At present, it is more difficult to recognize ship targets under strong jamming conditions. Therefore, an improved model based on YOLOv5 model is proposed in this paper to improve the detection accuracy and adaptability of ship targets and passive jamming. First, the original network is optimized by adding a detection layer for small targets in the YOLOv5 model, which aims to enhance the detection accuracy of small targets and ensure more effective identification of target ships in complex Marine environments. Secondly, due to the integration of an Exponential Moving Average (EMA), not only can reduce the impact of ocean noise and complex background, but also make the model have stronger feature expression ability in recognition, thus improving the recognition performance of the algorithm. Finally, the ship RD image data set under passive interference environment is used for experimental verification. The experimental results show that the improved method in this paper achieves better target recognition performance on the RD data set, and effectively improves the accuracy of target recognition.