Multi-class object detection is critical for intelligent traffic monitoring applications in smart cities as well as connected autonomous vehicles. Although, numerous research works evaluate the performance of image processing algorithms for onvehicle cameras, the body of research evaluating performance of image processing of stationary cameras located near intersections is limited. In this rese...

Quick and reliable estimation of traffic conditions is of critical importance for advanced traffic management systems, especially when heavy congestion occurs. This paper proposes a methodology to predict queue spillovers in city street networks with signalized intersections using data from loop detectors (counts and occupancy). The key idea of the developed methodology is that when spillovers ...

This study proposes a two-equation Bayesian modelling approach to simultaneously study cyclist injury occurrence and bicycle activity at signalized intersections as joint outcomes. This approach deals with the potential presence of endogeneity and unobserved heterogeneities and is used to identify factors associated with both cyclist injuries and volumes. Its application to identify high-risk c...

This paper presents a scalable, discreet and mobile video-camera system that takes elevated video data of roadway locations for traffic safety analysis. The video is used to extract microscopic traffic parameters including road-user trajectories, lane changes and speeds. Collected video data is processed using an open-source automatic tracking tool. Trajectories can be then used to analyse road...

Modeling the traffic flow at signalized intersections has been discussed in many works [1][2][3][4]. Though streets and intersections and designed to be Ergodic, the traffic flow during busy hours is not necessarily Ergodic. In this paper, we modeled the traffic at intersection during busy hours by using M/G/1 model. And based on the collected data, we modeled a special service distribution pat...