用视觉语言模型提升遥感图像船舶检测的语义感知能力
Semantic-Aware Ship Detection with Vision-Language Integration
- 融合视觉语言模型与多尺度滑动窗口策略
- 构建专用数据集ShipSem-VL捕捉船舶细粒度属性
- 在复杂场景下显著提升检测精度，适合遥感应用研究者
遥感图像中的船舶检测在海洋活动监控、航运物流和环境研究中具有重要意义。现有方法常难以捕捉细粒度语义信息，限制了其在复杂场景下的效果。为此，我们提出一种结合视觉语言模型（VLMs）与多尺度自适应滑动窗口策略的新检测框架。为实现语义感知船舶检测（SASD），我们构建了专用的ShipSem-VL视觉语言数据集，以捕捉船舶的细粒度属性。通过三个明确的任务评估，全面分析了该框架的性能，从多个角度验证了其在推进SASD方面的有效性。
原文摘要 · Abstract (English)
Ship detection in remote sensing imagery is a critical task with wide-ranging applications, such as maritime activity monitoring, shipping logistics, and environmental studies. However, existing methods often struggle to capture fine-grained semantic information, limiting their effectiveness in complex scenarios. To address these challenges, we propose a novel detection framework that combines Vision-Language Models (VLMs) with a multi-scale adaptive sliding window strategy. To facilitate Semantic-Aware Ship Detection (SASD), we introduce ShipSem-VL, a specialized Vision-Language dataset designed to capture fine-grained ship attributes. We evaluate our framework through three well-defined tasks, providing a comprehensive analysis of its performance and demonstrating its effectiveness in advancing SASD from multiple perspectives.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。