Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

SDD-YOLO: A Small-Target Detection Framework for Ground-to-Air Anti-UAV Surveillance with Edge-Efficient Deployment

Pengyu Chen, Haotian Sa, Yiwei Hu, Yuhan Cheng, Junbo Wang

Abstract

Detecting small unmanned aerial vehicles (UAVs) from a ground-to-air (G2A) perspective presents significant challenges, including extremely low pixel occupancy, cluttered aerial backgrounds, and strict real-time constraints. Existing YOLO-based detectors are primarily optimized for general object detection and often lack adequate feature resolution for sub-pixel targets, while introducing complexities during deployment. In this paper, we propose SDD-YOLO, a small-target detection framework tailored for G2A anti-UAV surveillance. To capture fine-grained spatial details critical for micro-targets, SDD-YOLO introduces a P2 high-resolution detection head operating at 4 times downsampling. Furthermore, we integrate the recent architectural advancements from YOLO26, including a DFL-free, NMS-free architecture for streamlined inference, and the MuSGD hybrid training strategy with ProgLoss and STAL, which substantially mitigates gradient oscillation on sparse small-target signals. To support our evaluation, we construct DroneSOD-30K, a large-scale G2A dataset comprising approximately 30,000 annotated images covering diverse meteorological conditions. Experiments demonstrate that SDD-YOLO-n achieves a mAP@0.5 of 86.0% on DroneSOD-30K, surpassing the YOLOv5n baseline by 7.8 percentage points. Extensive inference analysis shows our model attains 226 FPS on an NVIDIA RTX 5090 and 35 FPS on an Intel Xeon CPU, demonstrating exceptional efficiency for future edge deployment.

SDD-YOLO: A Small-Target Detection Framework for Ground-to-Air Anti-UAV Surveillance with Edge-Efficient Deployment

Abstract

Detecting small unmanned aerial vehicles (UAVs) from a ground-to-air (G2A) perspective presents significant challenges, including extremely low pixel occupancy, cluttered aerial backgrounds, and strict real-time constraints. Existing YOLO-based detectors are primarily optimized for general object detection and often lack adequate feature resolution for sub-pixel targets, while introducing complexities during deployment. In this paper, we propose SDD-YOLO, a small-target detection framework tailored for G2A anti-UAV surveillance. To capture fine-grained spatial details critical for micro-targets, SDD-YOLO introduces a P2 high-resolution detection head operating at 4 times downsampling. Furthermore, we integrate the recent architectural advancements from YOLO26, including a DFL-free, NMS-free architecture for streamlined inference, and the MuSGD hybrid training strategy with ProgLoss and STAL, which substantially mitigates gradient oscillation on sparse small-target signals. To support our evaluation, we construct DroneSOD-30K, a large-scale G2A dataset comprising approximately 30,000 annotated images covering diverse meteorological conditions. Experiments demonstrate that SDD-YOLO-n achieves a mAP@0.5 of 86.0% on DroneSOD-30K, surpassing the YOLOv5n baseline by 7.8 percentage points. Extensive inference analysis shows our model attains 226 FPS on an NVIDIA RTX 5090 and 35 FPS on an Intel Xeon CPU, demonstrating exceptional efficiency for future edge deployment.

Paper Structure

This paper contains 22 sections, 7 equations, 5 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Ground-to-Air UAV Detection
  4. YOLO Architecture Evolution
  5. Knowledge Distillation for Compact Detectors
  6. The DroneSOD-30K Dataset
  7. Data Collection and Annotation
  8. Dataset Statistics
  9. Methodology
  10. Overall Architecture
  11. P2 High-Resolution Detection Head
  12. DFL-Free Design for Streamlined Computation
  13. NMS-Free End-to-End Inference
  14. Dual Attention Mechanism
  15. YOLO26's MuSGD Hybrid Training Strategy
  16. ...and 7 more sections

Figures (5)

  • Figure 1: Target size distribution in DroneSOD-30K.
  • Figure 2: Sample images across different conditions (complex background, occlusion, complex weather, low-light) in DroneSOD-30K.
  • Figure 3: Overall architecture of SDD-YOLO.
  • Figure 4: Knowledge Distillation framework transferring spatial representations from the Teacher to the Student network.
  • Figure 5: Qualitative comparison highlighting micro-target detection capabilities. SDD-YOLO successfully avoids false positives (e.g., birds, dogs, branches) while accurately localizing distant UAVs.