AMSRDet: An Adaptive Multi-Scale UAV Infrared-Visible Remote Sensing Vehicle Detection Network
Sensors · 26.01.2026 · 26 (3) · 817
DOI: 10.3390/s26030817 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 26.01.2026. Verfasst von Zekai Yan und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Art and Science, Columbia University, New York, NY 10027, USA. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 71 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Unmanned Aerial Vehicle (UAV) platforms enable flexible and cost-effective vehicle detection for intelligent transportation systems, yet small-scale vehicles in complex aerial scenes pose substantial challenges from extreme scale variations, environmental interference, and single-sensor limitations. We present AMSRDet (Adaptive Multi-Scale Remote Sensing Detector), an adaptive multi-scale detection network fusing infrared (IR) and visible (RGB) modalities for robust UAV-based vehicle detection. Our framework comprises four novel components: (1) a MobileMamba-based dual-stream encoder extracting complementary features via Selective State-Space 2D (SS2D) blocks with linear complexity O(HWC), achieving 2.1× efficiency improvement over standard Transformers; (2) a Cross-Modal Global Fusion (CMGF) module capturing global dependencies through spatial-channel attention while suppressing modality-specific noise via adaptive gating; (3) a Scale-Coordinate Attention Fusion (SCAF) module integrating multi-scale features via coordinate attention and learned scale-aware weighting, improving small object detection by 2.5 percentage points; and (4) a Separable Dynamic Decoder generating scale-adaptive predictions through content-aware dynamic convolution, reducing computational cost by 48.9% compared to standard DETR decoders. On the DroneVehicle dataset, AMSRDet achieves 45.8% mAP@0.5:0.95 (81.2% mAP@0.5) at 68.3 Frames Per Second (FPS) with 28.6 million (M) parameters and 47.2 Giga Floating Point Operations (GFLOPs), outperforming twenty state-of-the-art detectors including YOLOv12 (+0.7% mAP), DEIM (+0.8% mAP), and Mamba-YOLO (+1.5% mAP). Cross-dataset evaluation on Camera-vehicle yields 52.3% mAP without fine-tuning, demonstrating strong generalization across viewpoints and scenarios.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Art and Science, Columbia University, New York, NY 10027, USA.
- School of Cyberspace Security (School of Cryptology), Hainan University, Haikou 570228, China.
ORCID-Profile: Yuheng Li
Zitieren
APA
Yan, Z., & Li, Y. (2026). AMSRDet: An Adaptive Multi-Scale UAV Infrared-Visible Remote Sensing Vehicle Detection Network. Sensors, 26(3), 817. https://doi.org/10.3390/s26030817
Vancouver
Yan Z, Li Y. AMSRDet: An Adaptive Multi-Scale UAV Infrared-Visible Remote Sensing Vehicle Detection Network. Sensors. 2026;26(3):817. doi:10.3390/s26030817
BibTeX
@article{Yan2026,
author = {Yan, Zekai and Li, Yuheng},
title = {AMSRDet: An Adaptive Multi-Scale UAV Infrared-Visible Remote Sensing Vehicle Detection Network},
journal = {Sensors},
year = {2026},
volume = {26},
number = {3},
pages = {817},
doi = {10.3390/s26030817}
}
EUVIMED