遥感图像船舶目标检测作为遥感应用的重要方向，在海洋监测、港口管理和国防安全等领域具有广泛的应用价值，近年来，深度学习技术的快速发展为船舶目标检测提供了新的解决方案。为系统分析现有船舶目标检测算法的优势与局限性，全面探讨了遥感图像船舶检测的改进策略，从而为各类船舶的运行组织提供有力的人工智能技术支撑。首先，系统总结了基于深度学习的目标检测算法的发展历程；随后，针对遥感图像的检测难点分析当前各阶段改进措施的优点与不足。之后，利用CiteSpace对中国知网（China National Knowledge Infrastructure, CNKI）和Web of Science近8年的文献进行关键词共现分析，探讨当前的研究进展和领域热点。此外，结合最新的YOLOv10和YOLOv11实验结果，剖析现有技术的优势与不足。最后，基于文献综述和实验结果，总结了现有技术的局限性，并提出了未来的研究方向。

As an important direction of remote sensing application, remote sensing image ship target detection has wide application value in marine monitoring, port management, national defense security and other fields. In recent years, the rapid development of deep learning technology provides a new solution for ship target detection. To systematically analyze the strengths and limitations of existing ship detection algorithms, improvement strategies for remote sensing image detection were comprehensively discussed, so as to provide powerful artificial intelligence technology support for the operation organization of various ships. Firstly, the development process of object detection algorithms based on deep learning was systematically summarized. Then, the advantages and disadvantages of the improvement measures at each stage were analyzed for the detection difficulties of remote sensing images. After that, CiteSpace was used to conduct keyword co-occurrence analysis of literature from CNKI (China National Knowledge Infrastructure) and Web of Science in the past 8 years, and the current research progress and field hotspots were discussed. In addition, combined with the latest YOLOv10 and YOLOv11 experimental results, the advantages and disadvantages of existing technologies were analyzed. Finally, based on the literature review and experimental results, the limitations of the existing techniques were summarized and future research directions were proposed.