A DAISY descriptor based multi-view stereo method for large-scale scenes.pdfVIP

下载本文档

14
0
约3.18万字
约 10页
2017-03-16 发布于天津
举报
版权申诉

A DAISY descriptor based multi-view stereo method for large-scale scenes.pdf

1、本文档共10页，可阅读全部内容。
2、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。
3、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。
5、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
6、成为VIP后，下载本文档将扣除1次下载权益。下载后，不支持退款、换文档。如有疑问请联系我们。
7、成为VIP后，您将拥有八大权益，权益包括：VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
8、VIP文档为合作方或网友上传，每下载1次，网站将根据用户上传文档的质量评分、类型等，对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档

A DAISY descriptor based multi-view stereo method for large-scale scenes.pdf

J. Vis. Commun. Image R. 35 (2016) 15–24 Contents lists available at ScienceDirect J. Vis. Commun. Image R. journal homepage: /locate/jvci A DAISY descriptor based multi-view stereo method for large-scale scenes q Bindang Xue ?, Lei Cao, Donghai Han, Xiangzhi Bai, Fugen Zhou, Zhiguo Jiang Image Processing Center, Beihang University, Beijing 100191, China article info Article history: Received 27 March 2015 Accepted 15 November 2015 Available online 2 December 2015 Keywords: Computer vision 3D reconstruction Multi-view stereo Large-scale DAISY descriptor Photometric discrepancy function Feature matching Feature point growing abstract Normalized cross-correlation (NCC) has been widely used as the matching cost function in multi-view stereo methods. However, NCC is vulnerable in the occlusion area and edge region of large-scale scenes because of color distortion and illumination changes. To alleviate the above problems, we present an improved patch based multi-view stereo method by introducing a photometric discrepancy function based on DAISY descriptor. In the patch extraction stage, a new corresponding point matching method based on the DAISY descriptor is proposed and the epipolar constraint is used to ?lter mismatched points. In the patch optimization stage, a photometric discrepancy function based on DAISY descriptor is proposed to measure the photo-consistency among reconstructed patches to identify reliable patches. Finally, dense patches are obtained by expanding sparse patches with global visibility information and patch optimization. Experimental results show that the proposed algorithm obtains better reconstruction results in occlusion and edge regions of large-scale scenes. ó 2015 Elsevier Inc. All rights reserved. 1. Introduction Multi-view stereo (MVS) reconstruction is to obtain 3D scene models from a collection of images. The existed MVS algorithms can be roughly classi?ed into four categories [1]: the voxel based methods [4–9], the surface evolution ba