AutoLTS: Automating Cycling Stress Assessment via Contrastive Learning and Spatial Post-processing

TL;DR

This paper introduces AutoLTS, a deep learning framework that rapidly and accurately assesses cycling stress from street-view images, aiding urban planning without relying on detailed traffic data.

Contribution

The paper presents a novel contrastive learning approach combined with spatial post-processing for large-scale cycling stress assessment using street-view images.

Findings

Effective stress prediction on 39,153 Toronto road segments

Outperforms traditional methods in speed and accuracy

Demonstrates value of image data for urban cycling infrastructure planning

Abstract

Cycling stress assessment, which quantifies cyclists' perceived stress imposed by the built environment and motor traffics, increasingly informs cycling infrastructure planning and cycling route recommendation. However, currently calculating cycling stress is slow and data-intensive, which hinders its broader application. In this paper, We propose a deep learning framework to support accurate, fast, and large-scale cycling stress assessments for urban road networks based on street-view images. Our framework features i) a contrastive learning approach that leverages the ordinal relationship among cycling stress labels, and ii) a post-processing technique that enforces spatial smoothness into our predictions. On a dataset of 39,153 road segments collected in Toronto, Canada, our results demonstrate the effectiveness of our deep learning framework and the value of using image data for cycling stress assessment in the absence of high-quality road geometry and motor traffic data.