|本期目录/Table of Contents|

[1]章秀华,白浩玉,李毅.多目立体视觉三维重建系统的设计[J].武汉工程大学学报,2013,(03):70-74.[doi:103969/jissn16742869201303015]
　ZHANG Xiu hua,BAI Hao yu,LI Yi.Design of 3D reconstruction system based on multiview stereo vision[J].Journal of Wuhan Institute of Technology,2013,(03):70-74.[doi:103969/jissn16742869201303015]
点击复制

多目立体视觉三维重建系统的设计(/HTML)
分享到：

《武汉工程大学学报》[ISSN:1674-2869/CN:42-1779/TQ]

卷:
期数:
2013年03期
页码:
70-74
栏目:
机电与信息工程
出版日期:
2013-03-31

文章信息/Info

Title:
Design of 3D reconstruction system based on multiview stereo vision
文章编号:
16742869(2013)03007005
作者:
章秀华; 白浩玉; 李毅
武汉工程大学图像处理与智能控制研究室 湖北 武汉 430205
Author(s):
ZHANG Xiuhua; BAI Haoyu; LI Yi
Laboratory of Image Processing and Intelligent Control, Wuhan Institute of Technology, Wuhan 430205, China
关键词:
多目视觉; 张正友标定; Harris角点检测; 高斯差分检测; 泊松表面重建
Keywords:
multiview;  Zhengyou Zhang calibration;  Harris corner detection; Difference of Gaussian detection;  poisson surface reconstruction
分类号:
TP391.4
DOI:
103969/jissn16742869201303015
文献标志码:
A
摘要:
针对工业产品质量检测过程中产品三维表面的重建问题，提出一种基于多目立体视觉三维重建方法.设计了一套由八个直线分布的工业相机构成的三维重建系统方案.首先通过图像采集模块，在八个不同方向对目标物体进行图像采集.其次对采集到的图像进行预处理，其中包括图像背景抑制和目标物体分割.然后通过相机标定模块，对八个相机进行标定，获得它们的内外参数，并结合Harris角点检测及高斯差分检测算法对预处理后的图像实现特征点提取.在此结果上，再利用三角形法对提取到的特征点进行匹配和校正.最后采用泊松表面重建方法准确地获取和优化角点，并找到角点特征的匹配点，从而对物体进行三维表面的精确重建.实验结果表明，设计的系统能够重建出静止物体的局部三维表面，重建结果中的物体表面完整，结构清晰，表面上的字符重建完整，能够很好地进行识别.
Abstract:
To solve the problem of threedimensional reconstruction of the surface of the product in the process of industrial products quality inspection, a method based on multiview stereo vision was proposed. A system of threedimensional reconstruction program with eight linear industrial cameras was designed. Firstly, through the image acquisition module, the images of the target object were acquired in eight different directions. Secondly, those images were used to preprocess, including image background suppression and target object segmentation. Then the internal and external parameters of eight cameras were got by the camera calibration module, and combined with Harris corner detection and Difference of Gaussian detection algorithm，feature point extraction was achieved for the pretreatment pictures. Based on these results，the extractive the feature points were matched and checked by the triangular method. Finally, after accurately obtaining and optimizing the angle points，finding a corner feature matching points, the surface of object was reconstructed accurately by the Poisson surface reconstruction method. The experimental results show that this system can reconstruct the threedimensional surface of the static object, the surface of the object is integrity and its structure is clear in the reconstruction results. The characters on the surface are reconstructed completely, which can be well used for character recognition.

参考文献/References:

［1］洪汉玉. 现代图像图形处理与分析\[M\]. 武汉：中国地质大学出版社，2011.［2］王新字．基于计算机立体视觉的三维重建\[D\]．长沙：中南大学，2004.［3］张天序. 成像自动目标识别\[M\]. 武汉:湖北科学技术出版社，2005.［4］邱茂林，马颂德，李毅. 计算机视觉中摄像机定标综述\[J\]. 自动化学报，2000，26（1）：4355.［5］苏小红，李东，唐好选，等.计算机图形学实用教程\[M\].北京：人民邮电出版社，2010.［6］于勇，张晖，林茂松.基于双目立体视觉三位重建系统的研究与设计\[J\].计算机技术与发展，2009，19（6）：127130.［7］Zhang Z Y. A Flexible New Technique for Camera Calibration\[J\].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(11):13301334.［8］Zhang Z Y．Flexible Camera Calibration By Viewing a Plane From Unknown Orientations \[C\]// Proceedings of the 7th IEEE International Conference on Computer Vision，2027 September,1999,Kerkyra，Greece. \[S.l.\]: IEEE Computer Society，1999，1：666673.［9］Harris C，Stephens M. A Combined Comer and Edge Detector\[C\]// Proceedings of the 4th Alvey Vision Conference,University of Manchester,31 August2 September,1988 Manchester:\[s.n.\]，1988:147151.［10］张永军.基于序列图像的视觉检测理论与方法\[M\].武汉：武汉大学出版社，2008.［11］Lowe D G. Distinctive image features from scale invariant keypoints\[J\].International Journal of Computer Vision,2004,60(2):91110.［12］高健，黄心汉，彭刚，等. 基于Harris角点和高斯差分的特征点提取算法\[J\].模式识别与人工智能，2008，21（2）：171176. ［13］Kazhdan M，Bolitho M，Hoppe H. Poisson Surface Reconstruction\[C\]// Dieter Fellner, Spencer S.Proceedings of the Fourth Eurographics Symposium on Geometry Processing, June 2628, 2006, Cagliari, Sardinia, Italy. ArielaVille,Switzerland: the Eurographics Association,2006,6170.

相似文献/References:

[1]洪汉玉,张文莫,章秀华,等.双目视图运动图像去模糊方法[J].武汉工程大学学报,2015,37(04):45.[doi:10. 3969/j. issn. 1674—2869. 2015. 0４. 010]
　,SHI Yu,et al.Ｄｅｂｌｕｒｒｉｎｇ ｏｆ ｄｏｕｂｌｅ ｖｉｅｗ ｍｏｔｉｏｎ ｉｍａｇｅ[J].Journal of Wuhan Institute of Technology,2015,37(03):45.[doi:10. 3969/j. issn. 1674—2869. 2015. 0４. 010]

备注/Memo

备注/Memo:
收稿日期：20121119基金项目：国家自然科学基金面上项目(50975211，61175013)；湖北省自然科学基金创新群体项目（2012FFA046）；湖北省教育厅科学技术研究项目(Q20121507)作者简介：章秀华(1976)，女，湖北天门人，副教授，博士.研究方向：图像处理与模式识别
更新日期/Last Update: 2013-04-23