TranSTD: A Wavelet-Driven Transformer-Based SAR Target Detection Framework With Adaptive Feature Enhancement and Fusion

作者：Bobo Xi, Jiaqi Chen, Yan Huang, Jiaojiao Li, Yunsong Li, Zan Li, Xiang‐Gen Xia · 发表于：IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · 年份：2025 · DOI：10.1109/jstars.2025.3639785 · 被引用次数：1 · 研究领域：Advanced SAR Imaging Techniques、Synthetic Aperture Radar (SAR) Applications and Techniques、Advanced Neural Network Applications

Target detection in Synthetic Aperture Radar (SAR) images is of great importance in civilian monitoring and military reconnaissance. However, the unique speckle noise inherent in SAR images leads to semantic information loss, while traditional CNN downsampling methods exacerbate this issue, impacting detection accuracy and robustness. Moreover, some dense target scenarios and weak scattering features of targets make it challenging to achieve sufficient feature discriminability, adding complexity to the detection task. Additionally, the multi-scale characteristic of SAR targets presents difficulties in balancing detection performance with computational efficiency in complex scenes. To tackle these difficulties, this paper introduces a wavelet-driven transformer-based SAR target detection framework called TranSTD. Specifically, it incorporates the Haar wavelet dynamic downsampling (HWDD) and semantic preserving dynamic downsampling (SPDD) modules, which effectively suppress noise and preserve semantic information using techniques such as Haar wavelet denoise (HW Denoise) and input-driven dynamic pooling downsampling (IDPD). Furthermore, the SAR adaptive convolution bottleneck (SAC Bottleneck) is proposed for enhancing the discrimination of features. To optimize performance and efficiency across varying scene complexities, a multiscale SAR attention fusion encoder (MSAF Encoder) is developed. Extensive experiments are carried out on three datasets, showing that our proposed algo...