当前位置: X-MOL 学术Acta Numer. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A survey of structure from motion.
Acta Numerica ( IF 16.3 ) Pub Date : 2017-05-05 , DOI: 10.1017/s096249291700006x
Onur Özyeşil , Vladislav Voroninski , Ronen Basri , Amit Singer

The structure from motion (SfM) problem in computer vision is to recover the three-dimensional (3D) structure of a stationary scene from a set of projective measurements, represented as a collection of two-dimensional (2D) images, via estimation of motion of the cameras corresponding to these images. In essence, SfM involves the three main stages of (i) extracting features in images (e.g. points of interest, lines,etc.) and matching these features between images, (ii) camera motion estimation (e.g. using relative pairwise camera positions estimated from the extracted features), and (iii) recovery of the 3D structure using the estimated motion and features (e.g. by minimizing the so-calledreprojection error). This survey mainly focuses on relatively recent developments in the literature pertaining to stages (ii) and (iii). More specifically, after touching upon the early factorization-based techniques for motion and structure estimation, we provide a detailed account of some of the recent cameralocationestimation methods in the literature, followed by discussion of notable techniques for 3D structure recovery. We also cover the basics of thesimultaneous localization and mapping(SLAM) problem, which can be viewed as a specific case of the SfM problem. Further, our survey includes a review of the fundamentals of feature extraction and matching (i.e. stage (i) above), various recent methods for handling ambiguities in 3D scenes, SfM techniques involving relatively uncommon camera models and image features, and popular sources of data and SfM software.

中文翻译:

从运动对结构的调查。

计算机视觉中的运动结构 (SfM) 问题是通过运动估计从一组投影测量中恢复静止场景的三维 (3D) 结构,表示为二维 (2D) 图像的集合对应于这些图像的相机。本质上,SfM 涉及三个主要阶段:(i)提取图像中的特征(例如兴趣点、线路、等等。)并在图像之间匹配这些特征,(ii)相机运动估计(例如使用从提取的特征估计的相对成对相机位置),以及(iii)使用估计的运动和特征恢复 3D 结构(例如通过最小化所谓的重投影误差)。本次调查主要关注与阶段 (ii) 和 (iii) 有关的文献中相对较新的发展。更具体地说,在接触了早期基于分解的运动和结构估计技术之后,我们详细介绍了一些最近的相机地点文献中的估计方法,然后讨论 3D 结构恢复的显着技术。我们还介绍了同时定位和映射(SLAM) 问题,可以看作是 SfM 问题的一个特例。此外,我们的调查还包括对特征提取和匹配基础的回顾(IE上面的阶段 (i))、最近处理 3D 场景中的模糊性的各种方法、涉及相对不常见的相机模型和图像特征的 SfM 技术,以及流行的数据源和 SfM 软件。
更新日期:2017-05-05
down
wechat
bug