Open Access Paper
12 November 2024 Novel SURF image mosaic method based on wavelet transform
Quan Gan, Yongjian Wu, Yunqiang Ma
Author Affiliations +
Proceedings Volume 13395, International Conference on Optics, Electronics, and Communication Engineering (OECE 2024) ; 1339542 (2024) https://doi.org/10.1117/12.3049845
Event: International Conference on Optics, Electronics, and Communication Engineering, 2024, Wuhan, China
Abstract
To tackle the issues of significant computational requirements and extended processing times inherent in traditional image mosaic algorithms, a novel SURF-based image mosaic method that employs wavelet transform is proposed in this paper. Firstly, the Haar wavelet image preprocessing method is adopted to obtain the second order decomposition and extract the low-frequency (LF) components of the image. Then the wavelet gradient vector is utilized to extract characteristic points in the overlap region of LF images. This allows for quick acquisition of transformation parameters for characteristic points in LF images, which can guide the selection of characteristic point extraction in high-frequency (HF) images. Based on this, an improved SURF image matching algorithm is proposed utilizing properties such as single direction matching and orientation coherence. This approach effectively eliminates mismatched point pairs, thereby improving accuracy and real-time performance of characteristic point matching. Finally, two experiments are conducted to confirm the practicality and usefulness of these proposed outcomes.
(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Quan Gan, Yongjian Wu, and Yunqiang Ma "Novel SURF image mosaic method based on wavelet transform", Proc. SPIE 13395, International Conference on Optics, Electronics, and Communication Engineering (OECE 2024) , 1339542 (12 November 2024); https://doi.org/10.1117/12.3049845
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Wavelets

Image enhancement

Wavelet transforms

Image registration

Image fusion

Image processing

Cameras

Back to Top