Journal of Computer Applications ›› 2018, Vol. 38 ›› Issue (9): 2678-2682.DOI: 10.11772/j.issn.1001-9081.2018030621

Previous Articles     Next Articles

Rapid mismatching elimination algorithm based on motion smoothing constraints

LI Wei, LI Weixiang, ZHANG Fan, JIE Wei   

  1. College of Electrical Engineering and Control Science, Nanjing Tech University, Nanjing Jiangsu 211800, China
  • Received:2018-03-26 Revised:2018-04-27 Online:2018-09-10 Published:2018-09-06
  • Contact: 李为相
  • Supported by:
    This work is partially supported by the Six Talent Peaks Project in Jiangsu Province (XXR-012).

基于运动平滑约束项的快速误匹配剔除算法

李为, 李为相, 张璠, 揭伟   

  1. 南京工业大学 电气工程与控制科学学院, 南京 211800
  • 通讯作者: 李为相
  • 作者简介:李为(1994—),男,湖北石首人,硕士研究生,主要研究方向:图像处理、模式识别;李为相(1973—),男,河南光山人,副教授,博士,主要研究方向:智能决策、社交网络、图像处理;张璠(1994—),男,浙江金华人,硕士研究生,主要研究方向:推荐系统、社交网络;揭伟(1994—),男,福建龙岩人,硕士研究生,主要研究方向:图像处理、模式识别。
  • 基金资助:
    江苏省"六大人才高峰"项目(XXR-012)。

Abstract: To solve the problem of huge computation cost and low matching accuracy in the course of iterative calculation while using RANdom SAmple Consensus (RANSAC) algorithm for image splicing, a mismatching elimination algorithm was proposed based on motion smoothing constraint terms. Firstly, feature points were extracted with ORB (Oriented FAST and Rotated BRIEF) algorithm, and initial matching of feature points was implemented based on Hamming distance. Secondly, the statistical neighboring support estimators based on motion smoothing constraint terms were used to achieve rough mismatching elimination, and then spatial geometric constraints were applied to refine mismatching elimination. Finally, grouping sorting was used to solve the model parameters, and weighted averaging was used to realize image fusion. The experimental results show that the mismatching elimination rate is improved by 75.6% compared to the algorithm for reducing the total number of sampling points and 24% compared to adaptive threshold algorithm. This method can effectively eliminate mismatching and realize accurate image mosaic.

Key words: image matching, Oriented FAST (Features from Accelerated Segment Test) and Rotated BRIEF (Binary Robust Independent Elmentary Features)(ORB), motion smoothing constraint term, wrong matching, structural similarity

摘要: 针对图像拼接时用随机抽样一致性(RANSAC)算法迭代计算过程中计算量大、匹配正确率低的问题,提出了一种基于运动平滑约束项的误匹配剔除算法。首先采用快速旋转不变特征(ORB)算法提取特征点,基于汉明距离实现特征点初匹配;其次,基于运动平滑约束项统计邻域支持估计量实现误匹配粗剔除;然后,进一步采用空间几何约束关系实现误匹配精剔除;最后,利用分组排序采样求解模型参数,采用加权平均实现图像融合。实验结果表明,该算法的误匹配剔除率相比缩小抽样点总量算法提升了75.6%,相比自适应阈值算法提升了24%,此方法能有效剔除误匹配,实现图像精确拼接。

关键词: 图像匹配, 快速旋转不变特征, 运动平滑约束项, 误匹配, 结构相似度

CLC Number: