PCP: A Prompt-Based Cartographic-Level Polygonal Vector Extraction Framework for Remote Sensing Images

Accurate cartographic-level polygonal vector extraction from remote sensing images is crucial for land survey and land cover mapping. However, current deep learning-based segmentation models often generate raster outputs with irregular boundaries, making them unsuitable for applications requiring precise vector data. This study presents the prompt-based cartographic-level polygonal (PCP) vector extraction framework, which leverages segmentation results as prompts to guide the extraction process and enhance regularity. Built upon the segment anything model (SAM), the PCP extracts the segmentation mask and an additional vertex map. To improve vertex extraction accuracy and enable more regular polygon generation, two key modules are introduced: the iterative upscaling refinement (IUR) module, which addresses challenges related to low-resolution feature maps, and the shape-rule-based vertex filtering and connecting (SRVFC) module, which enhances the vertex filtering process by learning from shape features. Experimental results on the land survey vector (LSV), LoveDA, and WHU-Mix (Vector) datasets demonstrate that the PCP outperforms existing methods in terms of vertex precision and recall, reflecting geometric accuracy, as well as in complexity-aware intersection over union (C-IoU), which balances overall accuracy and simplicity. Thus, the PCP framework provides a promising solution for cartographic-level vector extraction in remote sensing applications. The source code is available at https://github.com/wchh-2000/PCP