首页 | 本学科首页   官方微博 | 高级检索  
     

双目立体重建中的去噪及补洞方法
引用本文:韩坤芳,沈会良,程岳.双目立体重建中的去噪及补洞方法[J].中国图象图形学报,2011,16(6):1057-1063.
作者姓名:韩坤芳  沈会良  程岳
作者单位:浙江大学,浙江大学,浙江大学
基金项目:国家重点基础研究发展计划(973)项目(2009CB320801);国家自然科学基金项目(60778050)。
摘    要:通过双目立体视觉重建得到的真实物体3维模型一般具有较大的噪声,并可能存在孔洞。针对这一问题,提出在规则3维点集下,通过非局部(NL)方法来滤除3维模型的噪声并填补孔洞。为提高算法效率,对含孔区域和非孔区域的点集,分别做基本NL滤波和基于主成分分析的NL滤波,然后进一步通过NL方法对孔洞做填补。实验结果表明,对于多种真实物体,所提出的方法均能有效地重建3维模型,且与其他方法相比具有更高的精度。

关 键 词:双目立体    非局部    去噪    补洞    主成分分析
收稿时间:4/26/2010 1:15:05 PM
修稿时间:3/24/2011 9:29:36 AM

Denoising and hole-filling for binocular stereo reconstruction
Han Kunfang,Shen Huiliang and Cheng Yue.Denoising and hole-filling for binocular stereo reconstruction[J].Journal of Image and Graphics,2011,16(6):1057-1063.
Authors:Han Kunfang  Shen Huiliang and Cheng Yue
Affiliation:Han Kunfang,Shen Huiliang,Cheng Yue(Department of Information and Electronic Engineering,Zhejiang University,Hangzhou 310027 China)
Abstract:The 3D models reconstructed from binocular stereo always have noticeable noise, and even contain holes. To deal with this issue, this paper presents a non-local (NL) method to denoise and hole-fill the original model on a regular vertex set. To improve computational efficiency, the proposed method uses a basic NL method and principal component analysis (PCA) based NL method to remove model noise in hole and non-hole regions, respectively. The filled holes are then processed by NL denoising to improve the consistency with the surrounding surfaces. The experimental results show that, when evaluated on different real objects with various sizes, the proposed method can reconstruct 3D models effectively and performs much better than previous methods.
Keywords:binocular stereo  non-local  denoising  hole filling  principal component analysis
本文献已被 CNKI 等数据库收录!
点击此处可从《中国图象图形学报》浏览原始摘要信息
点击此处可从《中国图象图形学报》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号