期刊名称：International Journal of Computer and Information Technology
印刷版ISSN：2279-0764
出版年度：2017
卷号：6
期号：6
页码：358-364
出版社：International Journal of Computer and Information Technology
摘要：Structure from motion (SFM) is one of the most
popular problems that researchers interested in the field of
computer vision and computer graphics. Structure from motion
is the problem of reconstructing 3D from 2D images. According
to the data they use are a set of features matches or an optical
flow field, 3D reconstruction Approaches can be classified as
feature-based or flow based Techniques. Feature-based
reconstruction is carried out using corresponding features in
pairs of images of the same scene taken from different
viewpoints. In flow-based Matching is replaced by optical flow
the features velocity field generated by the camera motion. In
this paper, we discuss and analyze the efforts of scientists in this
field to cover all aspects of structure from motion. We discuss the
techniques; the most critical applications depend on SFM,
challenges, and the current research topics.
关键词：Structure from motion (SFM); 3D reconstruction;
Bundle Adjustment (BA); Factorization; Omnidirectional;
triangulation; rectification; correspondence search; incremental
bundle adjustment (IBA);
