Translator Disclaimer
11 September 2019 Establishing feature point correspondences between multisensor images with a robust feature matching strategy
Author Affiliations +
Abstract

Establishing cross-spectral feature point correspondences is a challenging problem due to high textural and intensity changes between multisensor images. To overcome such changes, a new feature matching strategy is proposed. The proposed strategy is based on Gaussian mixture model-universal background model (GMM-UBM). GMM-UBM is widely used as a classifier in speech-related applications. GMM-UBM is used to establish feature point correspondences between multisensor images. Experiments were performed using 17 different state-of-the-art feature points and GMM-UBM was validated on two different image datasets. The experimental results show that the proposed GMM-UBM method outperforms traditional Euclidean distance-based feature matching strategies and provides better results on multisensor images.

© 2019 SPIE and IS&T 1017-9909/2019/$28.00 © 2019 SPIE and IS&T
Sajid Saleem "Establishing feature point correspondences between multisensor images with a robust feature matching strategy," Journal of Electronic Imaging 28(5), 053004 (11 September 2019). https://doi.org/10.1117/1.JEI.28.5.053004
Received: 22 January 2019; Accepted: 12 August 2019; Published: 11 September 2019
JOURNAL ARTICLE
12 PAGES


SHARE
Advertisement
Advertisement
Back to Top