A traffic signal and loop detector dataset of an urban intersection regulated by a fully actuated signal control system.

Fully actuated signal controls are becoming increasingly popular in modern urban environments, attempting to reduce congestion locally, synchronize flows, or prioritize specific types of vehicles. This trend is expected to grow as more vehicles are expected to communicate via Vehicle-to-Infrastructure (V2I) communication. The presented dataset contains cleaned observations from a fully actuated signal control system with priority for public transportation. Time series data of traffic signals that regulate vehicle, public transportation, bicycle, and pedestrian traffic flows are available, showing where a traffic signal operates in a red or green phase. Also, loop detector data representing the occupancy at several locations at an urban intersection in Zurich, Switzerland is available. The data of all traffic signals and loop detectors corresponds to January and February 2019 and has a resolution of 1 s. Recent advances in transportation science show novel approaches for signalized intersections, but most publications assess their methodology on self-collected or simulated data. Therefore, the presented dataset aims at facilitating the development, calibration, and validation of novel methodological developments for modeling, estimation, forecasting, and other tasks in traffic engineering. Furthermore, it can be used as a real-world benchmark dataset for objectively comparing different methodologies.

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

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.