Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

UFO-DETR: Frequency-Guided End-to-End Detector for UAV Tiny Objects

Yuankai Chen, Kai Lin, Qihong Wu, Xinxuan Yang, Jiashuo Lai, Ruoen Chen, Haonan Shi, Minfan He, Meihua Wang

TL;DR

An end-to-end object detection framework, UFO-DETR, which integrates an LSKNet-based backbone network to optimize the receptive field and reduce the number of parameters is proposed, providing an efficient solution for UAV edge computing.

Abstract

Small target detection in UAV imagery faces significant challenges such as scale variations, dense distribution, and the dominance of small targets. Existing algorithms rely on manually designed components, and general-purpose detectors are not optimized for UAV images, making it difficult to balance accuracy and complexity. To address these challenges, this paper proposes an end-to-end object detection framework, UFO-DETR, which integrates an LSKNet-based backbone network to optimize the receptive field and reduce the number of parameters. By combining the DAttention and AIFI modules, the model flexibly models multi-scale spatial relationships, improving multi-scale target detection performance. Additionally, the DynFreq-C3 module is proposed to enhance small target detection capability through cross-space frequency feature enhancement. Experimental results show that, compared to RT-DETR-L, the proposed method offers significant advantages in both detection performance and computational efficiency, providing an efficient solution for UAV edge computing.

UFO-DETR: Frequency-Guided End-to-End Detector for UAV Tiny Objects

TL;DR

An end-to-end object detection framework, UFO-DETR, which integrates an LSKNet-based backbone network to optimize the receptive field and reduce the number of parameters is proposed, providing an efficient solution for UAV edge computing.

Abstract

Small target detection in UAV imagery faces significant challenges such as scale variations, dense distribution, and the dominance of small targets. Existing algorithms rely on manually designed components, and general-purpose detectors are not optimized for UAV images, making it difficult to balance accuracy and complexity. To address these challenges, this paper proposes an end-to-end object detection framework, UFO-DETR, which integrates an LSKNet-based backbone network to optimize the receptive field and reduce the number of parameters. By combining the DAttention and AIFI modules, the model flexibly models multi-scale spatial relationships, improving multi-scale target detection performance. Additionally, the DynFreq-C3 module is proposed to enhance small target detection capability through cross-space frequency feature enhancement. Experimental results show that, compared to RT-DETR-L, the proposed method offers significant advantages in both detection performance and computational efficiency, providing an efficient solution for UAV edge computing.
Paper Structure (15 sections, 8 equations, 6 figures, 2 tables)

This paper contains 15 sections, 8 equations, 6 figures, 2 tables.

Table of Contents

  1. Introduction
  2. RELATED WORK
  3. Object Detection in UAV Imagery
  4. Real-time detection of UAV images
  5. Multi-Scale Feature Fusion
  6. PROPOSED METHOD
  7. LSKNet Backbone Network
  8. Deformable Attention
  9. DynFreq-C3
  10. EXPERIMENT
  11. Experimental Setup
  12. Ablation Study
  13. Comparative experiments of different models
  14. Visualization
  15. CONCLUSION

Figures (6)

  • Figure 1: Overview of the UFO-DETR. It is divided into the backbone, encoder, and detection head. The backbone is rebuilt using LSKNet. The decoder is implemented through CCFD based on DyFreqC3 design and AIFI with integrated deformable attention. The detection head consists of the decoder and auxiliary prediction heads, completing the final object detection task.
  • Figure 2: Structure of the LSKNet Block and LK Selection.
  • Figure 3: An illustration of Deformable Attention mechanism.
  • Figure 4: (a) RepC3 structure diagram; (b) DynFreq-C3 structure diagram.
  • Figure 5: Visual comparison results of RTDETR-L, YOLOv8M, YOLOv10, YOLOv11M. (a) shows Repeated Detections of the same object, (b) corresponds to model false positives, and (c) denotes objects that the model failed to detect.
  • ...and 1 more figures