Mapping suburban bicycle lanes using street scene images and deep learning

TL;DR

This paper introduces a deep learning-based method to map bicycle lanes using street scene images, effectively identifying lanes that are missing from official and crowdsourced datasets, thereby improving urban cycling infrastructure data.

Contribution

It presents a novel approach combining street scene imagery and deep learning to detect bicycle lanes and enhance existing geospatial datasets.

Findings

Successfully mapped bicycle lanes in Melbourne's suburbs

Detected lanes not recorded in official or crowdsourced maps

Method improves accuracy of bicycle lane datasets

Abstract

On-road bicycle lanes improve safety for cyclists, and encourage participation in cycling for active transport and recreation. With many local authorities responsible for portions of the infrastructure, official maps and datasets of bicycle lanes may be out-of-date and incomplete. Even "crowdsourced" databases may have significant gaps, especially outside popular metropolitan areas. This thesis presents a method to create a map of bicycle lanes in a survey area by taking sample street scene images from each road, and then applying a deep learning model that has been trained to recognise bicycle lane symbols. The list of coordinates where bicycle lane markings are detected is then correlated to geospatial data about the road network to record bicycle lane routes. The method was applied to successfully build a map for a survey area in the outer suburbs of Melbourne. It was able to identify bicycle lanes not previously recorded in the official state government dataset, OpenStreetMap, or the "biking" layer of Google Maps.