SMMNet: A Plug-and-Play Lightweight Detection Framework for UAV Aerial Imagery
Remote Sensing · 06.07.2026 · 18 (13) · 2232
DOI: 10.3390/rs18132232 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 06.07.2026. Verfasst von Minna Liu und 3 weiteren Autor:innen. Die Arbeit nennt 81 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Project of the Xiangjiang Laboratory, National Natural Science Foundation.
Abstract (Originalsprache)
Object detection in UAV aerial imagery is challenged by dense small targets, large-scale variation, complex backgrounds, and strict onboard computation limits. To address these issues, this paper proposes SMMNet (Structured-diffusion Mamba Mixture Network), a lightweight plug-and-play detection framework evaluated with YOLO family detectors. SMMNet contains three modules. The Structured Diffusion Feature Extractor (SDFE) uses anisotropic diffusion to preserve boundary-sensitive features during downsampling. The Mamba-driven Receptive-field Context Aggregator (MRCA) performs multi-directional selective state-space scanning to capture long-range context with linear complexity. The Mask-guided Bayesian Box Refinement (MBBR) applies a MAP-inspired confidence-adaptive box update using MobileSAM mask evidence and ELBO-based false-positive filtering. Using YOLOv13-S as the main detector, SMMNet achieves 32.8% mAP@0.5:0.95 and 52.6% mAP@0.5 on VisDrone2019 at 87 FPS on an NVIDIA A800 GPU, improving the YOLOv13-S baseline by 3.6 and 4.5 points, respectively. The added modules reduce throughput compared with the detector-only baseline (168 FPS), but the resulting 87 FPS remains real-time and provides a favorable accuracy–latency trade-off. Three independent-seed runs further show a mean paired gain of 3.60 ± 0.10 mAP on VisDrone2019, 2.53 ± 0.12 mAP on DroneVehicle, and 2.77 ± 0.06 mAP on SeaDronesSee for the YOLOv13-S setting. Additional experiments on DroneVehicle and SeaDronesSee, together with cross-backbone evaluations on YOLOv5/v6/v7/v8/v10/v11/v13 across different UAV benchmarks, show aligned performance trends under matched settings. Edge deployment on an NVIDIA Jetson Orin NX reaches 30 FPS under TensorRT FP16 inference at 15 W TDP, indicating the suitability of SMMNet for resource-constrained UAV perception.
Förderung
- Key Project of the Xiangjiang Laboratory
- National Natural Science Foundation
Zitieren
APA
Liu, M., Luo, Z., Hu, Y., & Liu, J. (2026). SMMNet: A Plug-and-Play Lightweight Detection Framework for UAV Aerial Imagery. Remote Sensing, 18(13), 2232. https://doi.org/10.3390/rs18132232
Vancouver
Liu M, Luo Z, Hu Y, Liu J. SMMNet: A Plug-and-Play Lightweight Detection Framework for UAV Aerial Imagery. Remote Sensing. 2026;18(13):2232. doi:10.3390/rs18132232
BibTeX
@article{Liu2026,
author = {Liu, Minna and Luo, Zhigang and Hu, Yaowen and Liu, Jialang},
title = {SMMNet: A Plug-and-Play Lightweight Detection Framework for UAV Aerial Imagery},
journal = {Remote Sensing},
year = {2026},
volume = {18},
number = {13},
pages = {2232},
doi = {10.3390/rs18132232}
}
EUVIMED