Crowdsourcing Urban Bicycle Level of Service Measures

Abstract: Cycling communities have been related to lower obesity rates and lower stress levels. Nevertheless, one of the main obstacles to increase ridership in cities is the lack of information regarding perceived cycling safety at the street level. City planners have typically used extensive road network and traffic information to approximate cycling safety levels. However, this approach requires the deployment of expensive sensors thus making it hard for many cities to get access to accurate cycling safety maps. In this poster, we present an evaluation of several methods to predict urban cycling safety at the street level, exclusively using public information from open and crowdsourced datasets. We also present an open-source, crowdsourced platform developed to help cities gather ground truth cycling safety labels so as to train their own local models to achieve the highest safety prediction accuracies. We evaluate the proposed approach in the city of Washington D.C. and achieve F1 scores of 66%, 69% and 85% when five, four or three different cycling safety levels are considered. Overall, our project demonstrates a novel way to answer cycling safety questions using a combination of large-scale, open and crowdsourced data together with the power of machine learning techniques.

Explanation of Demonstration: The demonstration will showcase a web tool we have created to crowdsource cycling safety levels from cyclists. Visitors to the table will be able to explore the tool on a laptop, watch videos, provide safety ratings and explore the final map with the collected ratings for street segments in DC. Given the large number of visitors to the demos, we will also use it as an opportunity to collect more data from interested cyclists.