Classification of urban road functional structure by integrating physical and behavioral features

Abstract

Multisource data can extract diverse urban functional features, facilitating a deeper understanding of the functional structure of road networks. Street view images and taxi trajectories, as forms of urban geographic big data, capture features of the urban physical environment and travel behavior, serving as effective data sources for identifying the functional structure of urban spaces. However, street view and taxi trajectory data often suffer from sparse and uneven distributions, and the differences between features are relatively small in the process of multiple feature fusion, which poses significant challenges to accurate classification of road functions. To address these issues, this study proposes the use of the Louvain algorithm and triplet loss methods to enhance features at the community level, resolving the sparse data distribution problem. Simultaneously, the attention mechanism of the graph attention network is applied to dynamically adjust the feature weights within the road network, capturing subtle differences between different features. The experimental results demonstrate that the effectiveness of feature enhancement and capturing differences has improved the accuracy of calculating complex urban road functional structures. Additionally, this study analyzes the degree of mixing and distribution of road functions and explores the relationship between the road functional structure and traffic. The work in this paper assesses urban functional structure at the street level and provides decision-making support for urban planning at a fine scale.