Work

SFA-DETR: An Efficient UAV Detection Algorithm with Joint Spatial–Frequency-Domain Awareness

Year: 2025

Type: article

Abstract: Unmanned Aerial Vehicle (UAV) detection often faces challenges such as small target size, loss of textural details, and interference from complex backgrounds. To address these issues, this paper proposes a novel object detection algorithm named Spatial-Frequency Aware DETR (SFA-DETR), which integrates both spatial- and frequency-domain perception. For spatial-domain modeling, a backbone network named IncepMix is designed to dynamically fuse multi-scale receptive field information, enhancing the model's ability to capture contextual information while reducing computational cost. For frequency-domain modeling, a Frequency-Guided Attention Block (FGA Block) is introduced to improve perception of target boundaries through frequency-aware guidance, thereby increasing localization accuracy. Furthermore, an adaptive sparse attention mechanism is incorporated into AIFI to emphasize semantically critical information and suppress redundant features. Experiments conducted on the DUT Anti-UAV dataset demonstrate that SFA-DETR improves mAP50 and mAP50:95 by 1.2% and 1.7%, respectively, while reducing parameter count and computational cost by 14.44% and 3.34%. The results indicate that the proposed method achieves a balance between detection accuracy and computational efficiency, validating its effectiveness in UAV detection tasks.

Source: Sensors

DOI: 10.3390/s25216719

Authors: Peinan He, Xu Wang

Institution: Civil Aviation Flight University of China

Language: English

Topic: Advanced Neural Network Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $3,137

Funders: Dalian University of Technology, Department of Science and Technology of Sichuan Province