3D image processing of vehicular trajectories in roundabouts

Vehicular trajectory analysis is a challenging task both for safety and capacity concerns in road transportation. In particular, vehicular trajectories on roundabouts should be carefully designed in order to achieve desired performance. Therefore, the analysis of what happens on existing roundabouts is a key analytical tool in propelling the drafting of new design norms and in correcting building errors. Difficulties in analysing, by visual tracking, vehicle trajectories on roundabouts are known; for instance, different perspective effects on vehicle outlines during circulation, due to the way cameras are pointed, negatively affect precision both for vehicle position and speed estimation in 2D tracking. The research described in this paper overcomes the above mentioned problems and faces the trajectory tracking in roundabouts by estimating the true 3D position of each vehicle. Two different algorithms are investigated both based on a model based smoothing Montecarlo approach: the Viterbi algorithm and the Particle Smoother. The model used in this research for vehicles is a parallelepiped whose dimensions are directly estimated from images inferring vehicular class: cars, trucks or motorbikes. Both algorithms are tested and compared on data collected in one working roundabouts with two different set-ups. 3D tracking presents a higher complexity to be implemented since the object to be reconstructed needs to be modelled to retrieve its position and orientation from its 2D projection on the image plane. On the other hand, performance is enhanced and precision in trajectory and speed reconstruction (especially with the Particle Smoother algorithm) is not far from that obtainable by a RTK-GPS system. This new approach allows a better reconstruction of flow features in roundabouts and hence provides researchers with a very accurate tool for the analysis of roundabout performance, applicable also to other types of road infrastructures.