Proceedings of the 2024 2nd International Conference on Image, Algorithms and Artificial Intelligence (ICIAAI 2024)

<Previous Article In Volume
Next Article In Volume>

Research on Different Feature Matching Algorithms for Panoramic Image Stitching

Authors
Zhao Zhang1, *
1College of Physics, Xidian University, Xi’an, 710000, China
*Corresponding author. Email: 21009100551@stu.xidian.edu.cn
Corresponding Author
Zhao Zhang
Available Online 16 October 2024.
DOI
10.2991/978-94-6463-540-9_75How to use a DOI?
Keywords
Image stitching; computer vision; feature detection and matching
Abstract

Panoramic image stitching technology has penetrated into every field of modern life. As an important part of the stitching process, image feature matching directly affects the quality and speed of the stitching. In this paper, photos taken in daily life are used for experiments, and the precision and computational efficiency of three different feature matching algorithms, Scale Invariant Feature Transform (SIFT), Speeded-Up Robust Features (SURF), Oriented Fast and Rotated BRIEF (ORB), under rotation, scaling, light intensity transformation and perspective transformation, are compared to explore their applicable scenarios. The experimental results show that SIFT is most appropriate for perspective transformation, but its running speed is so slow that it is only suitable for occasions where the real-time requirement is not high. SURF has the greatest stability when dealing with scale changes and different light intensities, while it operates far quicker than SIFT. ORB exhibits the best robustness in the case of rotation and runs the fastest in all cases, so it is most suitable for applications in real-time scenarios.

Copyright
© 2024 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)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the 2024 2nd International Conference on Image, Algorithms and Artificial Intelligence (ICIAAI 2024)
Series
Advances in Computer Science Research
Publication Date
16 October 2024
ISBN
978-94-6463-540-9
ISSN
2352-538X
DOI
10.2991/978-94-6463-540-9_75How to use a DOI?
Copyright
© 2024 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

risenwbib
TY  - CONF
AU  - Zhao Zhang
PY  - 2024
DA  - 2024/10/16
TI  - Research on Different Feature Matching Algorithms for Panoramic Image Stitching
BT  - Proceedings of the 2024 2nd International Conference on Image, Algorithms and Artificial Intelligence (ICIAAI 2024)
PB  - Atlantis Press
SP  - 730
EP  - 743
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-540-9_75
DO  - 10.2991/978-94-6463-540-9_75
ID  - Zhang2024
ER  -