Cross-Sensor SAR Image Target Detection Based on Dynamic Feature Discrimination and Center-Aware Calibration

Xianghui Zhang, Siqian Zhang, Zhongzhen Sun, Chenfang Liu, Yuli Sun, Kefeng Ji, Gangyao Kuang

Abstract: In practical synthetic aperture radar (SAR) target detection applications, it is often encountered that the training and testing data come from different SAR sensors, leading to a decline in the SAR target detection performance. Although domain adaptation methods can achieve model generalization through feature transfer, the change of scattering characteristics for the same target and the difference in feature distribution, caused by cross sensor, cannot be ignored in SAR images. It is inevitable to lead to the escalation of the offset in the bounding box regression and deviation of the feature alignment. To address these issues, a cross-sensor SAR image target detection method based on the dynamic feature discrimination and center-aware calibration is proposed. Based on the domain adaptation framework, initially, a dynamic feature discrimination module (DFDM) is introduced to address the exacerbated offset in the regression. A bidirectional spatial feature aggregation (BSFA) mechanism is employed to aggregate features in both horizontal and vertical directions, and a multiscale structure is adopted to enhance the scattering and semantic features, which can dynamically constrain the target position while improving target discrimination capability. Then, the center-aware calibration module (CACM) is designed to address the alignment deviation in feature transfer. The target salience relationship is modeled based on the distance between different positions and the target center to suppress the background clutter interference. The perception center of the target is focused by combining the centerness map and classification map, which can calibrate the domain-invariant features and alleviate misalignment. Finally, the proposed method is tested on two datasets, MiniSAR and FARAD, and compared with the latest domain adaption methods. Both mAP and $F1$ values have improved by more than 6%–20%, verifying the effectiveness of the proposed method.

External IDs:dblp:journals/tgrs/ZhangZSLSJK25