A novel method for reconstructing general 3D curves from stereo images
- PDF / 2,286,002 Bytes
- 13 Pages / 595.276 x 790.866 pts Page_size
- 16 Downloads / 171 Views
ORIGINAL ARTICLE
A novel method for reconstructing general 3D curves from stereo images Yijun Zhou1,2 · Jianan Zhao1 · Chen Luo1
© Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Three-dimensional (3D) reconstruction of objects and scenes from camera images is of great interests due to its wide applications. Reconstruction based on feature point correspondence is an established approach. Existing research on curve-based reconstruction is limited to certain type of curves and constrained by case-dependent reconstruction accuracy. In view of that, this paper developed a new method to reconstruct general 3D curves from stereo images. Under proposal, a B-spline curve fitting is applied to sets of 2D edge points extracted from acquired stereo images. Derived approximating parametric curves are then used to construct conic surfaces. Further, robust iterative algorithms are developed to get intersection of corresponding conic surfaces to recover 3D curve. Due to the method design, proposed approach can reconstruct general 3D curves including both open and closed curves. The curve fitting technique and developed robust algorithms can meet accuracy requirement of many real applications. Validity of the proposed method is verified through experiments on a cylinder and teacup in laboratory and a real forging within a workshop. Keywords Curve reconstruction · Stereo vision · B-spline curve fitting · Multi-parameter iteration algorithm
1 Introduction Recovering 3D information of objects and scenes from 2D images attracts great research interests due to its wide potential applications in many different areas, e.g., in guiding industrial robots, processing medical images and navigating autonomous vehicles [1–3]. Two-dimensional images can be acquired from cameras mounted to a stereo vision system from different points of view. The essence of an image is a projection from a 3D scene onto a 2D plane, and the depth is lost during this process. The 3D point corresponding to a specific image point is constrained to be on the line of sight. If two images are * Chen Luo [email protected] Yijun Zhou [email protected] Jianan Zhao [email protected] 1
School of Mechanical Engineering, Southeast University, Nanjing 211189, China
Chengxian College, Southeast University, Nanjing 210088, China
2
available, then the position of a 3D point can be found as the intersection of the two projection rays through a process known as triangulation [4]. Point-based method, making use of feature point correspondence across multiple views, has been explored extensively by researchers [5, 6]. At its core, 3D reconstruction is the process by which a 3D object is inferred, or reconstructed, from a collection of discrete points that sample the object. Today, point-based method, or point correspondence approach, is an established method. Point clouds do not store or maintain topological information. Therefore, point-based methods are more flexible to handle complex or dynamically changing shapes. The simplicity of point-based r
Data Loading...
