Traffic Density Estimation under Heterogeneous Traffic Conditions using Data Fusion

Data fusion is one of the recent approaches in traffic analysis for the accurate estimation and prediction of traffic parameters. In this approach, the parameters are estimated using the data from more than one source for better accuracy. This paper discusses a model based approach to estimate the parameters of heterogeneous traffic using both location data and spatial data using data fusion. The proposed method uses the Kalman filtering technique for the estimation of traffic density. Traffic density is a spatial parameter which is difficult to measure directly from field and can be measured only using aerial photography. Hence, it is usually estimated from other easily measurable parameters such as speed, flow, etc., or from a combination of such parameters. The present study estimates density using the flow values measured from video and the travel time obtained from Global Positioning System (GPS) equipped vehicles. The study also reports density estimation using flow and Space Mean Speed (SMS) obtained from location based data alone without fusing with spatial data, using the Extended Kalman filter technique. The estimates are corroborated using actual values and the results show data fusion performing better while estimating density.