摘要
针对处理重复内容、非单一平面场景时传统方法常见的误匹配、漏匹配问题,提出基于特征点拓扑结构及三角剖分的无约束场景特征匹配方法.利用相似内容比非相似内容具有明显更近特征描述欧氏距离的特点,提出K近邻距离比算法,保留具有明显更小灰度及梯度差异的多对多特征点对作为初匹配,以减少漏匹配;通过特征点三角剖分的映射去除K近邻距离比初匹配中一对一误匹配;根据两图特点集的拓扑相似性度设计基于拓扑的分级三角剖分算法,并对K近邻距离比初匹配中多对多匹配进行一对一确认,得到无约束场景特征匹配结果.实验结果表明,该方法可同时显著抑制误匹配和漏匹配.
Repeated contents and non-single-plane scenes usually lead to serious mismatching or missed match-ing. A novel feature matching method using topology structure and triangulation is proposed to match images without any constraint conditions. First, using Euclidean distance to measure similarity, similar features are sig-nificantly closer than dissimilar contents.K nearest neighbors distance ratio algorithm is proposed to find match-ing candidates which have significantly smaller distances. Second, 1-to-1-matches in reference image are trian-gulated, and the triangulation is mapping to the target image. The outliers which do not conform to the triangula-tion rules are moved. Then, all feature-sets are hierarchically triangulated based on topology similarity measure, and m-to- n-matches are reduced to 1-to-1-matches. The experimental results show that with the proposed method, mismatching and missed matching can be greatly reduced.
出处
《计算机辅助设计与图形学学报》
EI
CSCD
北大核心
2015年第5期799-807,共9页
Journal of Computer-Aided Design & Computer Graphics
基金
国家自然科学基金(61301221)
上海市自然科学基金(11ZR1413400)
上海市教育委员会科研创新基金(12YZ007)
关键词
特征匹配
三角剖分
拓扑结构
K近邻距离比
feature matching
triangulation
topology structure
K nearest neighbors distance ratio