TPP-SAM: A Trajectory Point Prompting Segment Anything Model for Zero-Shot Road Extraction From High-Resolution Remote Sensing Imagery

Abstract

The segment anything model (SAM) enables zero-shot or interactive segmentation of visual content and has shown remarkable performance with natural images. However, SAM often fails to accurately extract roads from high-resolution remote sensing imagery (HRSI) due to complex road boundaries, background interference, and its semantic-agnostic nature. This article proposes an automated road extraction method called trajectory points prompting SAM (TPP-SAM), which uses trajectory points as segmentation prompts for roads in HRSI, eliminating the need for complex manual prompts. TPP-SAM introduces road centerline constraint (RCC) and sampling constraint (SC) layers to select reliable trajectory prompt points and migrates centroid information from building roofs as a background constraint (BC). This three-layer constraint system integrates real-world crowdsourced information with the vision foundation model. In addition, the data structure of prompt points is organized using map matching and recoding rules, accounting for their attributes and relative positional coordinates. The processed data are then embedded into the prompt encoder to generate road semantic masks. Results show that TPP-SAM achieves comprehensive road segmentation across various scenarios, demonstrating the viability of using trajectory points as interactive road segmentation prompts. The proposed model extends the application of geographic image segmentation and holds potential for other geolabeled features.

Keywords

• High-resolution remote sensing imagery (HRSI)
• mathematical morphology
• road extraction
• segment anything model (SAM)
• trajectories