Open AccessAnalysis of feasibility and advantages of multi‐source image registration using regional features
Author(s) -
Zeng Liang,
Lu Danwei,
Zhu Qingtao,
Xing Cheng,
Yin Junjun,
Yang Jian
Publication year - 2021
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
eISSN - 1350-911X
pISSN - 0013-5194
DOI - 10.1049/ell2.12119
Subject(s) - robustness (evolution) , computer science , artificial intelligence , image registration , computer vision , feature extraction , multi source , feature (linguistics) , pixel , image (mathematics) , pattern recognition (psychology) , remote sensing , geography , mathematics , statistics , biochemistry , chemistry , linguistics , philosophy , gene
Automatic registration of multi‐source remote sensing data is a challenging task due to the high non‐linearity of radiometric differences among various data. Feature extraction is a key enabling technique in registration algorithm design. In this letter, we prove the feasibility of using extracted regional features for multi‐source image registration. In particular, regional features can be extracted through pixel‐level image classification, and existing off‐the‐shelf algorithms can be directly adopted. Experiment results demonstrate the robustness of the regional‐feature‐based registration method.