Disparity estimation and image restoration for reflection stereo vision

JIANG Wei; WEI Shi-heng

doi:10.3788/OPE.20111907.1701

您当前的位置：

首页 >

文章列表页 >

Disparity estimation and image restoration for reflection stereo vision

Article | 更新时间：2020-08-12

- Disparity estimation and image restoration for reflection stereo vision
- Optics and Precision Engineering Vol. 19, Issue 7, Pages: 1701-1707(2011)
- 作者机构：
  
  浙江大学工业控制技术国家重点实验室,浙江杭州,310027
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20111907.1701
  CLC： TP242.62;TP391.4
- Received：29 October 2010，
  
  Revised：18 January 2011，
  
  Published Online：25 July 2011，
  
  Published：25 July 2011
- 稿件说明：
移动端阅览
姜伟, 魏世衡. 反射型立体视觉系统的视差估计和图像复原[J]. 光学精密工程, 2011,19(7): 1701-1707

JIANG Wei, WEI Shi-heng. Disparity estimation and image restoration for reflection stereo vision[J]. Editorial Office of Optics and Precision Engineering, 2011,19(7): 1701-1707
姜伟, 魏世衡. 反射型立体视觉系统的视差估计和图像复原[J]. 光学精密工程, 2011,19(7): 1701-1707 DOI： 10.3788/OPE.20111907.1701.

JIANG Wei, WEI Shi-heng. Disparity estimation and image restoration for reflection stereo vision[J]. Editorial Office of Optics and Precision Engineering, 2011,19(7): 1701-1707 DOI： 10.3788/OPE.20111907.1701.

摘要

根据反射型立体视觉系统的成像特点

提出了一种基于倒谱分析的反射型立体视觉系统视差估计方法

并利用逆滤波原理对反射型立体视觉系统的重影图像进行复原

获得目标场景的清晰图像。反射型立体视觉系统是一种新型单目测距方式

可以实时获取目标场景的重影图像。首先

将图像分割为矩形观测区域小块;然后

对各观测区域块进行倒谱分析

并通过检测倒谱域峰值位置估计图像的重影位移量(即视差)

计算目标点的三维空间距离;最后

利用估计的视差构造逆滤波器

对重影图像进行逆滤波复原

获取场景清晰图像。通过真实场景实验验证了本文方法的正确性和有效性

结果表明

本文方法的视差估计结果比自相关法提高了15%~20%

实现了稳定视差估计

复原了场景的清晰图像。

Abstract

On the basis of imaging characteristics of a reflection stereo vision

an approach for disparity estimation and image restoration of reflection stereo vision was proposed and the double image of the vision system was restored.The reflection stereo vision is a monocular system

and can capture the double image in real time. In experiment

the image was segmented into the rectangle observing blocks firstly

then

the cepstrum analysis was used to estimate the displacement amount (disparity) of each pixel in the double image by detecting the two symmetrical peaks from the cepstrum domain and to calculate the 3D space distance of a target point. Finally

the disparity was used to combine an inverse filter to restore the double image and to obtain a good scene image. Experimental results show that the method is effective for disparity estimation and image restoration

and the accuracy of the disparity estimation has improved by 15%-20%.

关键词

Keywords

references

JAMES P M, ALAN C B, LAWRENCE K C. Active, foveated, uncalibrated stereovision[J]. International Journal of Computer Vision, 2009,85(2):192-207.[2] MONACO J P, BOVIK A C, CORMACK L K. Nonlinearitiesin stereoscopic phase-differencing[J]. IEEE Transactions on Image Processing, 2008,17(9):1672-1684.[3] JAVIER D, EDUARDO R, SILVIO P S, et al. A phase-based stereo vision system-on-a-chip[J]. BioSystems, 2007, 87:314-321.[4] GLUCKMAN J M, NAYAR S K. Catadioptric stereo using planar mirrors [J]. International Journal of Computer Vision, 2001,44(1):65-79.[5] JIANG W, SHIMIZU M, OKUTOMI M.Single-camera multi-baseline stereo using fish-eye lens and mirrors. Proceedings of the 9th Asian Conference on Computer Vision. Xian P. R. China:IEEE,2009:347-358.[6] GAO C, AHUJA N. A refractive camera for acquiring stereo and super-resolution images. Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, New York: IEEE, 2006:2316-2323.[7] SEITZ S, CURLESS B, DIEBEL J, et al. A comparison and evaluation of multi-view stereo reconstruction algorithms. Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2006:519-528.[8] PACHIDIS T P, LYGOURAS J N. Pseudo-stereo vision system: a detailed study[J]. Journal of Intelligent and Robotic Systems, 2005, 42(2):135-167. [9] SHIMIZU M, OKUTOMI M. Reflection stereo-novel monocular stereo using a transparent plate. Canadian Conference on Computer and Robot Vision, CRV, 2006:14-14.[10] SHIMIZU M, OKUTOMI M. Calibration and rectification for relection stereo. Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition. Anchorage, AK:IEEE,2008:1-8.[11] BOGERT B P, HEALY M J R, TUKEY J W. The quefrency alanysis of time series for echoes:cepstrum, pseudo- autocovariance,cross-cepstrum,and saphe cracking[J]. Time Series Analysis, 1963(15):209-243. [12] GIANNIS C, NIKOLAOS G, ARISTIDIS L,et al. Variational bayesian image restoration based on a product of t-distributions image prior[J]. IEEE Transactions on Image Processing,2008, 17(10):1795-1805.[13] BUADES A, COLL B, MOREL J M. A review of image denoising algorithms, with a new one[J]. Multiscale Modeling and Simulation, 2005,4(2):490-530.

Views

431

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Multi-regularization image restoration method for X-ray images of integrated circuit

Restoration of blurred infrared image by adaptive double edge method

End-to-end image dehazing under separated features and collaborative network

Magneto-optical imaging restoration and recognition technology for damaged characters

Combined exposure computational imaging system and image restoration method

Related Author

MA Ge

LIN Sen

LI Zhifu

ZHAO Zhijia

ZOU Tao

Xueying CAO

Lin WANG

Qinyan TAN

Related Institution

School of Mechanical and Electrical Engineering， Guangzhou University

Infrared Detection Technology Research & Development Center of CASC

Shanghai Academy of Spaceflight Technology

School of Physics and Optoelectronic Engineering， Xidian University

School of Electronic and Information Engineering， Lanzhou Jiaotong University

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