Safety Supervision Quality Department, State Grid Anqing Electric Power Supply Corporation, Anqing Anhui 246000, China;
    3. School of Electronics and Information Engineering, Anhui University, Hefei Anhui 230601, China;
    4. Anhui Nari Jiyuan Electric Power System Technology Company Limited, Hefei Anhui 230088, China
  • Received:2016-06-06 Revised:2016-07-20 Online:2016-12-10 Published:2016-12-08
  • Supported by:
    This work is partially supported by the National Science and Technology Support Program (2014BAH27F01), the Science and Technology Project of China State Grid Corporation (5212D01502DB).

摘要: 快速视网膜特征(FREAK)描述子通过计算模式方向实现了旋转不变性,但对于旋转尺度变化较大的情况匹配性能并不理想,误匹配率较高,为此提出了一种改进的基于FREAK描述子的精确图像配准算法。首先,对原有FREAK算法添加长距离点对,设定距离阈值,只利用关键点采样模式中距离较远的点来生成角度信息。其次,对Hamming距离进行加权。对每一个关键点,在为了生成描述子选择点对时,对训练数据描述子的每一列计算均值,越接近0.5的列权值越大,改进了原来Hamming距离计算粗略的状态,使距离计算更精确。最后,使用最近邻匹配结合最近邻和次近邻的比值以及随机抽样一致(RANSAC)方法进行快速匹配和优化。实验结果表明,改进算法更适用于旋转尺度变化较大的环境及匹配性能要求较高的场合。

关键词: 快速视网膜特征, 特征提取, Hamming距离, 图像配准

Abstract: The algorithm of Fast REtinA Keypoint (FREAK) descriptor has achieved the rotation invariance via the direction of calculation model, but its matching performance for large change of rotation scale is not ideal and the matching error rate is high. In order to solve the problem, an improved image registration algorithm based on FREAK descriptor was proposed. Firstly, long distance point pairs judged with a given distance threshold, was added to the original FREAK. Only the points of long distance in the keypoint sampling pattern were used to generate angle information. Then, the Hamming distance was weighted. In order to generate descriptor selection point pairs for every key point, the mean of each column of training data descriptors was computed. The mean was closer to 0.5, the weight of the column was larger. This method improved the coarse-calculating state of original Hamming distance and made the distance calculation more accurate. The nearest neighbor matching method combined with the ratio of the nearest neighbor and next nearest neighbor, and the method of RANdom SAmple Consensus (RANSAC) were used for rapid matching and optimization. The experimental results show that, the improved algorithm is more suitable for the applications with large variation of rotation scale and high demand of matching performance.

Key words: Fast REtinA Keypoint (FREAK), feature extraction, Hamming distance, image registration

中图分类号: