| 面向宽基线立体影像匹配的高质量仿射不变特征提取方法 |
| |
| 引用本文： | 程亮,龚健雅,宋小刚,杨晓霞.面向宽基线立体影像匹配的高质量仿射不变特征提取方法[J].测绘学报,2008,37(1):77-82. |
| |
| 作者姓名： | 程亮 龚健雅 宋小刚 杨晓霞 |
| |
| 作者单位： | 武汉大学测绘遥感信息工程国家重点实验室,湖北武汉,430079;武汉大学遥感信息工程学院,湖北武汉,430079 |
| |
| 基金项目： | 国家重点基础研究发展计划(973计划) |
| |
| 摘 要： | 针对宽基线影像匹配问题,提出基于信息量和空间分布均衡性双重约束的多层次特征筛选方法,并在此基础上探讨集成该特征筛选方法、MSER(Maximally Stable Extremal Region detector)、SIFT(Scale Invariant Scale Transformation)的特征提取算法,以达到提取高质量(高信息量、空间分布均衡、高重复率)仿射不变特征的目的。实验表明,相对现有最优算法,本文方法具有更高的重复率和匹配成功率,更有利于后续的(宽基线)立体匹配。
|
| 关 键 词： | 宽基线立体匹配 仿射不变 特征提取 信息量 空间分布离散度 |
| 文章编号： | 1001-1595（2008）01-0077-06 |
| 收稿时间： | 2007-02-06 |
| 修稿时间： | 2007-06-01 |
A Method for Affine Invariant Feature Extraction with High Quality for Wide Baseline Stereo Image Matching |
| |
| CHENG Liang,GONG Jian-ya,SONG Xiao-gang,YANG Xiao-xia.A Method for Affine Invariant Feature Extraction with High Quality for Wide Baseline Stereo Image Matching[J].Acta Geodaetica et Cartographica Sinica,2008,37(1):77-82. |
| |
| Authors: | CHENG Liang GONG Jian-ya SONG Xiao-gang YANG Xiao-xia |
| |
| Abstract: | Wide baseline stereo image matching is a challenging problem in image processing and computer vision. For the purpose of wide baseline stereo image matching, a filter strategy of affine invariant feature based on information content and spatial distribution constraints is put forward. Moreover, a new feature extraction algorithm integrating MSER, SIFT and this filter method is discussed, in order to realize high quality (high information content, good spatial distribution, high repeatability) affine invariant feature extraction. The experiments by using of actual wide baseline images sequence with different texture features prove that this method guarantees much better repeatability, which benefits the subsequent stereo image matching. |
| |
| Keywords: | wide baseline stereo matching affine invariant feature extraction information content spatial distribution dispersion |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
