T 9903 , Task 75 Traffic Video — ITS Backbone VIDEO IMAGE PROCESSING TO CREATE A SPEED SENSOR

Image processing has been applied to traffic analysis in recent years, with different goals. In this report, a new approach is presented for extracting vehicular speed information, given a sequence of real-time traffic images. We extract moving edges and process the resulting edge information to obtain quantitative geometric measurements of vehicles. This differs from existing approaches because we use simple geometric relations obtained directly from the image instead of using reference objects to perform camera calibrations. Our method allows the recovery of the physical descriptions of traffic scenes without explicit camera calibration. In this report, extensive experiments using images from active TMS (Transportation Management System) freeway cameras are reported. The results presented in this report demonstrate the validity of our approach which requires neither direct camera control nor placement of a calibration object in the environment. We further argue that it is straightforward to extend our method to other related traffic applications.