Aug 2026· International Conference on Machine Learning and Unmanned Systems· Vol 14307, pp. 1430706 - 1430706-7· 0 citations· 18 references
Engineering
TL;DR
A stride-4 P2 detection head with shared Distribution Focal Loss and channel scaling is co-designed, reducing parameters by 7.4% while improving mAP50 by 2.95% and AP_S by 3.19 pp on VisDrone-DET2019, indicating that resolution and parameter efficiency in UAV detection are not inherently at odds.
Abstract
Small object detection from UAVs is fundamentally limited by the resolution loss imposed by standard P3–P5 feature pyramids, which leave nearly 47% of VisDrone annotations under-resolved. We address this by co-designing a stride-4 P2 detection head with shared Distribution Focal Loss and channel scaling, reducing parameters by 7.4% while improving mAP50 by 2.95% and AP_S by 3.19 pp on VisDrone-DET2019. On the RTX 3090 (FP16), the model runs at 128.9 FPS. A channel-selective variant (Variant G, 8.46M) recovers large-object AP by up to 9.7 pp; on the RK3588 NPU (INT8), it achieves 8.4 FPS within 9.70 MB NPU memory. The results indicate that resolution and parameter efficiency in UAV detection are not inherently at odds.
A lightweight, high-precision framework extending the YOLOv11 architecture, integrating Progressive Channel-wise Self-Attention and Dynamic Tanh, which provides a practical and efficient solution for real-time aerial surveillance at night.
Hongbo Wang, Jiadi Qu, Da Yang et al.· IEEE Access· 0 citations
PDLL-YOLO comprises a P2–P3–P4 high-resolution prediction architecture and three core modules: the detail-structure-aware module (DSAM), the local-context enhanced fusion module (LCEF), and the local density hint module (LDH).
Zhi-Wei Sun, Guang-Lei Zhang, Yu-Xin Xing et al.· IEEE Journal of Selected Top...· 0 citations
Small-object detection in unmanned aerial vehicle (UAV) imagery remains challenging due to small target scales, dense target distributions, complex backgrounds, and limited onboard computational resources. To address these coupled problems, this paper proposes ASE-YOLO11, a lightweight improved detector based on YOLO11...
Shi-Hua Hou· 2026 7th International Confe...· 0 citations
These results support improved accuracy under the specified controlled RGB corruptions, while not establishing universal real-weather or cross-modal robustness, while not establishing universal real-weather or cross-modal robustness.
Yang Zhong, Xiu-Zai Zhang, Juan-Juan Ji et al.· Remote Sensing· 0 citations
Small vehicle detection in uncrewed aerial vehicle (UAV) imagery is severely hindered by low target resolution, drastic scale variations, and complex background occlusion, yielding high false-negative rates in conventional detectors. Here, we propose an enhanced YOLO11 architecture optimized to resolve these limitation...
Yu Zhang, Bao-Dong Li, Ji-Hai Li et al.· 2026 3rd International Confe...· 0 citations
. To address the issues of low pixel ratio of extremely small targets and the susceptibility to missed detections and false detections in traditional detection algorithms under complex environmental conditions during drone aerial surveillance, this paper proposes a new detection scheme based on YOLOv8s.This study first...
Hao-Rui Huang· Proceedings of the 4th Inter...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
