Zero-Shot Sea-Land Segmentation Based on Edge Analysis and Automatic Prompt Point Generation

In this study, we tackle the critical challenge of sea-land segmentation for enhancing ship detection in remote sensing imagery. By focusing the search area, we significantly reduce the false alarm rate in ship detection. To overcome the limitations of scarce training data and annotation complexity, we introduce a novel zero-shot sea-land segmentation framework. This framework is integrated with a robust image segmentation model and employs an automatic prompt point generation strategy to facilitate sea-land discrimination. Our method is structured around three core components: image preprocessing, image block classification, and prompt point generation. The preprocessing module generates an edge feature map using downsampling and edge detection techniques. The classification module segments land and sea areas through a rasterization and classification process. The prompt point generation module leverages edge point clustering to create prompts on the land image block background. These prompts are then utilized by the image segmentation model to achieve precise sea segmentation. Our extensive experiments on public land-sea segmentation datasets show that our approach is robust across various parameter settings and outperforms current state-of-the-art methods.