An Experimental Urban Case Study with Various Data Sources and a Model for Traffic Estimation

Abstract

A reliable estimation of the traffic state in a network is essential, as it is the input of any traffic management strategy. The idea of using the same type of sensors along large networks is not feasible; as a result, data fusion from different sources for the same location should be performed. However, the problem of estimating the traffic state alongside combining input data from multiple sensors is complex for several reasons, such as variable specifications per sensor type, different noise levels, and heterogeneous data inputs. To assess sensor accuracy and propose a fusion methodology, we organized a video measurement campaign in an urban test area in Zurich, Switzerland. The work focuses on capturing traffic conditions regarding traffic flows and travel times. The video measurements are processed (a) manually for ground truth and (b) with an algorithm for license plate recognition. Additional processing of data from established thermal imaging cameras and the Google Distance Matrix allows for evaluating the various sensors’ accuracy and robustness. Finally, we propose an estimation baseline MLR (multiple linear regression) model (5% of ground truth) that is compared to a final MLR model that fuses the 5% sample with conventional loop detector and traffic signal data. The comparison results with the ground truth demonstrate the efficiency and robustness of the proposed assessment and estimation methodology.

Link Travel Time Estimation for Arterial Networks Based on Sparse GPS Data and Considering Progressive Correlations

“…For one of the benchmarks, we decided on travel time data provided by the Google direction API [45]. Google historical data is used among other researchers as a comparison benchmark [46]. Google historical travel time data is fetched through third party website Outscraper [47] in which we could extract the instantaneous travel time from an origin to a destination exactly for the study time and date.…”

A Survey and Tutorial on Network Optimization for Intelligent Transport System Using the Internet of Vehicles

“…Vehicular nodes are informed about traffic situations early based on communication received. This may assist vehicles with changing their courses in case of traffic congestion and minimizes travel time [ 45 , 46 ]. The application for road congestion control helps ensure free flow of traffic by reducing road congestion.…”

DataFITS: A Heterogeneous Data Fusion Framework for Traffic and Incident Prediction

“…In [27], the authors introduce a model to estimate traffic within a small urban area in Zurich, with data acquired as part of a video measurement campaign. Their solution fuses information from Loop detectors, traffic lights, and other sensors (e.g., video plus license plate recognition, thermal cameras) and trains different MLR models with this data.…”