Long-range 3D reconstruction based on wide-baseline stereo vision

doi:10.3785/j.issn.1008-973X.2010.06.004

2010, Vol. 44

Issue (6): 1073-1078 DOI: 10.3785/j.issn.1008-973X.2010.06.004

Long-range 3D reconstruction based on wide-baseline stereo vision

WANG Wei-qiang, XU Jin, DU Xin, LIU Ji-lin

Institute of Information and Communication Engineering, Zhejiang University, Zhejiang Provincial Key Laboratory of Information Network Technology, Hangzhou 310027,China

Download:

PDF(0KB) HTML
Export: BibTeX | EndNote (RIS)

Abstract

A self-calibration based wide-baseline stereo vision technique was proposed for remote scene’s 3D reconstruction in vision based navigation of lunar rover. Correspondences between stereo rig were obtained by extracting and matching of scaleinvariant feature transform (SIFT) features. Then with the epipolar geometrical description of rectifying collineation, the leastsquares solution to Sampson error was achieved by Levenberg-Marquardt(LM) algorithm, which obtained the camera parameter and the rectified stereo rig. Following, the widebaseline dense matching was completed using seeds’ disparity expansion algorithm. Finally, target’s 3D reconstruction was achieved on the calculated disparity. This technique is demonstrated to have good performance on a number of remote natural mountain scenes and solve the problems of field calibration, change in illumination, perspective deformations and occlusions in widebaseline stereo vision.

Published: 16 July 2010

CLC:

TP 391.41

	Service
	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors

Cite this article:

WANG Wei-Jiang, XU Jin, DU Xin, LIU Ji-Lin. Long-range 3D reconstruction based on wide-baseline stereo vision. J4, 2010, 44(6): 1073-1078.

URL:

http://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2010.06.004 OR http://www.zjujournals.com/eng/Y2010/V44/I6/1073

基于宽基线立体视觉的远距离三维重建

针对月球车视觉导航中远距离场景的三维重建问题,提出一种基于相机自标定的宽基线立体视觉方法.该方法首先提取立体图对的尺寸不变性（SIFT）特征并进行匹配,得到特征点对应关系；再使用外极线几何约束描述立体图像校正的直射变换,对其Sampson误差使用LevenbergMarquardt(LM)算法求得最小二乘最优解,完成相机参数估计和图像校正；对校正后的图像使用种子像素视差扩张算法进行宽基线立体匹配,根据匹配得到的视差完成目标场景三维重建.实验表明:该方法解决了月球车相机的现场标定难题,并能够解决宽基线立体视觉面临的光照差异、透视畸变、遮挡等问题,对远距离山脉等自然场景的三维重建效果良好,重建精度较高.

［1］ PRITCHETT P, ZISSERMAN A. Wide baseline stereo matching ［C］∥ Proceedings of the 6th International Conference on Computer Vision. Bombay, India: IEEE Computer Society, 1998: 754759.

［2］ TUYTELAARS T, VAN GOOL L. Wide baseline stereo matching based on local, affinely invariant regions ［C］∥ Proceedings of the 11th British Machine Vision Conference. Bristol, UK: ILES Central, 2000: 412425.

［3］ TELL D, CADSSON S. Wide baseline point matching using invariants computed from intensity profiles ［C］∥ Proceedings of the 6th European Conference on Computer Vision. Dublin, Ireland: Springer, 2000.

［4］ LOWE D G. Distinctive image features from scaleinvariant key points ［J］. International Journal of Computer Vision, 2004: 60（2）：91110.

［5］ IRSARA L, FUSIELLO A. Quasieuclidean uncalibrated epipolar rectification ［C］∥ International Conference on Pattern Recognition (ICPR). Tampa, USA: \
[s.n.\], 2008: 14.

［6］ HEYDEN A, POLLEFEYS M. Multiple view geometry ［M］. NJ, USA: Prentice Hall, 2005.

［7］沈晔湖,刘济林.利用立体图对的三维人脸模型重建算法［J］.计算机辅助设计与图形学学报,2006,12(18): 19041909.

SHEN Yehu, LIU Jilin. From stereo pair to 3D face model ［J］. Journal of ComputerAided Design & Computer Graphics, 2006, 12(18): 19041909.

［8］ NovAtel产品类型大全［EB/OL］.［20080823］.http:∥www.novatel.com.cn/products/NovAtel%20product.pdf.

［9］ Google Earth 4.3 ［CP/OL］. ［20080820］. http:∥earth.google.com/downloadearth.html.

[1]	YANH Yu-ting, SHI Yu-hui, XIA Shun-ren. Discussion mechanism based brain storm optimization algorithm[J]. J4, 2013, 47(10): 1705-1711.

[2]	ZHU Xiao-en, HAO Xin, XIA Shun-ren. Feature selection algorithm based on Levy flight[J]. J4, 2013, 47(4): 638-643.

[3]	SON Chang-il , ZHEN Shuai, XIA Shun-ren. Attractor range based affine registration of multi-modal brain magnetic resonance images[J]. J4, 2012, 46(9): 1722-1728.

[4]	XIE Di, TONG Ruo-feng, TANG Min, FENG Yang. Distinguishable method for video fire detection[J]. J4, 2012, 46(4): 698-704.

[5]	DAI Yuan-ming, WEI Wei, LIN Yi-ning. An improved Mean-shift tracking algorithm based on color and texture feature[J]. J4, 2012, 46(2): 212-217.

[6]	Qi lei, JIN Wen-guang, GENG Wei-dong. Human motion capture using wireless inertial sensors[J]. J4, 2012, 46(2): 280-285.

[7]	LIU Chen-bin, PAN Ying, ZHANG Hai-shi, HUANG Feng-ping, XIA Shun-ren. Detecting MGMT expression status of glioma with magnetic resonance image[J]. J4, 2012, 46(1): 170-176.

[8]	QIAN Cheng, ZHANG San-yuan. Weighted incremental subspace learning algorithm suitable for object tracking[J]. J4, 2011, 45(12): 2240-2246.

[9]	CAO Ying, HAO Xin, ZHU Xiao-en, XIA Shun-ren. Mammographic mass segmentation algorithm based on automatic random walks[J]. J4, 2011, 45(10): 1753-1760.

[10]	LV Gu-lai,LI Jian-ping,LI Qiang,YU Li-xing,ZHU Song-ming,LOU Jian-zhong. Method for rootstock position recognition based on machine vision[J]. J4, 2011, 45(10): 1766-1770.

[11]	LAI Xiao-bo , ZHU Shi-qiang. Mutual information based non-parametric transform stereo matching algorithm[J]. J4, 2011, 45(9): 1636-1642.

[12]	LIU Jian-ming, LU Dong-ming, GE Rong. Global optimization based image inpainting and its implementation on GPU[J]. J4, 2011, 45(2): 247-252.

[13]	WANG Jin-de, SHOU Li-dan, LI Xiao-yan, CHEN Gang. Bundling features with multiple segmentations for object-based image retrieval[J]. J4, 2011, 45(2): 259-266.

[14]	LIANG Wen-feng, XIANG Zhi-yu. Algorithm of robust object tracking using PTZ camera[J]. J4, 2011, 45(1): 59-63.

[15]	ZHAN Jiang-tao, LIU Qiang, CHAI Chun-lei. Facial feature tracking using three-dimensional model and Gabor wavelet[J]. J4, 2011, 45(1): 30-36.

Viewed

Full text

Abstract

Cited

Shared

Discussed