基于视差与灰度双层支持窗的立体匹配算法

doi:10.16180/j.cnki.issn1007-7820.2019.11.003

电子科技 ›› 2019, Vol. 32 ›› Issue (11): 12-18.doi: 10.16180/j.cnki.issn1007-7820.2019.11.003

基于视差与灰度双层支持窗的立体匹配算法

李小林,李文国,李浩

昆明理工大学机电工程学院,云南昆明 650500

收稿日期:2018-11-12 出版日期:2019-11-15 发布日期:2019-11-15
作者简介:李小林(1993-),男,硕士研究生。研究方向:机器视觉。|李文国(1973-),男,博士,副教授。研究方向:光学精密测量技术、机器视觉与图像处理技术、微型计算机测控技术、机器人视觉测量与控制技术。|李浩(1992-),男,硕士研究生。研究方向:光学精密测量技术、机器视觉。
基金资助:
昆明理工大学自然bepaly手机下载基金(KKSY201301070)

A Stereo Matching Using Double Layer Support Windows Based on RGB Map and Disparity Map

LI Xiaolin,LI Wenguo,LI Hao

Faculty of Mechanical and Electrical Engineering,Kunming University of Science and Technology,Kunming 650500,China

Received:2018-11-12 Online:2019-11-15 Published:2019-11-15
Supported by:
Natural Science Research Foundation of Kunming University of Science and Technology(KKSY201301070)

摘要/Abstract

摘要：

针对传统局部匹配支持窗难以利用空间、灰度距离远的像素信息的问题,提出一种基于视差和灰度的双层支持窗立体匹配算法。该算法根据视差图获得第一层视差支持窗,在视差支持窗内配合参考图RGB颜色灰度值获得灰度相似子支持窗;随后以视差窗、灰度窗、中心像素为优化路径,通过类动态规划算法优化聚合匹配代价;最后采用WTA策略选取最佳视差,更新所有视差,并不断迭代优化视差图直到视差收敛。经过Middlebury 平台的测评,新算法的平均误匹配率为5.15%。

关键词: 视差图, 灰度图, 双层支持窗, 动态规划, 迭代

Abstract:

Aiming at the problem that traditional local matching support window is difficult to use pixel information with long distance and gray distance, a stereoscopic matching algorithm using double layer support windows based on disparity map and RGB map was proposed in this study. The algorithm obtained the first layer disparity support window according to the disparity map, and obtained the gray scale similar sub-support window by matching the RGB color gray value of the reference picture in the disparity support window. The aggregation matching cost was optimized by class dynamic programming algorithm with parallax window, gray window and central pixel as optimized paths. Finally, the WTA strategy was used to select the best disparity, update all disparities and iteratively optimize the disparity map until convergence of the disparity map was achieved. After evaluation by the Middlebury platform, the average mismatch rate of the new algorithm was 5.15%.

Key words: the disparity map, the grey map, double layer support windows, dynamic programming, iterative

中图分类号:

TN911.73

李小林,李文国,李浩. 基于视差与灰度双层支持窗的立体匹配算法[J]. 电子科技, 2019, 32(11): 12-18.

LI Xiaolin,LI Wenguo,LI Hao. A Stereo Matching Using Double Layer Support Windows Based on RGB Map and Disparity Map[J]. Electronic Science and Technology, 2019, 32(11): 12-18.

图/表 5

图1

图2

图3

图4

表1

参考文献 18

[1]	张力, 黄影平 . 实时双目立体视觉系统的实现[J]. 电子科技, 2016,29(3):68-70.
	Zhang Li, Huang Yingping . Implementation of real-time binocular stereo vision system[J]. Electronic Science and Technology, 2016,29(3):68-70.
[2]	Hosni A, Rhemann C, Bleyer M , et al. Fast cost-volume filtering for visual correspondence and beyond[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013,35(2):504-11. doi: 10.1109/TPAMI.2012.156
[3]	林川 . 基于新扫描策略的快速立体匹配算法[J]. 电子科技, 2011,24(8):12-15.
	Lin Chuan . Fast stereo matching algorithm based on new scanning strategy[J]. Electronic Science and Technology, 2011,24(8):12-15.
[4]	Kanade T, Okutomi M . A stereo matching algorithm with an adaptive window: Theory and experiment[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1994,16(9):920-932.
[5]	Yoon K J, Kweon I S . Adaptive support-weight approach for correspondence search[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006,28(4):650-656.
[6]	Hirschmuller H . Stereo processing by semiglobal matching and mutual information[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2008,30(2):328-341.
[7]	Cheng F, Zhang H, Sun M , et al. Cross-trees, edge and superpixel priors-based cost aggregation for Stereo matching[J]. Pattern Recognition, 2015,48(7):2269-2278.
[8]	刘杰, 张建勋, 代煜 . 基于区域增长的稠密立体匹配[J]. 机器人, 2017,39(2):182-188.
	Liu Jie, Zhang Jianxun, Dai Yu . Dense stereo matching based on region growing[J]. Robot, 2017,39(2):182-188.
[9]	Min D, Lu J, Do M N . Joint histogram-based cost aggregation for stereo matching[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013,35(10):2539-2545. doi: 10.1109/TPAMI.2013.15
[10]	Wang L Q, Liu Z, Zhang Z H . Feature based stereo matching using two-step expansion[J].Mathematical Problems in Engineering 2014(14):452803-452809.
[11]	祝世平, 闫利那, 李政 . 基于改进Census 变换和动态规划的立体匹配算法[J]. 光学学报, 2016,36(4):0415001-415018.
	Zhu Shiping, Yan Lina, Li Zheng . Stereo Matching algorithm based on Improved census transform and dynamic programming[J]. Acta Optics Sin, 2016,36(4):0415001-0415018.
[12]	Scharstein D, Szeliski R . A taxonomy and evaluation of dense two-frame stereo correspondence algorithms[J]. International Journal of Computer Vision, 2002,47(1-3):7-42. doi: 10.1023/A:1014573219977
[13]	Taniai T, Matsushita Y, Naemura T. Graph cut based continuous stereo matching using locally shared labels [C].Columbus:IEEE Conference on Computer Vision and Pattern Recognition,IEEE Computer Society, 2014.
[14]	Yang Q. A non-local cost aggregation method for stereo matching [C]. Providence:Computer Vision and Pattern Recognition,IEEE, 2012.
[15]	Chang X, Zhou Z, Wang L, et al. Real-time accurate stereo matching using modified two-pass aggregation and winner-take-all guided dynamic programming [C]. Hangzhou:International Conference on 3D Imaging, Modeling, Processing,Visualization and Transmission, 2011.
[16]	Rhemann C, Hosni A, Bleyer M, et al. Fast cost-volume filtering for visual correspondence and beyond [C]. Colorado Springs:IEEE Conference on Computer Vision and Pattern Recognition, 2011.
[17]	Psota E T, Kowalczuk J, Carlson J , et al. A local iterative refinement method for adaptive support-weight stereo matching[C].Las Vegas:Proceedings of the International Conference on Image Processing, Computer Vision, and Pattern Recognition(IPCV) , 2011.
[18]	Wang L, Yang R. Global stereo matching leveraged by sparse ground control points [C]. Colorado Springs:IEEE Conference on Computer Vision and Pattern Recognition, 2011.

算法	Tsukuba			Venus			Teddy			Cones			Average Error
算法	n-occ	all	disc	n-occ	all	disc	n-occ	all	disc	n-occ	all	disc	Average Error
本文算法	1.29	1.78	6.99	0.26	0.45	2.38	5.42	10.49	15.02	2.34	8.63	6.77	5.15
CostFilter	1.51	1.85	7.61	0.20	0.39	2.42	6.16	11.80	16.00	2.71	8.24	7.66	5.55
MCT	1.41	1.74	6.86	0.27	0.38	3.04	5.94	11.40	14.90	2.64	7.86	7.37	5.31
GlobalGCP	0.87	2.54	4.69	0.46	0.53	2.22	6.44	11.50	16.20	3.59	9.49	8.90	5.60
CrossTrees+SP	1.68	1.99	7.82	0.22	0.32	2.84	6.23	11.70	14.80	2.52	7.71	7.50	5.44
HistoAggr2	1.93	2.30	6.39	0.16	0.46	2.22	5.88	11.30	14.70	2.41	7.78	6.89	5.20
IterAdaptWgt	0.85	1.28	4.59	0.35	0.86	4.53	7.60	14.50	17.30	3.20	9.36	8.49	6.08
TwoStep	2.91	3.68	13.30	0.27	0.45	2.63	7.42	12.60	18.00	4.09	10.10	10.30	7.14

基于视差与灰度双层支持窗的立体匹配算法

A Stereo Matching Using Double Layer Support Windows Based on RGB Map and Disparity Map

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 5

参考文献 18

相关文章 15

Metrics

本文评价

推荐阅读 3

[1]	唐胜男,吕毅斌,王樱子,房巾莉,武德安. 基于Hybrid迭代法的多连通域数值保角变换计算法[J]. 电子科技, 2021, 34(7): 13-18.
[2]	严羽灵,唐清善,白创. 基于仿射变换的地磁匹配定位算法[J]. 电子科技, 2021, 34(4): 70-74.
[3]	张雪映,吴小婷,Daniel Eliote Mbanze,周正威. 基于SEOA算法的抽水蓄能梯级水库调度研究[J]. 电子科技, 2019, 32(7): 17-21.
[4]	赵威,曾国辉,黄勃,朱爽鑫,刘瑾. 基于改进局部搜索算法的三维空间路径规划研究[J]. 电子科技, 2019, 32(6): 58-63.
[5]	张龙，卫琛戈，常伟，张睿航，钟岩. 牛顿迭代法在草图约束优化问题中的改进[J]. , 2018, 31(4): 64-.
[6]	卢文良. 两种针对小信号的脉压优化算法及实现[J]. , 2016, 29(3): 61-.
[7]	龚楷椿,邬春学. 基于邻接矩阵的自适应图像分割算法研究[J]. , 2016, 29(2): 66-.
[8]	李影，徐伯庆. 一种基于压缩感知的迭代重建算法[J]. , 2016, 29(11): 129-.
[9]	莫礼东，徐伯庆. 一种改进的TV图像重建算法[J]. , 2016, 29(10): 47-.
[10]	年雷，麦云飞. 基于机器视觉的自由曲面轮廓度检测系统[J]. , 2016, 29(10): 104-.
[11]	李超. 基于FPGA的TPC编译码器设计与实现[J]. , 2015, 28(5): 121-.
[12]	余婷. 基于结构相似度的图像去噪新方法[J]. , 2015, 28(3): 1-.
[13]	刘梦涛,金晓峰,刘道余,梁添才. 基于迭代算法的纸币图像偏色校正技术[J]. , 2015, 28(12): 107-.
[14]	胡娟,仰枫帆. 基于FPGA的大围数QC_LDPC码的译码器[J]. , 2014, 27(3): 112-.
[15]	陈玥琪. 一类牛顿迭代法求解绝对值方程[J]. , 2014, 27(2): 1-.