SFG-Net: A Scattering Feature Guidance Network for Oriented Aircraft Detection in SAR Images

Synthetic Aperture Radar (SAR) aircraft detection plays a crucial role in various civilian applications. Benefiting from the powerful capacity of feature extraction and analysis of deep learning, aircraft detection performance has been improved by most traditional general-purpose visual intelligence methods. However, the inherent imaging mechanisms of SAR fundamentally differ from optical images, which poses challenges for SAR aircraft detection. Aircraft targets in SAR imagery typically exhibit indistinct details, discrete features, and weak contextual associations and are prone to non-target interference, which makes it difficult for existing visual detectors to capture critical features of aircraft, limiting further optimization of their performance. To address these issues, we propose the scattering feature guidance network (SFG-Net), which integrates feature extraction, global feature fusion, and label assignment with essential scattering distribution of targets. This enables the network to focus on critical discriminative features and leverage robust scattering features as guidance to enhance detection accuracy while suppressing interference. The core components of the proposed method include the detail feature supplement (DFS) module and the context-aware scattering feature enhancement (CAFE) module. The former integrates low-level texture and contour features to mitigate detail ambiguity and noise interference, while the latter leverages global context of strong scattering information to generate more discriminative feature representations, guiding the network to focus on critical scattering regions and improving learning of essential features. Additionally, a feature scattering center-based label assignment (FLA) strategy is introduced, which utilizes the spatial distribution of scattering information to adaptively adjust the sample coverage and ensure that strong scattering regions are prioritized during training. A series of experiments was conducted on the CSAR-AC dataset to validate the effectiveness and generalizability of the proposed method.