Ship Target Search in Multisource Visible Remote Sensing Images Based on Two-Branch Deep Learning

Ship target search tasks aim to match specific ships across two or more satellite images. Like pedestrian and vehicle reidentification tasks in computer vision, accurate ship reidentification encounters challenges, including subtle differences between the ships of the same type and substantial intrainstance variations due to satellite angle of view and spectral differences. To tackle these challenges, this letter introduces a deep learning (DL)-based two-branch framework for ship target search, integrating ship detection and reidentification tasks. One branch extracts the target ship features, while the other captures the search region features. These features are then fused through a dedicated layer, and the final output is derived from the keypoint detection header. A new dataset was curated using Sentinel-2 and Gaofen-1 satellite data. Experimental results validate the robustness of the proposed method, achieving an accuracy of 94.37% on the new dataset. Our method's scalability has been validated through experiments using CBERS-04 and Gaofen-6 satellite data.