Crowdsourced Speed Data: An Alternative to Conventional Speed Measurements

Abstract

Measurement of the fundamental properties of traffic flow, speed, and density on a road network is a key aspect of assessing its performance. Traditional traffic speed measurement techniques such as loop detectors, pneumatic tubes, sensors, video detection, etc., have served as primary resources to collect these data that has been used for descriptive statistical analysis of existing conditions as well as the development of transport models used to rank and compare future infrastructure projects. However, they require investment towards the purchase and installation as well as the development of a physical system to collect the necessary data which has proven to be the bottleneck. Over the last 2 decades, crowdsourced data, through smart phone technology, has offered an alternative traffic data source which is void of the capital outlay that exists with the traditional techniques. However, till date, there is no clear understanding of the quality of such crowdsourced data and how well the data matches the data from traditional sources. In this regard, we assess traffic speed measurements obtained from the Google API by comparing it with (i) the loop detector traffic speed data for 3 state highways in the city of Portland, Oregon gathered from the Portland Bureau of Transportation and (ii) the floating car traffic speed data collected for selected arterial and collector roads in the city of Bandung and Cirebon, Indonesia. Almost 95 percent of the sites indicated no significant statistical difference between the data sources highlighting the potential of the crowdsourced data as a reliable and cost-effective means of traffic speed data collection.