Road user behaviour analyses based on video detections: Status and best practice examples from the RUBA software

To a large extent, traffic safety improvements rely on reliable and full-covering accident registration. This is difficult to obtain in practice. Hence, surrogate measures as traffic conflict studies can contribute with more information. To make these studies more efficient, a software called RUBA has been developed. It works as a watchdog – if a passing road user affects defined part(s) of the video frame, RUBA records the time of the activity. It operates with three type of detectors (defined parts of the video frame): 1) if a road user passes the detector independent of the direction, 2) if a road user passes the area in one pre-adjusted specific direction and 3) if a road user is standing still in the detector area. Also, RUBA can be adjusted so it registers massive entities (e.g. cars) while less massive ones (e.g. cyclists) are not registered. The software has been used for various analyses of traffic behaviour: traffic counts with and without removal of different modes of transportation, traffic conflicts, traffic behaviour for specific traffic flows and modes and comparisons of speeds in rebuilt road areas. While there is still space for improvement regarding data treatment speed and user-friendliness, it is the conclusion that, at present, the RUBA software assists a number of traffic behaviour studies more efficiently and reliably than what is obtainable by human observers.