改进非参数变换测度下的立体匹配

胡春海; 平兆娜; 郭士亮; 苏翔宇

doi:doi:10.3969/j.issn.1003-501x.2014.04.008

光电工程, 2014, 41 (4): 47, 网络出版: 2014-04-09

改进非参数变换测度下的立体匹配

Stereo Matching with Modified Non-parametric Transform Measure

论文大纲

胡春海 ^*平兆娜郭士亮苏翔宇

作者单位

燕山大学测试计量技术及仪器重点实验室, 河北秦皇岛 066004

机器视觉立体匹配相似性测度纹理度量非参数变换 machine vision stereo matching similarity measure texture metric non-parametric transform

摘要

针对传统非参数变换测度的局限性, 提出了一种基于局部纹理加权项的非参数Census 变换测度, 并使用半全局匹配法聚合代价的立体匹配算法。根据图像纹理度量的方向性, 通过增加局部纹理反差值计算匹配窗口内所有像素的灰度均值, 将其与反差值的加权和作为现匹配基元。使用半全局匹配法计算8 邻域方向的匹配代价, 以最小代价为匹配条件选取初始视差值。最后, 利用图像分割法统计各分割区域的视差直方图, 以直方图主峰所对应的视差值作为最终视差值。实验结果表明, 该算法获得的视差精度优于当前多数局部算法, 处理立体匹配中幅度失真的问题效果明显, 能够很好地适应于真实场景测量。

Abstract

Due to the limitations of the traditional non-parametric transform measures, a stereo matching algorithm based on non-parametric transform measure with local texture weighted item and semi-global matching method to aggregate cost is proposed. According to the directivity of the image texture metric, a contrast value of local texture is added to calculate the grayscale mean of all of the pixels in the window. The mean and the local texture contrast value are weighted sum as new matching primitive. The matching cost is determined by using semi-global matching from 8 directions. It is subsequently optimized by minimum cost to gain initial disparity. Finally, the parallax histogram of each divided region is obtained through image segmentation based on mean-shift. Peak is selected as the final disparity of each region to obtain the dense disparity map. Experimental results show that the algorithm gets more accurate results than lots of the local algorithms. It is a good solution to the distortion problem and be well adapted to the measurement of the real scene.

参考文献

[1] 胡春海, 张立兴, 孟春婵, 等. 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.

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

[2] 邾继贵, 于之靖. 视觉测量原理与方法 [M]. 北京: 机械工业出版社, 2012.

ZHU Jigui, YU Zhijing. Principle of Vision Metrology [M]. Beijing: Mechanical Industry Press, 2012.

[3] Scharstein D, Szeliski R. A Taxonomy and Evaluation of Dense Two-frame Stereo Correspondence Algorithms [J]. International Journal of Computer Vision(S0920-5691), 2002, 47(1): 7-42.

[4] Yoon K, Kweon S. Locally Adaptive Support-weight Approach for Visual Correspondence Search [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence(S0162-8828), 2006, 28(4): 650-656.

[5] Tombari F, Mattoccia S, Stefano L D. Segmentation Based Adaptive Support for Accurate Stereo Correspondence [C]//Proceedings of IEEE Pacific Rim Symposium on Video and Technology, Santiago, Chile, Dec 17-19, 2007: 427-438.

[6] Heo Y S, Lee K M, Lee S U. Robust Stereo Matching Using Adaptive Normalized Cross-correlation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence(S0162-8828), 2011, 33(4): 807-822.

[7] Hirschmuller H, Scharstein D. Evaluation of Stereo Matching Cost on Images with Radiometric Differences [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence(S0162-8828), 2009, 31(9): 1582-1599.

[8] Hirschmuller H. Accurate and Efficient Stereo Processing by Semi-global Matching and Mutual Information [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence(S0162-8828), 2008, 30(2): 328-341.

[9] Comanici D, Meer P. Mean Shift: A Robust Approach Toward Feature Space Analysis [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence(S0162-8828), 2002, 24(5): 603-619.

[10] 周龙, 徐贵力, 李开宇, 等. 基于Census 变换和改进自适应窗口的立体匹配算法 [J]. 航空学报, 2012, 33(5): 886-892.

ZHOU Long, XU Guili, LI Kaiyu, et al. Stereo Matching Algorithm Based on Census Transform and Modified Adaptive Windows [J]. Aeronautica et Astronautica Sinica, 2012, 33(5): 886-892.

[11] 王天召, 徐克虎, 陈金玉, 等. 运动背景下移动目标分割定位算法研究 [J]. 光电工程, 2013, 40(10): 35-41.

WANG Tianzhao, XU Kehu, CHEN Jinyu, et al. Algorithm of Segmentation and Location of Moving Object in Moving Scenes [J]. Opto-Electronic Engineering, 2013, 40(10): 35-41.

[12] 刘振涛, 王朝英, 刘卫群. 基于多特征的双模版自适应更新跟踪算法 [J]. 应用光学, 2012, 33(1): 78-84.

LIU Zhentao, WANG Zhaoying, LIU Weiqun. Tracking Algorithm of Dual Template Adaptive Updating Based on Multiple Features [J]. Journal of Applied Optics, 2012, 33(1): 78-84.

[13] Boykov Y, Veksler O, Zabih R. Fast Approximate Energy Minimization via Graph Cuts [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence(S0162-8828), 2001, 23(11): 1222-1239.

[14] Humenberger M, Zinner C, Weber M, et al. A Fast Stereo Matching Algorithm Suitable for Embedded Real-time Systems [J]. Computer Vision and Image Understanding(S1077-3142), 2010, 114(11): 1180-1202.

[15] Mei X, Sun X, Zhou M, et al. On Building an Accurate Stereo Matching System on Graphics Hardware [C]// Proceedings of IEEE Computer Vision Workshop on GPU in Computer Vision Applications, Barcelona, Spain, Nov 6-13, 2011: 467-474.

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[J]. 光电工程, 2014, 41(4): 47. HU Chunhai, PING Zhaona, GUO Shiliang, SU Xiangyu. Stereo Matching with Modified Non-parametric Transform Measure[J]. Opto-Electronic Engineering, 2014, 41(4): 47.

改进非参数变换测度下的立体匹配

关于本站 Cookie 的使用提示

全站搜索

改进非参数变换测度下的立体匹配

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索