INVAID TYPE B processor : the use of rule based techniques to detect traffic incidents from qualitative traffic data.

This paper describes the principal elements of the INVAID TYPE B processing module for high speed roads. In this context high speed roads are dual-carriageway, multi-lane highways where stopping is only permitted in emergencies, or only occurs as a direct consequence of an emergency or congestion. Permitted traffic speeds are normally greater than 100 km/h and intersections are grade-separated. The Type B processor is based upon a particular computer vision technique, IMPACTS, researched and developed at University College London, UK. The incoming surveillance camera images are processed to give a spatial description of some of the basic traffic characteristics. This description is of a qualitative nature and aims to reflect the behaviour of the traffic directly. It does not produce the classical measures of traffic flow, detector occupancy and speed which are found by aggregating data from vehicle detection. The spatial description output from the IMPACTS algorithm shows where within the image of the road there is moving, stationary and no traffic. The Type B processor takes this description and looks for features which indicate the presence of an incident. Information is also sought from any existing conventional detectors that may be within the field of view, and from a small database which contains information about the road and its environment. By combining this information, the robustness of the incident detection should be improved. The processor also checks its data internally to assess how much confidence can be placed in the output and to detect system errors at an early stage. The Type B processor is envisaged as being located at the instation, i.e. a control centre, with video images being transmitted from remote cameras. Multiple cameras would each have their own associated Type B process which would then be fed into the central system. The processor combines a number of sub-processes, each of which is described in this paper. The function of each sub-process is defined and its method of operation described. Some experiments based on video-recordings of different traffic scenarios are also reported.