Counting traffic using optical flow algorithm on video footage of a complex crossroad

A practical solution for counting traffic is analysed in this paper. The goal was to develop a solution that focuses on more CPU processing than on placing many complex sensors. This approach should reduce costs of both deployment and maintenance of such system. The proposed solution is to use video footage from a properly placed camera as input data. Vehicle movement is detected using optical flow algorithm. A great deal of post-processing is used to cope with problems that arise from this method of movement detection. Since the video of the entire crossroad is available, it is possible to fully analyse vehicle movement and produce turning movement counts and efficiently estimate (time varying) origin-destination trip tables if enough crossroads are monitored this way. The solution was developed in Simulink using Video and Image Processing Toolbox and custom blocks.