ETQ-Matcher: Efficient Quadtree-Attention-Guided Transformer for Detector-Free Aerial–Ground Image Matching
Remote Sensing · 05.04.2025 · 17 (7) · 1300
DOI: 10.3390/rs17071300 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 05.04.2025. Verfasst von Chuan Xu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Geomatics Technology and Application Key Laboratory of Qinghai Province, Hubei Province Young Science and Technology Talent Morning Hight Lift Project, Science and Technology Research Project of Education Department of Hubei Province Hubei Provincial Natural Science Foundation of China.
Abstract (Originalsprache)
UAV aerial–ground feature matching is used for remote sensing applications, such as urban mapping, disaster management, and surveillance. However, current semi-dense detectors are sparse and inadequate for comprehensively addressing problems like scale variations from inherent viewpoint differences, occlusions, illumination changes, and repeated textures. To address these issues, we propose an efficient quadtree-attention-guided transformer (ETQ-Matcher) based on efficient LoFTR, which integrates the multi-layer transformer with channel attention (MTCA) to capture global features. Specifically, to tackle various complex urban building scenarios, we propose quadtree-attention feature fusion (QAFF), which implements alternating self- and cross-attention operations to capture the context of global images and establish correlations between image pairs. We collect 12 pairs of UAV remote sensing images using drones and handheld devices, and we further utilize representative multi-source remote sensing images along with MegaDepth datasets to demonstrate their strong generalization ability. We compare ETQ-Matcher to classic algorithms, and our experimental results demonstrate its superior performance in challenging aerial–ground urban scenes and multi-source remote sensing scenarios.
Förderung
- Geomatics Technology and Application Key Laboratory of Qinghai Province
- Hubei Province Young Science and Technology Talent Morning Hight Lift Project
- Science and Technology Research Project of Education Department of Hubei Province Hubei Provincial Natural Science Foundation of China
- Doctoral Starting up Foundation of Hubei University of Technology
Zitieren
APA
Xu, C., Wang, B., Ye, Z., & Mei, L. (2025). ETQ-Matcher: Efficient Quadtree-Attention-Guided Transformer for Detector-Free Aerial–Ground Image Matching. Remote Sensing, 17(7), 1300. https://doi.org/10.3390/rs17071300
Vancouver
Xu C, Wang B, Ye Z, Mei L. ETQ-Matcher: Efficient Quadtree-Attention-Guided Transformer for Detector-Free Aerial–Ground Image Matching. Remote Sensing. 2025;17(7):1300. doi:10.3390/rs17071300
BibTeX
@article{Xu2025,
author = {Xu, Chuan and Wang, Beikang and Ye, Zhiwei and Mei, Liye},
title = {ETQ-Matcher: Efficient Quadtree-Attention-Guided Transformer for Detector-Free Aerial–Ground Image Matching},
journal = {Remote Sensing},
year = {2025},
volume = {17},
number = {7},
pages = {1300},
doi = {10.3390/rs17071300}
}
EUVIMED