Analysis of Space-Mean Speed Measurement Methods

Accurate measurement of space-mean speed is essential for traffic monitoring and transportation modelling. This study compares three space-mean speed measurement methods: indirect radar estimation, direct measurement using video-based license plate recognition and crowdsourced data from the Google Maps API. Using video-based recognition as the reference, the accuracy of radar and Google Maps data is evaluated using the Mean Absolute Error (MAE). Results indicate that radar measurements are more precise (MAE = 5.74 km/h, deviation = 15.77 %) than Google Maps API data (MAE = 8.12 km/h, deviation = 19.86 %). While both methods generally reflect traffic speed trends on the analysed section, radar demonstrates higher accuracy under the given conditions. Despite its greater deviation, Google Maps API remains a promising alternative for space-mean speed estimation. However, further validation is required to assess the performance of both radar and Google Maps API data across roads with different geometric characteristics.