EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

RTUAV-YOLO: A Family of Efficient and Lightweight Models for Real-Time Object Detection in UAV Aerial Imagery

Ruizhi Zhang iD, Jinghua Hou, Le Li, Ke Zhang, Li Zhao, Shuo Gao

Sensors · 25.10.2025 · 25 (21) · 6573

DOI: 10.3390/s25216573 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 25.10.2025. Verfasst von Ruizhi Zhang und 5 weiteren Autor:innen. Beteiligte Einrichtung: United Laboratories of TT&C and Communication, Jiuquan Satellite Launch Center, Lanzhou 732750, China. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Real-time object detection in Unmanned Aerial Vehicle (UAV) imagery is critical yet challenging, requiring high accuracy amidst complex scenes with multi-scale and small objects, under stringent onboard computational constraints. While existing methods struggle to balance accuracy and efficiency, we propose RTUAV-YOLO, a family of lightweight models based on YOLOv11 tailored for UAV real-time object detection. First, to mitigate the feature imbalance and progressive information degradation of small objects in current architectures multi-scale processing, we developed a Multi-Scale Feature Adaptive Modulation module (MSFAM) that enhances small-target feature extraction capabilities through adaptive weight generation mechanisms and dual-pathway heterogeneous feature aggregation. Second, to overcome the limitations in contextual information acquisition exhibited by current architectures in complex scene analysis, we propose a Progressive Dilated Separable Convolution Module (PDSCM) that achieves effective aggregation of multi-scale target contextual information through continuous receptive field expansion. Third, to preserve fine-grained spatial information of small objects during feature map downsampling operations, we engineered a Lightweight DownSampling Module (LDSM) to replace the traditional convolutional module. Finally, to rectify the insensitivity of current Intersection over Union (IoU) metrics toward small objects, we introduce the Minimum Point Distance Wise IoU (MPDWIoU) loss function, which enhances small-target localization precision through the integration of distance-aware penalty terms and adaptive weighting mechanisms. Comprehensive experiments on the VisDrone2019 dataset show that RTUAV-YOLO achieves an average improvement of 3.4% and 2.4% in mAP50 and mAP50-95, respectively, compared to the baseline model, while reducing the number of parameters by 65.3%. Its generalization capability for UAV object detection is further validated on the UAVDT and UAVVaste datasets. The proposed model is deployed on a typical airborne platform, Jetson Orin Nano, providing an effective solution for real-time object detection scenarios in actual UAVs.

Schlagwörter

Stichwörter der Autor:innen

RTUAV-YOLOUAV aerial imageryYOLOv11lightweight modelsmall objects detection

Autor:innen und Institutionen

  • United Laboratories of TT&C and Communication, Jiuquan Satellite Launch Center, Lanzhou 732750, China.
  • School of Instrumentation and Optoelectronic Engineering, Beihang University, Beijing 100191, China.

ORCID-Profile: Ruizhi Zhang

Zitieren

APA

Zhang, R., Hou, J., Li, L., Zhang, K., Zhao, L., & Gao, S. (2025). RTUAV-YOLO: A Family of Efficient and Lightweight Models for Real-Time Object Detection in UAV Aerial Imagery. Sensors, 25(21), 6573. https://doi.org/10.3390/s25216573

Vancouver

Zhang R, Hou J, Li L, Zhang K, Zhao L, Gao S. RTUAV-YOLO: A Family of Efficient and Lightweight Models for Real-Time Object Detection in UAV Aerial Imagery. Sensors. 2025;25(21):6573. doi:10.3390/s25216573

BibTeX
@article{Zhang2025,
  author = {Zhang, Ruizhi and Hou, Jinghua and Li, Le and Zhang, Ke and Zhao, Li and Gao, Shuo},
  title = {RTUAV-YOLO: A Family of Efficient and Lightweight Models for Real-Time Object Detection in UAV Aerial Imagery},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {21},
  pages = {6573},
  doi = {10.3390/s25216573}
}
Kostenlos starten →