A Multisource Dynamic Fusion Network for Urban Functional Zone Identification on Remote Sensing, POI, and Building Footprint

Abstract

Urban functional zones (UFZ) identification with remote sensing imagery (RSI) is attracting increasing attention in urban planning and resource allocation in urban areas, etc. The UFZ is a comprehensive unit comprising geographical, how to effectively integrate the RSI and points of interest (POI) with different physical and socioeconomic characteristics is important and promising. However, there are two challenges for the UFZ identification. On one hand, the UFZ is closely related to buildings, and most current methods lack an in-depth understanding of building semantics. Therefore, an efficient integration of building footprint (FT) data deserves further investigation. On the other hand, these RSI, POI, and FT data are heterogeneous; how to effectively leverage complementary information among these highly heterogeneous modalities to enhance the comprehensive understanding of urban. To solve the above challenges, this article introduces an end-to-end deep learning-based multisource dynamic fusion network for UFZ identification on RSI, POI, and FT. In the proposed method, an adaptive weight interactive fusion module is designed to comprehensively integrate the complementary information among the heterogeneous RSI, POI, and FT data sources. In addition, a multiscale feature focus module is proposed to extract multiscale image features and emphasize critical characteristics. This method was applied to UFZ classification in Ningbo, Zhejiang Province, China, and the experimental results demonstrate the competitive performance.

Keywords

• Deep learning (DL)
• multimodal data fusion
• remote sensing imagery (RSI)
• social sensing data
• urban functional zone (UFZ)