Proceedings of the 2023 2nd International Conference on Educational Innovation and Multimedia Technology (EIMT 2023)

Feature Extraction and Matching Algorithm Based on Improved SIFT

Authors
Xi Chen1, Sisi Sun1, Junying Wu1, Zihan Zhang2, *, Jiao Peng1, Yanyan Lu1, Rukun Liu1
1State Grid Hebei Information and Telecommunication Branch, Shijiazhuang, 050000, China
2North China Electric Power University, Baoding, 071003, Hebei, China
*Corresponding author. Email: zhangzihan0321@163.com
Corresponding Author
Zihan Zhang
Available Online 4 July 2023.
DOI
10.2991/978-94-6463-192-0_23How to use a DOI?
Keywords
SIFT; IMU; Nonlinear filtering; Extraction; Match
Abstract

To solve the problem that the SIFT algorithm used in augmented reality algorithm can not accurately extract matching and the matching efficiency is low, a matching method combining SIFT algorithm, fast explicit diffusion FED and IMU is proposed. Firstly, the input image of the initial matching is processed by a nonlinear filtering operation using FED. Pre-integration is performed by the IMU inertial measurement unit to calculate the pose change of the camera between two frames of images. Then, the SIFT algorithm is adopted for image matching. Finally, the corresponding relationship between the virtual object coordinates registered on the screen and the real space coordinates is determined. With the help of IMU and the nonlinear image fuzzy processing, the proposed method has strong adaptability to images and can obtain the corresponding coordinates of real space in complex environments.

Copyright
© 2023 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

Volume Title
Proceedings of the 2023 2nd International Conference on Educational Innovation and Multimedia Technology (EIMT 2023)
Series
Atlantis Highlights in Social Sciences, Education and Humanities
Publication Date
4 July 2023
ISBN
978-94-6463-192-0
ISSN
2667-128X
DOI
10.2991/978-94-6463-192-0_23How to use a DOI?
Copyright
© 2023 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

TY  - CONF
AU  - Xi Chen
AU  - Sisi Sun
AU  - Junying Wu
AU  - Zihan Zhang
AU  - Jiao Peng
AU  - Yanyan Lu
AU  - Rukun Liu
PY  - 2023
DA  - 2023/07/04
TI  - Feature Extraction and Matching Algorithm Based on Improved SIFT
BT  - Proceedings of the 2023 2nd International Conference on Educational Innovation and Multimedia Technology (EIMT 2023)
PB  - Atlantis Press
SP  - 162
EP  - 171
SN  - 2667-128X
UR  - https://doi.org/10.2991/978-94-6463-192-0_23
DO  - 10.2991/978-94-6463-192-0_23
ID  - Chen2023
ER  -