DAF-Net: Dual-Aperture Feature Fusion Network for Aircraft Detection on Complex-Valued SAR Image

Aircraft detection in synthetic aperture radar (SAR) images plays a crucial role in supporting essential tasks, such as airport management and airspace monitoring. Most of the existing SAR aircraft detection algorithms are predominantly designed based on the scattering characteristics of full-aperture images, which provide high-resolution and rich detail information. However, in full-aperture images, responses from different angles are aliased, making it challenging to disentangle angular-specific details for anisotropic aircraft. Furthermore, the extended synthetic aperture time exacerbates the defocusing of slow-moving aircraft, increasing the likelihood of missed detections. Considering the aforementioned challenges, for targets exhibiting anisotropy and dispersion under high resolution, their nonstationary characteristics can be extracted by decomposing subapertures and employed as additional information to enhance detection accuracy. Therefore, we propose a dual-aperture feature fusion network (DAF-Net) designed to improve aircraft detection by mining, enhancing, and fusing features from both full-aperture and subaperture images. Specifically, a siamese backbone network with position-consistent weight supervision is introduced to efficiently and accurately extract features from the parallel input of full-aperture and subaperture images. Subsequently, an aperture-based feature enhancement module is proposed to leverage the scattering characteristics of aircraft and their context, thereby reinforcing the unique semantic information present in both full-aperture and subaperture images. Finally, a region-aware cross-attention fusion module is developed, which adaptively associates and fuses full-aperture and subaperture features based on spatial mapping relationships. Furthermore, experiments conducted on complex-valued SAR aircraft dataset demonstrate the effectiveness of the proposed method. The DAF-Net improves AP50 and AP75 by 5.8% and 5.3% compared to the baseline, respectively, and achieves optimal performance compared to other detectors.