首页 > 论文 > 光电工程 > 40卷 > 3期(pp:35-41)

视差生长与张量相结合的多基线稠密匹配

Multi-baseline Dense Matching Algorithm Based on Disparity Growing and Trifocal Tensor

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对特征点的稠密匹配问题,提出了一种视差生长与张量相结合的多基线稠密匹配算法。利用 SIFT特征提取方法在三视图中提取特征点,并用欧氏距离的方法进行粗匹配,使用所提取特征点的梯度方向特征计算梯度主方向角度差直方图,来去除误匹配,用得到的三视图匹配对计算三焦点张量和视差初值,用来引导稠密匹配。选取得到的两视图匹配点对作为根点进行视差生长,同时利用三焦点张量的点对应,得到三视图稠密匹配,并用视差初值引导匹配,以提高稠密匹配的精度。实验结果表明,本文方法计算出了稠密匹配,最后得到了精确的稠密视差图。

Abstract

A novel dense matching algorithm based on disparity growing and trifocal tensor is proposed because of the problem of dense matching. SIFT algorithm is used for the feature extraction of three-view. Then, the coarse matching is obtained by using the method of Euclidean distance. For removing the part incorrect matching of coarse matching set, gradient principal direction angle difference histogram of key point is used. Trifocal tensor and initial value of disparity which is used for directing dense matching is calculated by three-view matching. Root points which are selected from two-view matching points are used for disparity growing. Three-view dense matching is obtained by using point correspondence of trifocal tensor the same time. Then, initial value of disparity is used for improving the precision of the extraction. The experimental results indicate that the method get the accurate and dense matching in widely baseline case. Dense disparity map can be obtained.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391.41

DOI:10.3969/j.issn.1003-501x.2013.03.006

所属栏目:光电测量与检测

基金项目:河北省自然科学基金资助项目 (F2011203117)

收稿日期:2012-10-31

修改稿日期:2012-12-28

网络出版日期:--

作者单位    点击查看

胡春海:河北省测试计量技术及仪器重点实验室 (燕山大学 ),河北秦皇岛 066004
张立兴:河北省测试计量技术及仪器重点实验室 (燕山大学 ),河北秦皇岛 066004
孟春婵:河北省测试计量技术及仪器重点实验室 (燕山大学 ),河北秦皇岛 066004
范鹏发:河北省测试计量技术及仪器重点实验室 (燕山大学 ),河北秦皇岛 066004
平兆娜:河北省测试计量技术及仪器重点实验室 (燕山大学 ),河北秦皇岛 066004

联系人作者:胡春海(fred-hu@ysu.edu.cn)

备注:胡春海(1966-),男(汉族),黑龙江大庆人。教授,博士,主要从事机器视觉、多传感器数据融合等方面的研究。

【1】游素亚,徐光祐. 立体视觉研究的现状与进展 [J].中国图象图形学报, 1997,2(1):17-23. YOU Suya,XU Guangyou. State of the art and future the development of stero vision [J]. China Journal of Image and Graphics,1997,2(1):17-23.

【2】Okutomi M,Kanade T. A multiple baseline stereo [J]. IEEE Transactions on PAMI(S0162-8828),1993,15(4):353-363.

【3】张祖勋,杨生春,张剑清,等 . 多基线-数字近景摄影测量 [J].地理空间信息, 2007,5(1):1-4. ZHANG Zuxun,YANG Shengchun,ZHANG Jianqing,et al. Multi-Baseline Digital Close-Range Photogrammetry [J]. Geospatial Information,2007,5(1):1-4.

【4】柯涛,张祖勋,张剑清 . 旋转多基线数字近景摄影测量 [J].武汉大学学报:信息科学版, 2009,34(1):44-47. KE Tao,ZHANG Zuxun,ZHANG Jianqing. Panning and Multi-baseline Digital Close-range Photogrammetry [J]. Geomatics and Information Science of Wuhan University,2009,34(1):44-47.

【5】张连怡,王爱平,万国伟,等 . 基于 SIFT的三视图像特征匹配算法 [J].计算机工程, 2008,34(13):177-179. ZHANG Lianyi,WANG Aiping,WAN Guowei,et al. SIFT-based Feature Matching Algorithm of Three-view Images [J]. Computer Engineering,2008,34(13):177-179.

【6】郎海涛,王涌天,刘越,等 . 基于未标定图像序列的稠密重建算法 [J].系统仿真学报, 2008,20(9):363-366. LANG Haitao,WANG Yongtian,LIU Yue,et al. A Dense Construction Algoritjm Based on Uncalibrated Images [J]. Journal of System Simulation,2008,20(9):363-366.

【7】Alagoz B B. Obtaning depth maps from colour images by region based stereo matching algorithms [J]. OncuBilim Algorithm and Sys. Labs,2008,8(4):1-13.

【8】Hartley R,Zisserman A. Multiple View Geometry in Computer Vision [M]. [S. l.]:Cambridge Univ. Press,2000.

【9】David G. Distinctive image features from scale-invariant keypoints [J]. International Journal of Computer Vision(S0920-5691),2004,60(2):91-110.

【10】赵明,林长青 . 基于改进 SIFT特征的红外与可见光图像配准方法 [J].光电工程, 2011,38(9):130-136. ZHAO Ming,LIN Changqing. Registration of Infrared and Visible Images Based on Improved SIFT Feature [J]. Opto-Electronic Engineering,2011,38(9):130-136.

【11】Mikolajczyk K,Schmid C. A performance evaluation of local descriptors [J]. IEEE Transactions Pattern Analysis and Machine Intelligence(S0162-8828),2005,27(10):1615-1630.

引用该论文

HU Chunhai,ZHANG Lixing,MENG Chunchan,FAN Pengfa,PING Zhaona. Multi-baseline Dense Matching Algorithm Based on Disparity Growing and Trifocal Tensor[J]. Opto-Electronic Engineering, 2013, 40(3): 35-41

胡春海,张立兴,孟春婵,范鹏发,平兆娜. 视差生长与张量相结合的多基线稠密匹配[J]. 光电工程, 2013, 40(3): 35-41

被引情况

【1】胡春海,平兆娜,郭士亮,苏翔宇. 改进非参数变换测度下的立体匹配. 光电工程, 2014, 41(4): 47-53

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF