Identify different types of urban renewal implementations at streetscape scale

This repository contains the codes used for the manuscript: "Identify different types of urban renewal implementations at streetscape scale".
AbstractUnderstanding different types of urban renewal implementations process is essential for enhancing residents’ quality of life and optimizing sustainable development strategies. Existing research primarily focuses on detecting pixel-level or object-level changes in urban physical space, often neglecting the semantic complexity inherent in urban renewal. This complexity involves integrating what has changed, where the change occurred, and how it occurred in order to identify between different types of renewal. To address this gap, this study proposes a multi-type urban renewal identification (MTURI) framework based on street view images (SVIs), integrating multi-source information at the street level. We developed an SVI benchmark dataset and a comprehensive indicator system that integrates built features, semantic attributes, and street-level environmental characteristics. Utilizing a two-stage recognition algorithm, the MTURI model is designed to identify various types of urban renewal activities. We also applied the model to four renewal community case studies to analyze the potential applications of the method. The results show that our model can effectively identify different types of renewal and offer an evidence-based evaluation of the effectiveness and benefits of urban policy interventions. We believe our model provides new tools and perspectives for SVI identification research and practice.