[1]洪磊[],嵇保健[],洪峰[]. 一种基于亚像素角点的 SIFT 立体匹配算法研究[J].计算机技术与发展,2016,26(01):48-52.
 HONG Lei[],JI Bao-jian[],HONG Feng[]. Research on a SIFT Stereo Matching Algorithm Based on Sub-pixel Corners[J].,2016,26(01):48-52.
点击复制

 一种基于亚像素角点的 SIFT 立体匹配算法研究()
分享到:

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
26
期数:
2016年01期
页码:
48-52
栏目:
智能、算法、系统工程
出版日期:
2016-01-10

文章信息/Info

Title:
 Research on a SIFT Stereo Matching Algorithm Based on Sub-pixel Corners
文章编号:
1673-629X(2016)01-0048-05
作者:
 洪磊[1]嵇保健[2] 洪峰[3]
1. 南京工程学院 汽车与轨道交通学院;2.南京工业大学 自动化与电气工程学院;3.南京航空航天大学 电子信息工程学院
Author(s):
 HONG Lei[1] JI Bao-jian[2] HONG Feng[3]
关键词:
 立体匹配亚像素角点尺度不变特征变换机器视觉
Keywords:
 stereo matchingsub-pixel cornerSIFTmachine vision
分类号:
TP391.41
文献标志码:
A
摘要:
 针对尺度不变特征变换(SIFT)算法在立体匹配应用中实时性差、误匹配、特征点无鲜明几何意义等问题,提出了一种新的基于亚像素角点的 SIFT 立体匹配算法。该算法首先提取图像角点作为特征点,并通过拟合内插法精确定位其亚像素坐标。在角点邻域内利用图像的梯度信息构造基于梯度直方图统计信息的特征描述子,最后通过对特征描述子的对称性相似度测量以及随机采样一致性筛选获得最终的目标匹配点。实验结果表明,该方法在保持较强鲁棒性的基础上,较大幅度地提高了算法的实时性能和匹配精度。
Abstract:
 In view of the problems of the poor real-time performance,mismatching and no distinct geometric characteristics points on ster-eo matching application based on the Scale Invariant Feature Transform (SIFT) algorithm,present a new SIFT stereo matching algorithm based on sub-pixel corners. At first,the image corners are extracted and located in sub pixel coordinates by fitting interpolation method. Then the feature descriptors are established by the field gradient image histogram information structure based on the statistical information for the corners. Finally,the symmetrical characteristic similarity is measured and random sample consensus algorithm is used to achieve ul-timate matching points. Experiments show that the proposed algorithm based on strong robustness,can greatly improve the real-time per-formance and the matching precision.

相似文献/References:

[1]王建文 王敏.基于双目立体视觉的鞋楦三维建模[J].计算机技术与发展,2009,(04):224.
 WANG Jian-wen,WANG Min.3D Reconstruction of Shoe- last Based on Binocular Stereo Vision[J].,2009,(01):224.
[2]方恒 吴怀宇.基于MRF和颜色空间的立体图像匹配算法[J].计算机技术与发展,2008,(12):28.
 FANG Heng,WU Huai-yu.Stereo Matching Based on MRF and Color Space[J].,2008,(01):28.
[3]印勇 张建华.基于三角形网格的浓密视差图提取[J].计算机技术与发展,2007,(11):52.
 YIN Yong,ZHANG Jian-hua.Dense Disparity Map Extraction Based on Triangulation Mesh[J].,2007,(01):52.
[4]毛雁明 杨慧玲.一种新的立体匹配算法[J].计算机技术与发展,2011,(03):105.
 MAO Yan-ming,YANG Hui-ling.A New Stereo Matching Algorithm[J].,2011,(01):105.
[5]周春燕 贾渊.基于遗传算法的图像配准研究及改进[J].计算机技术与发展,2011,(08):46.
 ZHOU Chun-yan,JIA Yuan.Research and Improvement of Image Registration Based on Genetic Algorithm[J].,2011,(01):46.
[6]王瑞 杨润泽 尹晓春.一种改进的立体像对密集点匹配算法[J].计算机技术与发展,2011,(09):70.
 WANG Rui,YANG Run-ze,YIN Xiao-chun.A Modified Image Dense Stereo Matching Algorithm[J].,2011,(01):70.
[7]袁力 张怡 丁丽君.基于加权匹配代价的初始视差估计算法[J].计算机技术与发展,2011,(10):36.
 YUAN Li,ZHANG Yi,DING Li-jun.Initial Disparity Estimation Algorithm Based on Weighted Matching Cost[J].,2011,(01):36.
[8]陈佳坤 罗谦 曾玉林.一种用于立体图像匹配的改进稀疏匹配算法[J].计算机技术与发展,2011,(10):63.
 CHEN Jia-kun,LUO Qian,ZENG Yu-lin.An Improved Sparse Matching Algorithm for Stereo Matching[J].,2011,(01):63.
[9]王兴昌 李炜 刘政怡 郭星.基于双密度双树复小波的立体匹配[J].计算机技术与发展,2012,(10):91.
 WANG Xing-chang,LI Wei,LIU Zheng-yi,et al.Stereo Matching Based on Double-density Dual-tree Complex Wavelet Transform[J].,2012,(01):91.
[10]汪瑶 徐杜 蒋永平 卢传泽.双目视觉小波域SIFT匹配与极线约束算法研究[J].计算机技术与发展,2012,(11):81.
 WANG Yao,XU Du,JIANG Yong-ping,et al.Study on Combined Wavelet-SIFT Matching and Epipolar Constraint Algorithm for Binocular Stereo Vision[J].,2012,(01):81.
[11]王雅宁[],梁新刚[]. 基于交互式图像分割的立体匹配方法[J].计算机技术与发展,2016,26(09):163.
 WANG Ya-ning[],LIANG Xin-gang[]. A Stereo Matching Method Based on Interactive Image Segmentation[J].,2016,26(01):163.

更新日期/Last Update: 2016-04-12