Traffic metrics at urban intersections using a low-cost image processing approach

© 2018 Association for Computing Machinery.This paper describes a cost-effective system to obtain trafPic metrics at urban intersections. The system combines background subtraction techniques with contrast analysis methods to obtain trafPic metrics based on a number of regions of interest. In order to reduce installation costs, the system has been designed to be able to work with already installed cameras. Moreover, it can be conPigured to adapt the computational requirements to the processing capacity of the target platform. In this paper, the system has been implemented on a BeagleBone Black platform and tested using a real surveillance video camera placed in Plaza de España (Madrid, Spain).