A self-supervised detection method for mixed urban functions based on trajectory temporal image

Open Webpage

Zhixing Chen, Luliang Tang, Xiaogang Guo, Guizhou Zheng

Published: 2024, Last Modified: 16 Nov 2025Comput. Environ. Urban Syst. 2024EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•We propose a novel feature representation structure termed the Trajectory Temporal Image using location big data.•We construct a self-supervised model for detecting mixed urban functions with image-based human activity semantics.•We reveal a polarized urban development trend based on the mixture index of urban functions.