Real-time roadway emissions estimation using visual traffic measurements

Monitoring the state of our roadways has become increasingly important in order to better manage traffic congestion. Sophisticated traffic management systems are being developed that are able to process both static and mobile sensor data that provide traffic information for the roadway network. In addition to typical traffic data such as flow, density, and average traffic speed, there is now strong interest in environmental factors such as greenhouse gas and pollutant emissions from traffic. It is now possible to combine real-time traffic data along with instantaneous emission models to estimate these environmental measures in real-time. In this paper, we describe a system that can more accurately determine average traffic fuel economy, CO2, CO, HC, and NOx emissions using a computer vision-based methodology that also incorporates energy/emission profiles from the comprehensive modal emissions model CMEM and EPA's MOVES emission factor database. The vision system provides information not only on average traffic speed, density, and flow, but also on individual vehicle trajectories and recognized vehicle categories. The vehicle trajectories for the specific identified categories are used by the emissions model to predict environmental parameters. This estimation process provides far more dynamic and accurate environmental information compared to static emission inventory estimation models.