| 三维重建算法研究综述 |
| |
| 引用本文： | 张彦雯,胡凯,王鹏盛.三维重建算法研究综述[J].南京气象学院学报,2020,12(5):591-602. |
| |
| 作者姓名： | 张彦雯 胡凯 王鹏盛 |
| |
| 作者单位： | 南京信息工程大学 自动化学院, 南京, 210044;南京信息工程大学 江苏省大气环境与装备技术协同创新中心, 南京, 210044,南京信息工程大学 自动化学院, 南京, 210044;南京信息工程大学 江苏省大气环境与装备技术协同创新中心, 南京, 210044,南京信息工程大学 自动化学院, 南京, 210044;南京信息工程大学 江苏省大气环境与装备技术协同创新中心, 南京, 210044 |
| |
| 基金项目： | 国家自然科学基金（61773219，61701244）；国家重点研发计划重点专项课题（2018YFC1405703） |
| |
| 摘 要： | 三维重建技术能够应用在医学中的三维CT图像、机器人中的路径规划及考古工作中的遗迹的展示等诸多领域中.三维重建效果的完整性、精确性与稀疏点云重建（Structure From Motion，SFM）、稠密点云重建（Multi-View System，MVS）有着直接关系，本文对这两个方法展开了具体的介绍.稀疏点云重建中主要介绍了特征点检测与匹配以及SFM重构方法，本文对近几年关于特征点检测与匹配的研究进行了总结，将SFM重构方法分为全局式、增量式、混合式，并进行了详细介绍.稠密点云重建中主要介绍了深度图估计，就传统的几何计算法、深度学习与几何计算相结合的方法、基于深度学习的方法进行了总结，同时介绍了三维重建的评价指标.最后对基于图像的三维重建进行了总结，并列举出了在未来可能面对的问题及发展趋势.
|
| 关 键 词： | 三维重建 图像 稀疏点云重建 稠密点云重建 评价指标 |
| 收稿时间： | 2019/11/20 0:00:00 |
Review of 3D reconstruction algorithms |
| |
| ZHANG Yanwen,HU Kai and WANG Pengsheng.Review of 3D reconstruction algorithms[J].Journal of Nanjing Institute of Meteorology,2020,12(5):591-602. |
| |
| Authors: | ZHANG Yanwen HU Kai and WANG Pengsheng |
| |
| Institution: | School of Automation, Nanjing University of Information Science&Technology, Nanjing 210044;Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET), Nanjing University of Information Science&Technology, Nanjing 210044,School of Automation, Nanjing University of Information Science&Technology, Nanjing 210044;Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET), Nanjing University of Information Science&Technology, Nanjing 210044 and School of Automation, Nanjing University of Information Science&Technology, Nanjing 210044;Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET), Nanjing University of Information Science&Technology, Nanjing 210044 |
| |
| Abstract: | Three-dimensional (3D) reconstruction technology can be applied in many fields such as 3D CT images in medicine,path planning in robots,and display of relics in archaeological work.The completeness and accuracy of 3D reconstruction are directly related to steps of Structure from Motion (SfM) and Multi-View System (MVS).In this paper,we introduce these two steps in detail.In the reconstruction of sparse point cloud,feature point detection and matching and SfM reconstruction methods are introduced and elaborated.We summarize the researches on feature point detection and matching in recent years,and classify the reconstruction methods of SFM into global and incremental ones,and introduce them in detail.In the dense point cloud reconstruction,the depth map estimation is introduced and elaborated,in which the traditional geometric calculation method,hybrid geometry-and deep learning-based approach,and deep learning based method are summarized.Meanwhile,the evaluation index of 3D reconstruction is introduced.Finally,the image based 3D reconstruction is summarized,and the problems facing the 3D reconstruction and possible future research directions are listed. |
| |
| Keywords: | 3D reconstruction images structure from motion multi-view system evaluation index |
|
| 点击此处可从《南京气象学院学报》浏览原始摘要信息 |
| 点击此处可从《南京气象学院学报》下载免费的PDF全文 |
|
