###
DOI:
工程科学与技术:2015,47(6):91-96
←前一篇   |   后一篇→
本文二维码信息
码上扫一扫!
一种新的大场景三维重建算法
(四川大学计算机学院)
A Novel 3D Reconstruction Algorithm for Large-Scale Scenes
摘要
图/表
参考文献
相似文献
本文已被:浏览 1429次   下载 26
投稿时间:2015-02-06    修订日期:2015-04-10
中文摘要: 大场景图像集具规模巨大、尺度多变、结构不整等特点。本文针对此类图像集,提出一种新的鲁棒稠密三维重建方法。该方法在选取图像的邻居图集时考虑了尺度鲁棒性,随后基于DAISY特征匹配和PatchMatch信息传播计算深度图,然后利用深度一致性优化、融合深度图,最后利用重建三维点精度去除冗余点。深度图计算时相互独立,故本方法易在图像级并行,适合大场景三维重建。实验结果表明,该方法重建结果具有较高的精度和完整性。
中文关键词: 三维重建  选图  深度图  PatchMatch  多视图立体
Abstract: To dealing with the large-scale image datasets with massive amount of unstructured photos, which were different in scale, view point, etc., a robust dense 3D reconstruction method was proposed. Firstly, large scale variants were considered during the neighboring image selection stage, which was proofed to be more robust for large-scale image datasets. Then, a robust depth map computing method was proposed based on the combination of the DAISY descriptor and PatchMatch information propagation scheme. Regularization was imposed by enforcing the depth consistency among different depth maps during the merging stage. Finally, redundancy 3D points were removed by using the accuracy of each points. The method could be parallelized at the image level naturally, which makes it extremely suitable for large-scale 3D reconstruction. Experimental results confirmed the performance of the proposed method, which has both high accuracy and completeness.
文章编号:201500127     中图分类号:    文献标志码:
基金项目:国家自然科学基金(61173182):基于动力系统的L1范数矩阵低秩分解及其应用研究;国家自然科学基金(613111154):基于光学孔径合成的立体超分辨率重建关键技术及其应用;四川省科技厅资助项目(2014HH0025):超分辨3D 重建技术与应用合作研究;四川省科技厅资助项目(2014HH0048):影像超分辨3D 化关键技术及相关战略性新兴产品培育国际合作研究;
Author NameAffiliationE-mail
liuyiguang  liuyg@scu.edu.cn 
yishoulin   
吴鹏飞   
崔鹏   
作者简介:
引用文本:
刘怡光,易守林,吴鹏飞,崔鹏.一种新的大场景三维重建算法[J].工程科学与技术,2015,47(6):91-96.
liuyiguang,yishoulin,吴鹏飞,崔鹏.A Novel 3D Reconstruction Algorithm for Large-Scale Scenes[J].Advanced Engineering Sciences,2015,47(6):91-96.