Fast extraction of traffic parameters and reidentification of vehicles from video data

Abstract

Cities can be monitored using video cameras in order to extract traffic data. Besides the remote sensing data, stationary cameras fixed at high buildings can be used which provide data 24 hours a day, even when it is raining. Therefore, such data complement remote sensing data. The data can be used, e.g., to optimize traffic flow by controlling traffic lights dynamically. In case of stationary cameras, in order to minimize the number of cameras it is useful to reidentify vehicles leaving one monitored region and afterwards entering the viewing field of a further camera. From reidentified vehicles travel times can be obtained which are relevant parameters to optimize traffic control. A method to reidentify vehicles based on extraction of 3-d-prototype vehicle models and color extraction from the top plane of vehicles is presented. Shadows and light reflections on wet street are corrected, and therefore, the high recognition accuracy is achieved which is necessary to find the top plane of the vehicles. The algorithms are suitable for real-time applications. The methods can also be used for remote sensing data. Reidentification of vehicles in remote sensing data is of interest, because vehicles can get lost for a while, e.g., when high buildings prevent a direct view onto parts of the street.