基于线性滤波的树结构动态规划立体匹配算法

储珺; 龚文; 缪君; 张桂梅

doi:10.16383/j.aas.2015.c140693

基于线性滤波的树结构动态规划立体匹配算法

doi: 10.16383/j.aas.2015.c140693

储珺^1,2, ,,
龚文²,
缪君^1,2,
张桂梅^1,2

1.
南昌航空大学计算机视觉研究所南昌 330063;
2.
江西省图像处理与模式识别重点实验室南昌 330063

基金项目:

国家自然科学基金(61263046,61462065),江西省自然科学基金(20122BAB201037)资助

详细信息

作者简介:
龚文南昌航空大学航空软件学院硕士研究生.主要研究方向为计算机视觉与图像处理.E-mail:gongwen@nchu.edu.cn

缪君南昌航空大学航空制造工程学院讲师.主要研究方向为计算机视觉与图像处理.E-mail:miaojun@nchu.edu.cn

张桂梅南昌航空大学航空制造工程学院教授.主要研究方向为图像处理,计算机视觉与模式识别.E-mail:zhangguimei@nchu.edu.cn

通讯作者:
储珺南昌航空大学软件学院教授.主要研究方向为图像处理与计算机视觉.本文通信作者.E-mail:chuj@nchu.edu.cn

计量
- 文章访问数: 2274
- HTML全文浏览量: 115
- PDF下载量: 997
- 被引次数: 0
出版历程
- 收稿日期: 2014-10-10
- 修回日期: 2015-08-09
- 刊出日期: 2015-11-20

A Tree Structure Dynamic Programming Stereo Matching Algorithm Based on Linear Filtering

CHU Jun^{1,2
, ,},
GONG Wen²,
MIAO Jun^1,2,
ZHANG Gui-Mei^1,2

1.
Institute of Computer Vision, Nanchang Hangkong University, Nanchang 330063;
2.
Jiangxi Province Key Laboratory of Image Processing and Pattern Recognition, Nanchang 330063

Funds:

Supported by National Natural Science Foundation of China (61263046, 61462065), Natural Science Foundation of Jiangxi Province (20122BAB201037)

摘要

摘要: 传统的动态规划立体匹配算法能有效保证匹配精度的同时提高运行速度, 但得到的视差深度图会出现明显的条纹现象,同时在图像弱纹理区域以及边缘存在较高的误匹配. 针对该问题,提出了一种新的基于线性滤波的树形结构动态规划立体匹配算法. 算法首先运用改进的结合颜色和梯度信息参数可调的自适应测度函数构建左右图像的匹配代价, 然后以左图像为引导图对构建的匹配代价进行滤波; 再运用行列双向树形结构的动态规划算法进行视差全局优化, 最后进行视差求精得到最终的视差图.理论分析和实验结果都表明, 本文的算法能有效地改善动态规划算法的条纹现象以及弱纹理区域和边缘存在的误匹配.
- 立体匹配 /
- 动态规划 /
- 树结构 /
- 线性滤波
Abstract: The traditional dynamic programming stereo matching algorithm can effectively guarantee the precision of matching and improve the running speed; but the depth of the parallax figure has the obvious stripes phenomenon, at the same time the low texture region and edge of the image have higher mismatch. For these problems, the paper proposes a new tree structure based on the linear filtering dynamic programming stereo matching algorithm. The algorithm firstly uses an improved adjustable parameters adaptive measure function to combine the color and gradient information of the matching images. Secondly, it uses the left image to guide the figure to filter the price of stereo matching. Thirdly, it utilizes the two direction simple tree structure dynamic programming optimization; and finally uses the parallax refinement method to get the final parallax figure. Theoretical analysis and experimental results have showed that the proposed algorithm can not only effectively eliminate the stripes phenomenon of dynamic programming algorithm but also improve the mismatch of the low texture area and the edge of the image.
- Stereo matching /
- dynamic programming /
- tree structure /
- linear filtering

HTML全文

参考文献(14)

[1]	[2] Scharstein D, Szeliski R. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. International Journal of Computer Vision, 2002, 47(1-3):7-42
[2]	Zheng Zhi-Gang, Wang Zeng-Fu. A region based stereo matching algorithm using cooperative optimization. Acta Automatica Sinica, 2009, 35(5):469-477(郑志刚, 汪增福. 基于区域间协同优化的立体匹配算法. 自动化学报, 2009, 35(5):469-477)
[3]	[4] Yoon K J, Kweon I S. Adaptive support-weight approach for correspondence search. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(4):650-656
[4]	Li De-Guang, Li Ke-Jie, Gao Li-Li. Stereo vision using multiresolution and multiorientation phase matching. Chinese Journal of Scientific Instrument, 2004, 25(4S):600-602(李德广, 李科杰, 高丽丽. 基于多尺度多方向相位匹配的立体视觉方法. 仪器仪表学报, 2004, 25(4S):600-602)
[5]	[6] Klaus A, Sormann M, Karner K. Segment-based stereo matching using belief propagation and a self-adapting dissimilarity measure. In:Proceedings of the 18th International Conference on Pattern Recognition. Hong Kong, China:IEEE, 2006. 15-18
[6]	[7] Wang H Q, Wu M, Zhang Y B, Zhang L. Effective stereo matching using reliable points based graph cut. In:Proceedings of the 2013 Visual Communications and Image Processing. Kuching:IEEE, 2013. 1-6
[7]	[8] Kim J C, Lee K M, Choi B T, Lee S U. A dense stereo matching using two-pass dynamic programming with generalized ground control points. In:Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, CA, USA:IEEE, 2005. 1075-1082
[8]	[9] Xu Z L, Ma L Z, Kimachi M, Suwa M. Efficient contrast invariant stereo correspondence using dynamic programming with vertical constraint. The Visual Computer, 2008, 24(1):45-55
[9]	Veksler O. Stereo correspondence by dynamic programming on a tree. In:Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, USA:IEEE, 2005. 384-390
[10]	Rhemann C, Hosni A, Bleyer M, Rother C, Gelautz M. Fast cost-volume filtering for visual correspondence and beyond. In:Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition. Providence, RI:IEEE, 2011. 3017-3024
[11]	Bleyer M, Gelautz M. Simple but effective tree structures for dynamic programming-based stereo matching. In:Proceedings of the Third International Conference on Computer Vision Theory and Applications. Madeira, Portugal:2008. 2
[12]	Hirschmuller H, Scharstein D. Evaluation of stereo matching costs on images with radiometric differences. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(9):1582-1599
[13]	Hu T B, Qi B J, Wu T, Xu X, He H G. Stereo matching using weighted dynamic programming on a single-direction four-connected tree. Computer Vision and Image Understanding, 2012, 116(8):908-921
[14]	Zhang Li-Min, Zhou Shang-Bo. Feature matching of scale invariant feature transform images based on fractional differential approach. Journal of Computer Applications, 2011, 31(4):1019-1023(张丽敏, 周尚波. 基于分数阶微分的尺度不变特征变换图像匹配算法. 计算机应用, 2011, 31(4):1019-1023)