Two-Stage Target Detection for Compact HFSWR With Space-to-Depth YOLOv8 and Multiframe ViT

Accurate and reliable target detection is a crucial requirement of high-frequency surface wave radar for effective maritime surveillance. However, existing methods based on single-frame radar images primarily focus on static target features, limiting their ability to capture dynamic ship behaviors across multiple frames. In this study, a two-stage multiframe target detection framework (MFTDF) is proposed to address this issue in ship-target detection from range-Doppler (RD) images. The framework consists of two stages: a space-to-depth YOLOv8 network in Stage-1 and a multiframe vision transformer network in Stage-2. First, Stage-1 aims to extract regions of interest (ROI) from the current and several preceding RD images. Thereafter, target association and pattern selection are applied to collect multiframe image patch sequences for each ROI result. Finally, Stage-2 focuses on further discriminating the input image patches to obtain refined target detection results. Moreover, the dataset for training and validating the two-stage network is automatically generated based on the automatic identification system ship data and constant false alarm rate detection results to identify all true and visible targets, ensuring the dataset's credibility. Experiments using the measured data show that the proposed MFTDF achieves a considerably improved precision rate while maintaining an average improvement of 12.3% in the recall rate. These results confirm that MFTDF delivers superior detection accuracy and efficiency, offering a robust solution for maritime target detection in complex scenarios.