Bridge too far for reckless truck drivers as Cambridge tech hits fresh heights
Cambridge University engineers have developed an intelligent detection system to prevent bridge strikes by tall trucks.
Using computer vision technology, the system is able to detect – in advance – whether approaching vehicles are at risk of hitting a bridge. One calibrated camera per direction is mounted on the side of the road at the maximum-allowed bridge height looking across all lanes of traffic. From there, it uses the over-height plane concept (shown as a line in the camera view) to find over-height vehicles.
The new system is paired with an LED display unit downstream to warn drivers of the upcoming low bridge and suggesting they take the nearest road exit. If the driver continues and hits the bridge, accelerometers on the bridge structure will instruct the system to keep a copy of the most recent video feed as evidence and extract from it number plate information. The collision report containing all this information is then sent to the relevant authorities for action.
Amazingly, a tall truck hits a bridge every four-and-a-half hours in the UK, causing traffic chaos and costing thousands of pounds in repair and maintenance.
In the UK alone, there are more than 10,000 railway bridges crossing over roadways. Of these, 3,400 are considered to be ‘at risk’ due to a low clearance height. The average cost per bridge strike ranges from £5,000 to £25,000.
Engineering PhD alumnus, Dr Bella Nguyen, investigated how to detect and prevent bridge strikes, the results of which were the subject of a recent study for Transport for London (TfL), published in the Journal of Computing in Civil Engineering.
Dr Ioannis Brilakis, Laing O’Rourke Reader in Construction Engineering, said the new vision-based detection system was the result of a joint project with TfL with partial funding secured from the Centre for Smart Infrastructure and Construction (CSIC).
Dr Brilakis said: “Bridge collisions involving over-height vehicles lead to traffic delays, congestion and, in extreme cases, can derail trains and cause bridges to collapse.
“At the Construction Information Technology Laboratory we have created an autonomous system that bridge owners can use to reduce the number of strikes and charge offenders when damage is caused. The new system matches the performance of its predecessors at a fraction of the cost.”
Dr Nguyen added: “Using computer vision, we are now able to detect over-height vehicles and capture number plates from the same camera feed in variable weather conditions. We mount the camera at the clearance height to detect vehicles that exceed it and remove any false detections caused by environmental factors. This allows us to provide a personalised warning for drivers, enabling them to take the nearest exit and avoid hitting the bridge.”