Oct 2026· Discover Computing· Vol 29· 0 citations· 40 references
TL;DR
EHL-YOLO, a task-oriented structural optimization of YOLOv10l that coordinates shallow feature preservation, hierarchical cross-scale interaction, and localization-quality-aware prediction, demonstrates an improved accuracy–complexity balance for visible-light UAV detection under the reported protocol, while the HIT-UAV results reveal a remaining limitation under infrared domain shift.
Abstract
Small-object detection in unmanned aerial vehicle (UAV) imagery remains challenging because targets are small, densely distributed, and easily confused with complex backgrounds. This study presents EHL-YOLO, a task-oriented structural optimization of YOLOv10l that coordinates shallow feature preservation, hierarchical cross-scale interaction, and localization-quality-aware prediction. The backbone replaces selected C2f-based units with Efficient Adaptive Multi-Scale Feature Extraction (EAMFE), the neck reconstructs the P3–P5 fusion pathway through a Hierarchical Adaptive Feature Interaction (HAFI) design, and the detection head incorporates Location Quality Estimation and Dual-Branch Collaborative detection (LQEDC). On VisDrone-DET2019, EHL-YOLO increases Precision from 0.493 to 0.507, Recall from 0.374 to 0.402, mAP50 from 0.363 to 0.392, and mAP50–95 from 0.217 to 0.228, while reducing parameters from 24.317 M to 22.106 M and GFLOPs from 120.0 to 112.9. The expanded comparison includes RT-DETR-L and UAV-oriented detectors. Under its implementation-specific training and preprocessing configuration, RT-DETR-L obtains 0.3200 mAP50 and 0.1914 mAP50–95, whereas EHL-YOLO obtains 0.3920 and 0.2280, respectively. A Top-m sensitivity study shows that m = 4 provides the highest Recall, mAP50, and mAP50–95 among m∈{2,4,8}. Cross-dataset evaluation on the HIT-UAV infrared benchmark increases Precision from 0.8827 to 0.9221 but decreases Recall and mAP50–95, revealing a conservative prediction tendency and a remaining cross-modal limitation. These results demonstrate an improved accuracy–complexity balance for visible-light UAV detection under the reported protocol, while the HIT-UAV results reveal a remaining limitation under infrared domain shift.
MF-YOLO improves small-object detection at the cost of substantially greater computation, and introduces a stride-4 P2 prediction scale, applies Global-to-Local Spatial Aggregation independently to C2–C5 before neck fusion, and connects P2–P5 through a 64-channel Bidirectional Feature Pyramid Network (BiFPN).
Yu-Fei Wang, Ji-Ming Yang, Fang Liu et al.· Italian National Conference...· 0 citations
Reliable detection of transmission-line components and defects in unmanned aerial vehicle (UAV) imagery supports preventive maintenance. Repeated downsampling, however, removes fine spatial detail, while limited interaction between feature levels hinders small-object detection. We developed YOLO11-DAL, a compact dete...
Tao Wu, Zhong-Hua Liu· Scientific Reports· 0 citations
Object detection in Uncrewed Aerial Vehicle (UAV) imagery remains challenging due to densely distributed small objects, complex backgrounds, substantial scale variations, and frequent occlusions. Although You Only Look Once (YOLO) based detectors achieve a favourable balance between detection accuracy and computational...
Yu-Kun Xiong· 2026 7th International Confe...· 0 citations
Small and densely distributed objects in unmanned aerial vehicle (UAV) imagery are difficult to detect because deep feature extraction progressively removes the spatial evidence needed to separate and localize neighboring targets. This paper presents UAV-YOLO, a resolution-guided multi-scale detector that couples spati...
Experimental results on public benchmark datasets demonstrate that the proposed SMDS-Net achieves highly competitive detection accuracy while significantly reducing the number of model parameters and theoretical computational complexity.
Ke-Lei Sun, Jia-Li Xia, Hua-Ping Zhou et al.· Journal of Supercomputing· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.