Urban Safety Perception Assessments via Integrating Multimodal Large Language Models with Street View Images

TL;DR

This paper introduces an automated approach using multimodal large language models and image retrieval techniques to assess urban safety perception efficiently and accurately, reducing reliance on manual annotations and improving transferability across cities.

Contribution

The study presents a novel automated method combining MLLMs and CLIP-based retrieval for urban safety evaluation, outperforming traditional deep learning models in efficiency and accuracy.

Findings

MLLMs closely align with human safety perception assessments

The CLIP-based K-NN method efficiently evaluates city-wide safety indices

Proposed approach outperforms existing deep learning methods in accuracy and speed

Abstract

Measuring urban safety perception is an important and complex task that traditionally relies heavily on human resources. This process often involves extensive field surveys, manual data collection, and subjective assessments, which can be time-consuming, costly, and sometimes inconsistent. Street View Images (SVIs), along with deep learning methods, provide a way to realize large-scale urban safety detection. However, achieving this goal often requires extensive human annotation to train safety ranking models, and the architectural differences between cities hinder the transferability of these models. Thus, a fully automated method for conducting safety evaluations is essential. Recent advances in multimodal large language models (MLLMs) have demonstrated powerful reasoning and analytical capabilities. Cutting-edge models, e.g., GPT-4 have shown surprising performance in many tasks. We employed these models for urban safety ranking on a human-annotated anchor set and validated that the results from MLLMs align closely with human perceptions. Additionally, we proposed a method based on the pre-trained Contrastive Language-Image Pre-training (CLIP) feature and K-Nearest Neighbors (K-NN) retrieval to quickly assess the safety index of the entire city. Experimental results show that our method outperforms existing training needed deep learning approaches, achieving efficient and accurate urban safety evaluations. The proposed automation for urban safety perception assessment is a valuable tool for city planners, policymakers, and researchers aiming to improve urban environments.