A survey of structure from motion
A survey of structure from motion
复制标题
DOI：
10.1017/s096249291700006x
复制
发表时间：
2017-01-01
期刊：
影响因子：
14.2
通讯作者：
Singer, Amit
中科院分区：
文献类型：
--
作者：
Ozyesil, Onur;Voroninski, Vladislav;Singer, Amit
计算机视觉中的运动结构 (SfM) 问题是通过估计与这些图像相对应的相机的运动，从一组表示为二维 (2D) 图像集合的投影测量中恢复静止场景的三维 (3D) 结构。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、线条等）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）相关的文献的近期发展。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，我们详细介绍了文献中的一些最新相机位置估计方法，然后讨论了 3D 结构恢复的著名技术。我们还介绍了同步定位与建图 (SLAM) 问题的基础知识，该问题可以被视为 SfM 问题的一个具体案例。此外，我们的调查还包括对特征提取和匹配基础知识（即上述阶段 (i)）、处理 3D 场景中模糊性的各种最新方法、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 软件的回顾。
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-called reprojection 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 camera location estimation methods in the literature, followed by discussion of notable techniques for 3D structure recovery. We also cover the basics of the simultaneous 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.