Stereo matching for Fish-eye images based on epipolar geometry and support neighborhood

Tao SONG; Wen-li XIONG; Pei-guo HOU; Hai-bin LI; Chen CHEN

doi:10.3788/OPE.20162408.2050

您当前的位置：

首页 >

文章列表页 >

Stereo matching for Fish-eye images based on epipolar geometry and support neighborhood

Information Sciences | 更新时间：2020-07-07

- Stereo matching for Fish-eye images based on epipolar geometry and support neighborhood
- Optics and Precision Engineering Vol. 24, Issue 8, Pages: 2050-2058(2016)
- 作者机构：
  
  1.燕山大学工业计算机控制工程河北省重点实验室, 河北秦皇岛 066004
  2.秦皇岛视听机械研究所, 河北秦皇岛 066000
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20162408.2050
  CLC： TP391.41
- Received：13 May 2016，
  
  Accepted：22 June 2016，
  
  Published：25 August 2016
- 稿件说明：
移动端阅览
Tao SONG, Wen-li XIONG, Pei-guo HOU, et al. Stereo matching for Fish-eye images based on epipolar geometry and support neighborhood[J]. Optics and precision engineering, 2016, 24(8): 2050-2058.
DOI：

Tao SONG, Wen-li XIONG, Pei-guo HOU, et al. Stereo matching for Fish-eye images based on epipolar geometry and support neighborhood[J]. Optics and precision engineering, 2016, 24(8): 2050-2058. DOI： 10.3788/OPE.20162408.2050.

摘要

提出了一种基于极曲线几何和变支持邻域的立体匹配算法来解决鱼眼立体视觉中图像变形导致的极曲线求取和匹配代价计算问题。首先，对鱼眼相机进行标定并获取相机的相关参数；针对鱼眼镜头的畸变问题，根据鱼眼镜头的优化投影模型推导出系统的极曲线方程，并利用得到的极线方程确定对应点的搜索范围。然后，根据同源像点在左右图像上的位置关系确定各中心像素点的支持邻域，并计算出不同视差条件下该支持邻域在另一幅图像上的对应支持邻域，利用获取的支持邻域计算出各点的匹配代价。最后，利用WTA(Winner Takes All)策略选取最佳匹配点得到最终的匹配结果。基于提出的极曲线和支持邻域对两组鱼眼图像进行了匹配实验并与传统方法进行了实验对比，结果表明：提出的方法的匹配准确度比传统方法分别提高了4.03%和4.64%。实验结果验证了极曲线的应用加快了匹配速度并减少了误匹配；支持邻域的使用使其对匹配代价计算的准确度优于传统方法。该算法满足了鱼眼图像立体匹配对信息获取速度、准确度和数量的要求。

Abstract

A stereo matching algorithm based on epipolar geometry and support neighborhood was proposed to solve the problems of epipolar curve and matching cost calculation caused by image distortion in fisheye stereo system. Firstly

a fisheye camera was calibrated to obtain its relevant parameters. For the lens distortion of a fisheye lens

the epipolar curves of the system were derived according to the projection model of fisheye lens

and these epipolar curves were used to define searching scope when searching for corresponding points. Then

according to the position relationship between homologous points on the left and right images

the support neighborhood of each pixel was determined

the corresponding support neighborhood in other image was calculated in different parallaxes and the local matching cost was calculated based on support neighborhoods. Finally

matching results were obtained by using the Winner Takes All(WTA) strategy. The epipolar geometry and support neighborhood were used to perform a matching experiment and a comparison experiment for two groups of fisheye images. Experimental results show that the matching accuracies of the two groups are increased by 4.03% and 4.64% respectively as compared to traditional methods. It concludes that the epipolar curves speed up the matching speed and reduce the error; the accuracy rate of matching cost calculation by proposed support neighborhood is also superior to that of the traditional matching for the fisheye lens. This method meets the requirements of stereo matching of fisheye images for capturing speeds

accuracy and quantity.

关键词

Keywords

references

王灿进, 孙涛, 陈娟. 局部不变特征匹配的并行加速技术研究[J]. 液晶与显示, 2014, 29(2): 266-274.

WANG C J, SUN T, CHEN J. Speeding up local invariant feature matching using parallel technology[J]. Chinese Journal of Liquid Crystals and Displays, 2014, 29(2): 266-274. (in Chinese)

肖志涛, 卢晓方, 耿磊, 等. 基于极线校正的亚像素相位立体匹配方法[J]. 红外与激光工程, 2014, 43(S1): 225-230.

XIAO ZH T, LU X F, GENG L, et al.. Sub-pixel matching method based on epipolar line rectification[J]. Infrared and Laser Engineering, 2014, 43(S1): 225-230. (in Chinese)

张来刚, 魏仲慧, 何昕, 等. 面向低纹理图像的快速立体匹配[J]. 液晶与显示, 2013, 28(3): 450-458.

ZHANG L G, WEI ZH H, HE X, et al.. New stereo matching method based edge extraction[J]. Chinese Journal of Liquid Crystals and Displays, 2013, 28(3): 450-458. (in Chinese)

杨晟, 李学军, 朱诗兵, 等. 抗仿射形变异构金字塔复合描述点特征匹配算法[J]. 红外与激光工程, 2014, 43(7): 2387-2392.

YANG SH, LI X J, ZHU SH B, et al.. Robust affine-invariant isomerous pyramid feature and multi-description for point feature matching [J]. Infrared and Laser Engineering, 2014, 43(7): 2387-2392. (in Chinese)

MOREAU J, AMBELLOUIS S, RUICHEK Y. 3D reconstruction of urban environments based on fisheye stereovision[C].IEEE International Conference on Signal Image Technology and Internet Based Systems (SITIS), 2012, 42(4): 36-41.

LI S G. Binocular spherical stereo[J]. IEEE Transactions on Intelligent Transportation Systems.2008, 9(4): 589-600.

LI S G. Real-time spherical stereo[C].IEEE International Conference on Pattern Recognition(ICPR). 2006, 3: 1046-1049.

HANE C, HENG L, LEE G, et al..Real-time direct dense matching on fisheye images using plane-sweeping stereo[C].IEEE International Conference on 3D Vision(3DV). 2014: 57-64.

DRULEA M, SZAKATS I, VATAVU A, et al.. Omnidirectional stereo vision using fisheye lenses[C].2014 IEEE International Conference on Intelligent Computer Communication and Processing (ICCP).2014: 251-258.

KIM D, CHOI J, YOO H, et al..Rear obstacle detection system with fisheye stereo camera using HCT[J].Expert Systems with Applications, 2015, 42(17-18): 6295-6305.

GOEDEME T, NUTTIN M , TUYTELAARS T, et al.. Omnidirectional vision based on topological navigation [J]. International Journal of Computer Vision(IJCV), 2007, 74(3): 219-236.

KITA N. Direct floor height measurement for biped walking robot by fisheye stereo[C]. IEEE International Conference on Humanoid Robots (Humanoids), 2011, 187-192.

陈琛, 胡春海. 球幕投影通用型变焦鱼眼镜头设计[J]. 光学精密工程, 2013, 21(2): 323-335.

CHEN CH, HU CH H. Design of general type zoom fish-eye lens for dome-screen projector [J]. Opt. Precision Eng., 2013, 21(2): 323-335.(in Chinese)

张宝龙, 李丹, 张少敬, 等. 非球面鱼眼镜头设计及畸变校正算法研究[J]. 光学学报, 2014, 34(12): 222-227.

ZHANG B L, LI D, ZHANG SH J, et al.. Design of aspheric fisheye lens and study of distortion correction algorithms [J]. Acta Optica Sinica, 2014, 34(12): 222-227.(in Chinese)

英向华, 胡占义. 一种基于球面透视投影约束的鱼眼镜头校正方法[J]. 计算机学报, 2003, 26 (12): 1702-1708.

YING X H, HU ZH Y. Fisheye lense distortion correction using spherical perspective projection constraint [J]. Chinese Journal of Computers, 2003, 26(12): 1702-1708.(in Chinese)

贾云得, 吕宏静, 徐岸, 等. 一种鱼眼镜头成像立体视觉系统的标定方法[J]. 计算机学报, 2000, 23(11): 1215-1219.

JIA Y D, LV H J, XU A, et al.. Fisheye lens camera calibration for stereo vision system[J]. Chinese Journal of computers, 2000, 23(11): 1215-1219.(in Chinese)

祝海江, 徐晓波, 周靖林. 基于球面透视投影旋转矩阵的鱼眼图像匹配[J]. 光学学报, 2013, 33(2): 122-129.

ZHU H J, XU X B, ZHOU J L. Fisheye image matching based on rotation matrix under spherical perspective projection[J].Acta Optica Sinica, 2013, 33(2): 122-129. (in Chinese)

许振辉, 张峰, 孙风梅, 等. 基于邻域传递的鱼眼图像的准稠密匹配[J]. 自动化学报, 2009, 35(9): 1159-1167.

XU ZH H, ZHANG F M, SUN F, et al.. Quasi-dense matching by neighborhood transfer for fish-eye images[J]. Acta Automatica Sinica, 2009, 35(9): 1159-1167.(in Chinese)

LI X, LI J. Rotation model based quasi-dense matching propagation for uncalibrated fisheye images[C].IEEE Conference on Computer Application and System Modeling (ICCASM), 2010, 11: 181-185. http://cn.bing.com/academic/profile?id=2068254297&encoded=0&v=paper_preview&mkt=zh-cn

姜宏志, 赵慧洁, 梁宵月, 等. 基于极线校正的快速相位立体匹配[J]. 光学精密工程, 2011, 19(10): 2520-2525.

JIANG H ZH, ZHAO H J, LIANG X Y, et al..Phase-based stereo matching using epipolar line rectification [J].Opt. Precision Eng., 2011, 19(10): 2520-2525.(in Chinese)

KANNALA J, BRANDT S S . A generic camera model and calibration method for conventional, wide-angle, and fish-eye lenses [J].IEEE Transactions on Pattern Analysis and Machine Intelligence(PAMI).2006, 28(8): 1335-1340.

李海滨, 褚光宇, 张强, 等. 基于优化的鱼眼镜头成像模型的空间点定位[J]. 光学学报, 2015, 35(7): 247-253.

LI H B, CHU G Y, ZHANG Q, et al..Space point positioning based on optimization of fisheye lens imaging model [J].Acta Optica Sinica , 2015, 35(7): 247-253.(in Chinese)

Views

413

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Binocular vision-based trackside pantograph anomaly detection under strong environmental noise

Atrous convolution and Bilateral grid network

Stereo matching based on urban satellite remote sensing image pair

Stereo matching method based on the plane constraint for lunar rover

Stereo matching method for lunar rover using the plane constraint

Related Author

ZHU Jigui

GUO Lei

YIN Shibin

GUO Yin

ZHAO Jin

DU Xingzhuo

ZHANG Jingjing

ZHI Shuai

Related Institution

ISVision（Hangzhou） Technology Co.， Ltd.

State Key Laboratory of Precision Measuring Technology and Instruments， Tianjin University

Shanghai Microsatellite Engineering Center

Innovation Academy for Microsatellites of Chinese Academy of Sciences

Engineering Research Center of Earth Exploration Intelligent Technology， Ministry of Education

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰