Generation of intra-community roads based on human-flow modeling (HFM)

Community roads are crucial for efficient navigation in residential areas. However, current navigation maps often lack comprehensive coverage of these roads. To address this issue, we present a Human-Flow Model (HFM) to identify roads within residential communities by utilizing abundant low-frequency trajectory data from human movements. First, the HFM leverages human movement density in residential zones to estimate the likelihood of road existence. Using the probability distribution of human movement and neighboring building footprints, we construct a Human-Flow Probability Field (HFPF), which serves as a distribution representation for modeling human movement within densely populated built-up areas. Then, the flow paths are extracted from the HFPF using hydrological analysis techniques, which facilitates the identification of main paths and smaller branches within the community road network. Finally, the road network is refined using morphological methods. Our model was tested using six residential communities located in Wuhan, China. It consistently outperformed other methods by detecting more roads with higher accuracy, especially intricate branches. By incorporating flow semantics, our model capitalizes on sparse trajectory data to enhance the fine-scale community road networks. This improvement enhances the last-mile navigation experience in sustainable cities, contributing to overall urban mobility and convenience for residents.