The capability of a telematic vision system of estimating dimensions of vehicles is used for such tasks as vehicle classification or preselection of vehicles that violate local vehicle size limitations. Also in some European countries dimensions of heavy vehicles must obey some global regulations. Furthermore, vehicle size estimation allows us to determine the structure of traffic and can be very useful for advanced traffic flow control. Many existing Intelligent Transportation Systems consist of a large number of video cameras located in various places e.g., the ITS in Wrocław uses more than 1400 cameras. In this paper we propose a new method developed by the ArsNumerica Group and CyberTech Scientific Circle for the precise estimation of vehicle sizes using a single camera. The method does not require the entering of measurements such as the distance between lane lines or the height of the camera above the roadway. Only one vehicle’s dimensions are used for calibration. The proposed method is easy to implement and may be applied with the OpenCV library which is free both for academic and commercial use. The method is tested on real-world video streams. The obtained results are shown and analyzed in the paper.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.