Development and Evaluation of Intersection-Based Turning Movement Counts Framework Using Two Channel LiDAR Sensors

This paper presents vehicle localization and tracking methodology to utilize two-channel LiDAR data for turning movement counts. The proposed methodology uniquely integrates a K-means clustering technique, an inverse sensor model, and a Kalman filter to obtain the final trajectories of an individual vehicle. The objective of applying K-means clustering is to robustly differentiate LiDAR data generated by pedestrians and multiple vehicles to identify their presence in the LiDAR’s field of view (FOV). To localize the detected vehicle, an inverse sensor model was used to calculate the accurate location of the vehicles in the LiDAR’s FOV with a known LiDAR position. A constant velocity model based Kalman filter is defined to utilize the localized vehicle information to construct its trajectory by combining LiDAR data from the consecutive scanning cycles. To test the accuracy of the proposed methodology, the turning movement data was collected from busy intersections located in Newark, NJ. The results show that the proposed method can effectively develop the trajectories of the turning vehicles at the intersections and has an average accuracy of 83.8%. Obtained R-squared value for localizing the vehicles ranges from 0.87 to 0.89. To measure the accuracy of the proposed method, it is compared with previously developed methods that focused on the application of multiple-channel LiDARs. The comparison shows that the proposed methodology utilizes two-channel LiDAR data effectively which has a low resolution of data cluster and can achieve acceptable accuracy compared to multiple-channel LiDARs and therefore can be used as a cost-effective measure for large-scale data collection of smart cities.

Assessment of driver compliance on roadside safety signs with auditory warning sounds generated from pavement surfaceea driving simulator study

A variety of word messages are used in highways in different forms to inform drivers of traffic safety information or to influence positively drivers＇ behavior. These include direct word messages for a particular event （such as road work） or general safety messages that warn drivers of risky driving behaviors （such as distracted driving and speeding）. However, it is often observed that many drivers even do not recognize the safety messages despite being displayed on roadside signs in a fairly good visibility condition. The present study focused on an engineering method, namely auditory warning sound （AWS）, which calls driver＇s attention on driving tasks and helps them comply with roadside safety signs. A driving simulator experiment was conducted to assess effects of AWS on driver compliance to roadside safety signs. AWS was implemented into driving simulator scenarios as a parameter to generate a certain level of growling warning sounds when subject vehicles are entering within a legi- bility distance of a roadside safety sign. The present study described laboratory setup and data for the driving simulator experiment, and drew conclusions on driver compliance to roadside safety signs with and without presence of AWS. The experiment results show that drivers are more compliant to roadside safety signs when AWS is used. It is expected that AWS will greatly help drivers comply with roadside safety signs where a specific safety concern is raised, such as a work-zone or a drowsy driving advisory zone.