Object detection in remote sensing imagery plays an irreplaceable role in critical fields such as military reconnaissance and disaster monitoring. However, when dealing with minute targets characterised by an extremely low pixel proportion, a lack of textural information, and severe background interference, existing algorithms still face the challenge of balancing detection accuracy with computational efficiency. To address this, this paper proposes a lightweight frequency-domain-aware end-to-end detection model, LE-DETR, based on an improved version of RT-DETR. Firstly, a Lightweight Feature Extraction Module (LFEM) is designed. Through a heterogeneous dual-path architecture and reparameterisation techniques, it significantly reduces computational complexity whilst enhancing the capture of fine-grained spatial features. Secondly, an Efficient Spatio-Frequency Fusion Module (ESFFM) is introduced. This utilises a multi-head self-attention mechanism to construct a global view whilst combining the Fourier transform to reconstruct target features from a frequency-domain perspective, thereby effectively suppressing background noise and enhancing the target’s edge signals. Finally, we propose the Efficient Frequency-Aware Fusion Feature Pyramid Network (EFAM-FPN), which utilises SPD Conv to mitigate the loss of key features during downsampling and introduces a frequency-domain attention mechanism to suppress complex background noise, thereby improving the model’s detection accuracy for extremely small objects. The experimental results show that, whilst reducing the number of parameters by 41.7% compared to the baseline model, LE-DETR achieved improvements of 2.6%, 1.7% and 2.4%, respectively, in the mAP50 metric across the three mainstream remote sensing datasets—VisDrone2019, NWPU VHR-10 and DIOR. This demonstrates an effective balance between detection accuracy and inference efficiency, fully validating its robustness and practical value in complex remote sensing application scenarios.

With the rapid advancement of remote sensing technology, target detection in remote sensing imagery plays a crucial role in military reconnaissance, urban planning, and other fields. However, there are problems such as large variations in target scale, arbitrary angles, and complex background interference in remote sensing images, making it difficult for existing target detection methods to achieve precise recognition and localization. To address these issues, this paper proposes a small target detection model for remote sensing images based on a dual-path attention mechanism and multi-scale frequency domain awareness. First, we propose the GDSC module, a gated deep separable spatial convolution module that enhances the extraction of local details and improves feature extraction efficiency. Additionally, the DAMF-DETR model uses a dual-path attention feature fusion module (DAFF) to capture fine details of densely packed small objects more effectively. We also introduce a novel and efficient multi-scale frequency domain pyramid network, termed EMSF-FPN, which employs multi-scale feature fusion and frequency domain attention mechanisms to focus on small object details, and maintains high detection accuracy even under low-contrast conditions. Finally, we introduce the Wise-Focaler-MPDIoU (WF-MPDIoU Loss), which dynamically adjusts weights using a scale factor to improve regression accuracy and accelerate convergence. Compared to the baseline model, DAMF-DETR achieves improvements of 4.1%, 3.6%, and 4.2% in the mAP50 metric on the VisDrone2019, NWPU VHR-10, and DOTA-v1.0 remote sensing image datasets, respectively, while reducing the number of parameters by 18.1%. These results demonstrate that DAMF-DETR enhances detection accuracy for small objects while maintaining a lightweight and efficient architecture.