 Our proposed rotation-dense feature Pyramid Networks, RDFPN, is a novel ship detection framework designed to address the limitations of existing methods. It uses dense connections between layers to enhance feature propagation and encourage feature reuse, while also incorporating a rotation anchor strategy to reduce the redundant detection region and improve recall. Experimental results demonstrate that RDFPN achieves superior performance compared to other state-of-the-art methods. This article was authored by Shui Yong, Hao Sun, Kun Fu, and others.