Traffic monitoring with serial images from airborne cameras

The classical means to measure traffic density and velocity depend on local measurements from induction loops and other on site instruments. This information does not give the whole picture of the two-dimensional traffic situation. In order to obtain precise knowledge about the traffic flow of a large area, only airborne cameras or cameras positioned at very high locations (towers, etc.) can provide an up-to-date image of all roads covered. The paper aims at showing the potential of using image time series from these cameras to derive traffic parameters on the basis of single car measurements. To be able to determine precise velocities and other parameters from an image time series, exact geocoding is one of the first requirements for the acquired image data. The methods presented here for determining several traffic parameters for single vehicles and vehicle groups involve recording and evaluating a number of digital or analog aerial images from high altitude and with a large total field of view. Visual and automatic methods for the interpretation of images are compared. It turns out that the recording frequency of the individual images should be at least 1/3 Hz (visual interpretation), but is preferably 3 Hz or more, especially for automatic vehicle tracking. The accuracy and potentials of the methods are analyzed and presented, as well as the usage of a digital road database for improving the tracking algorithm and for integrating the results for further traffic applications. Shortcomings of the methods are given as well as possible improvements regarding methodology and sensor platform.