OSM2Net: A Robust Road Network Extraction Framework From Noisy Indoor Parking OpenStreetMap

Intelligent Transportation Systems (ITS) rely on high-precision road networks, which are particularly scarce in indoor parking. Existing methods depend on expensive hardware (e.g., LiDAR) or manual mapping, both of which are costly and inefficient. The rise of the Internet of Things (IoT) has enabled large-scale data collection and connectivity, offering new opportunities for automated road network extraction. OpenStreetMap (OSM), as a crowdsourced IoT-driven platform, provides multilayer geospatial data, including the road network layer (RNL), lane boundary layer (LBL), and turn sign layer (TSL). However, OSM data often suffers from incompleteness and noisy connectivity, affecting the continuity and accuracy of road networks. This article introduces OSM2Net, a novel framework designed to extract road networks from individual layers and leverage multilayer data to construct directed road networks. Specifically, OSM2Net rasterizes noisy OSM data into bitmaps for image processing and multilayer fusion. By leveraging the topology relationship between lane boundaries and road networks, a Lane-Road Map Generator (LRMG) creates a simulated dataset for training. Then, utilizing the simulated dataset, a Lane2Net model is designed to extract road networks from sparse lane boundary images. The framework then vectorizes bitmaps into a lightweight, undirected road network and refines it into a directed network by extracting and matching turn sign information. Experimental results show that Lane2Net achieves Intersection over Union (IoU) of 93% and 92% using simulated and real-world datasets, respectively. Extensive experiments on real-world datasets confirm that OSM2Net delivers robust completeness and high-quality road network extraction.