Structure-Based Feature Representation for Robust Multi-Modal Image Matching
Remote Sensing · 14.08.2026 · 18 (16) · 2744
DOI: 10.3390/rs18162744 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 14.08.2026. Verfasst von Yameng Hong und 2 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Key Research and Development Program in Shaanxi Province of China, Natural Science Basic Research Plan in Shaanxi Province of China.
Abstract (Originalsprache)
Multi-modal image matching (MIM) remains a challenging problem due to nonlinear radiometric variations and geometric distortions across heterogeneous sensors. This paper proposes a robust feature-based matching framework that reduces reliance on intensity information while enhancing structural representation. The filter with local normalization is applied to transform the input images into a common intermediate domain. A block-based strategy is then employed to enforce a uniform spatial distribution of keypoints using the ORB (Oriented FAST and Rotated BRIEF) detector. To further suppress intensity variations and improve discriminability, a novel Max-Index-based HOG (MIHOG) is developed. This descriptor integrates multi-scale feature representations and encodes dominant structural information through discrete max-index mapping. Finally, correspondences are established using a brute-force matching strategy. Extensive experiments are conducted on two multi-modal datasets covering eight diverse scenarios. The proposed method achieves an average NCM of 224.52, RMSE of 3.4788, and SR of 92%. MIHOG obtains the highest NCM on 4/8 test scenarios and improves the average NCM by 18.3% compared with the second-best method. Meanwhile, it maintains competitive computational efficiency, with an average running time of 10.20s. These results demonstrate that MIHOG can provide dense and reliable correspondences under complex cross-modal radiometric and geometric variations.
Förderung
- National Natural Science Foundation of China
- Key Research and Development Program in Shaanxi Province of China
- Natural Science Basic Research Plan in Shaanxi Province of China
Zitieren
APA
Hong, Y., Leng, C., & Pei, Z. (2026). Structure-Based Feature Representation for Robust Multi-Modal Image Matching. Remote Sensing, 18(16), 2744. https://doi.org/10.3390/rs18162744
Vancouver
Hong Y, Leng C, Pei Z. Structure-Based Feature Representation for Robust Multi-Modal Image Matching. Remote Sensing. 2026;18(16):2744. doi:10.3390/rs18162744
BibTeX
@article{Hong2026,
author = {Hong, Yameng and Leng, Chengcai and Pei, Zhao},
title = {Structure-Based Feature Representation for Robust Multi-Modal Image Matching},
journal = {Remote Sensing},
year = {2026},
volume = {18},
number = {16},
pages = {2744},
doi = {10.3390/rs18162744}
}
EUVIMED