Crowd-sensing Driving Environments using Headway Dynamics (Demo Paper)

In this paper, we develop a set of normalized spatial temporal properties from which to assess road performance and detect abnormal traffic stream environments. Data is provided by non-instrumented retail vehicle telemetry data, which captures timestamps, GPS locations, and velocity provided every 3 seconds. Open Street Map (OSM) roadways are subdivided into 500-meter segments. Vehicles traveling across those segments are crowd- sensed every 15 minutes. The demonstration compares two traffic streams over the same segments and time periods exactly two weeks apart and illustrates the effectiveness of the approach. The novelty includes methods to create comparable spatial temporal frames and properties by transformations of telemetry data into driver experiences. The outcome of our approach generates a space time grid of cells from which to detect, describe, and diagnose traffic environments.