[1]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):91-93.
　WANG Xing-chang,LI Wei,LIU Zheng-yi,et al.Stereo Matching Based on Double-density Dual-tree Complex Wavelet Transform[J].,2012,(10):91-93.
点击复制

基于双密度双树复小波的立体匹配()
分享到：

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

卷:
期数:
2012年10期
页码:
91-93
栏目:
智能、算法、系统工程
出版日期:
1900-01-01

文章信息/Info

Title:
Stereo Matching Based on Double-density Dual-tree Complex Wavelet Transform
文章编号:
1673-629X（2012）10-0091-03
作者:
王兴昌 李炜 刘政怡 郭星
安徽大学计算机学院
Author(s):
WANG Xing-chang;  LI Wei;  LIU Zheng-yi;  GUO Xing
College of Computer, Anhui University
关键词:
立体匹配; 相位匹配; 双密度双树复小波; 金字塔模式
Keywords:
stereo matching ;  phase matching;  double-density dual tree complex wavelet ;  pyramid model
分类号:
TP31
文献标志码:
A
摘要:
立体匹配成为近年计算机视觉研究的重点，文中旨在通过研究和实验探索出一种比较理想的立体匹配算法从而提高图像立体匹配的鲁棒性。双密度双树复小波具有多分辨率、数据冗余的有限性以及平移不变性的优点，文章利用双密度双树复小波的这些优点提出一种相位匹配算法，其原理是提取多尺度的相位信息作为立体像对的匹配基元，再利用金字塔模式实现匹配。进行匹配时首先由最低分辨率的层级开始，再逐层推进，直至图层的最高级，并利用上层匹配所获得的视差结果来引导本层通道的相位匹配，形成一种多分辨率的层次匹配框架，即图像金字塔结构框架。作者利用这种方法最终达到了预期的实验效果。实验结果表明，采用此方法能够得到稠密的视差图，匹配结果精确度很高，是目前比较理想的立体匹配算法
Abstract:
Stereo matching is becoming the focus of computer vision research in recent years,it aims to explore a more ideal stereo matching algorithm by doing research and experiments to improve the robustness of image matching. Double-density dual-tree complex wavelet has the advantages of multi-resolution,limited data redundancy and translational invariance. According to these advantages of double-density dual-tree complex wavelet,proposed a phase-matching algorithm,its principle is to extract multi-scale phase information as a three-dimensional like a pair matching primitives,and then use the pyramid model to achieve matching. First match the lowest resolution level, layer by layer and then push forward until the layer which is the most advanced, and use the upper matching the parallax results to guide the phase matching of the channels in this layer,forming a multi-resolution level matching framework, call it the framework of the image pyramid structure. The author uses this method to ultimately achieve the expected experimental results. The experimental results show that by this method get a dense disparity map,which has the highly accurate matching results,at present it is the most ideal stereo matching algorithm

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,(10):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,(10):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,(10):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,(10):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,(10):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,(10):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,(10):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,(10):63.
[9]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,(10):81.
[10]李竹林,许淳.基于梯度不变的彩色图像宽基线立体匹配方法[J].计算机技术与发展,2013,(03):65.
　LI Zhu-lin,XU Chun.A Stereo Matching Method for Color Image Wide Baseline Based on Gradient Invariant[J].,2013,(10):65.

备注/Memo

备注/Memo:
安徽省自然基金青年基金项目（11040606Q07）;高校省级重点自然科学研究项目（kj2010A023）王兴昌（1985-），男，河北青县人，硕士研究生，研究方向为模式识别、计算机双目视觉；李炜，教授，博士，研究方向为中文信息处理、图像处理
更新日期/Last Update: 1900-01-01