| 摘要: |
| [目的]为了减小三维重建的重投影误差,提出一种改进的SIFT(Scale Invariant Feature Transform)算法。[方法]首先使用SIFT提取和匹配特征点,将这些匹配点作为归一化互相关(Normalized Cross-correlati-on,NCC)的初始匹配对;然后使用特征点的主方向对局部图像进行旋转校正;最后计算该初始匹配对NCC系数并将相似地貌中的误配点剔除。[结果]该方法剔除了大量的误配点,提高了特征点的正确匹配率和重建结果的精度。[结论]改进的SIFT算法能够得到更为准确的匹配点对,获得较好的重建效果。 |
| 关键词: SIFT 三维重建 重投影误差 归一化互相关(NCC) 主方向 正确匹配率 精度 |
| DOI： |
| 投稿时间：2013-12-10修订日期：2013-12-30 |
| 基金项目: |
|
| The Improvement of SIFT Algorithm |
|
YU Bo-yi1, LI Mei-yan2
|
| (1.The Second Middle School of Nanning, Nanning, Guangxi, 530022, China;2.School of Computer and Electronic Information, Guangxi University, Nanning, Guangxi, 530004, China) |
| Abstract: |
| [Objective] In order to reduce the reprojection error of reconstruction, an improved SIFT algorithm is proposed.[Method] Firstly, SIFT is used to detect and match the features. These match points are used as the initial match on normalized cross-correlation (NCC). Then dominant direction of feature points is used for rotation correction of local image. Finally, the coefficient of normalized cross-correlation matching(NCC) is calculated and the mismatches points in the similar geographical environment are removed.[Result] This method removes a lot of mismatches points, and improves the rate of correct matching and precision of reconstruction.[Conclusion] Experiment results show that the improved algorithm can achieve reconstruction effect. |
| Key words: SIFT 3D reconstruction reprojection error normalized cross correlation(NCC) dominant direction correct matching rate precision |
