Preventing bicycle theft -- and public safety

Published 3 January 2008

A graduate engineering student at Leeds University develops a clever video analytic tool to help cut down the number of bicycles being stolen in the U.K. every year (currently, 500,000 bicycles); tool can also be used for other public safety missions

One of the iconic movies of the post-Second World War Italian school of artistic realism is Vittorio De Sica’s “Ladri di biciclette” (Bicycle Thieves). It tells the story of Antonio Ricci, a poor man searching the streets of Rome for his stolen bicycle, which he needs to be able to work. Ricci would have benefitted from this new video analytic tool being developed at Leeds University, as it could put the brakes on bicycle thieves and may also be useful in flagging suspicious events in public places. Ph.D. student Dima Damen, from the University’s Faculty of Engineering, has developed a computer system which detects individuals parking their bicycles and can automatically warn security staff if it appears that someone other than the owner retrieves the vehicle. “It’s difficult to monitor CCTV cameras, as operators normally have a large number of screens to watch,” says Damen. “This often results in bicycle thefts being missed, even if they are happening right in front of the camera.”

More than 500,000 bicycles are stolen annually in the United Kingdom and only 5 percent of these are returned to their owners. The increase in the number of people traveling by bicycle as an more eco-friendly method of transport has provided greater opportunities for bicycle thieves across the United Kingdom. Many local councils have located CCTV cameras above public bicycle racks, but their effectiveness in deterring thieves is limited. Currently at prototype stage, Damen’s system takes color information from CCTV images when a bike is parked and stores it until the bike is retrieved. It then marries the stored information with the new image and where there are significant differences, it can raise an alert to CCTV operators. In initial tests using a camera located above a bike rack at the University of Leeds, eleven out of thirteen simulated thefts were detected. “Without a system like this, the benefit of CCTV cameras is diminished by the difficulties of manual monitoring,” said Damen. “It’s a simple solution to an extremely widespread problem.”

Damen is now developing her technology to identify suspicious events in public places, such as the problem of baggage — especially in airports. “Someone intending to leave a suspicious package won’t leave it in full view of a CCTV camera, but may choose to leave it in a toilet or behind a pillar,” said Damen. “We think we can engineer this technology to recognise people who enter ‘flagged’ areas with a package or bag, but then leave without it, raising an alert for security staff. That’s my next challenge.”