Parallel SURF Algorithm for 3D Reconstruction

DOI

10.2991/smont-19.2019.34How to use a DOI?

Keywords

SURF; parallel algorithm; feature extraction; OpenMP; CUDA; 3D reconstruction

Abstract

In this paper, we proposed a parallel SURF algorithm for 3d reconstruction to solve the problem of rapid feature extraction and matching in multi-view 3d reconstruction. SURF algorithm is an effective algorithm for feature extraction. Compared with the classic SIFT algorithm for feature extraction, it has improved somewhat in speed. However, SURF algorithm is still a time-consuming process. In this paper, we improved SURF algorithm. Aiming at the time-consuming problem of feature detection and description, we proposed a parallel algorithm based on multi-core OpenMP and CUDA architecture, and apply it to three-dimensional reconstruction. The experimental results show that the proposed algorithm achieves a certain acceleration ratio under the condition of 100% accuracy compared with the original algorithm.

Copyright

© 2019, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Suping Wu
AU  - Bing Feng
PY  - 2019/04
DA  - 2019/04
TI  - Parallel SURF Algorithm for 3D Reconstruction
BT  - Proceedings of the 2019 International Conference on Modeling, Simulation, Optimization and Numerical Techniques (SMONT 2019)
PB  - Atlantis Press
SP  - 153
EP  - 157
SN  - 1951-6851
UR  - https://doi.org/10.2991/smont-19.2019.34
DO  - 10.2991/smont-19.2019.34
ID  - Wu2019/04
ER  -