Skip to main content
Icons of Progress
 

The Management of Transportation Flow

IBM100 The Management of Transportation Flow iconic mark
 

It’s an issue in cities worldwide: too many cars. And Stockholm, Sweden, was no exception. In 2006, it launched an innovative road-charging system to reduce traffic and pollution.

IBM, as the prime contractor, designed, built and operated the technical operations that went into the traffic system. And the results were impressive and immediate: traffic was down nearly 25 percent, and train and transit passengers increased by 40,000 per day after the pilot project in 2006. After three years, the reduction in traffic wait time was 50%, 60,000 more passengers were taking public transit and vehicle emissions had dropped by 14 to 18 percent in the inner city. Many more Stockholm residents were combining auto use with extra walking and bicycling.

The smart traffic system IBM helped develop for Stockholm represented a new benchmark in scale, scope and sophistication at a time when other cities around the world—including London, Brisbane and Singapore—were developing their own solutions to manage congestion.

When the Swedish National Road Administration and the Stockholm City Council selected IBM to develop a traffic-charging system in the mid-2000s, traffic congestion had been a growing aggravation in Stockholm for years, with more than half a million cars traveling into the city every weekday. Congestion wasn’t going to get any better on its own. The population of Stockholm County was growing at a rate of around 20,000 people each year, which inevitably meant more traffic, and an even greater burden on city streets.

Simply building more roads wasn’t the answer—Stockholm is a city of islands linked by tunnels and bridges. Authorities in Stockholm had encouraged people to make greater use of public transportation, but still the bottlenecks got worse, especially at rush hour.

Stockholm officials decided that a road-charging scheme was the best solution—combined with park-and-ride services and improved transit options. They chose the IBM team to help develop a solution that could vary tolls by time and day to influence traffic patterns and congestion levels. Eighteen roadside control points located at Stockholm city entrances and exits were set up to identify and charge vehicles—higher fees during peak times; lower during off-peak hours.

Transponder tags installed in vehicles communicated with receivers at the control points and triggered automatic payment. Cars passing through these control points were photographed, and the license plate numbers were used to identify those vehicles without tags and to provide evidence to support the enforcement of non-payers. The information was sent to a computer system that matched the vehicle with its registration data, and a fee was charged to the owner. Drivers could then pay their bills at local banks, over the Internet and at area convenience stores.

The technologies at work included radio-frequency identification (RFID) tags and wireless sensors that can detect and measure real-world conditions and convert them into signals that are sent to computers.

Another emerging technology—optical character recognition software—was used to identify license plates from any angle. Because of varying degrees of illumination, bad weather and sometimes-awkward camera angles, not all license plates photographed by cameras at the roadside control points could be automatically identified by standard systems. IBM ® Research developed a sophisticated recognition system that used algorithms to make a second attempt at identifying unclear license plate images.

These algorithms use techniques such as image enhancement and comparison of front and back license plates to analyze the entire image and search for predefined patterns. Mimicking the human eye, the algorithms decipher images of often barely legible text by moving the image around until an optimal viewing angle is found, and the expected pattern can be recognized. After recognition, the system automatically records the license plate number, matches it with a vehicle registry database and processes billing.

Today, transponders are no longer required as the camera and optical recognition technology have evolved, and payment has been simplified with monthly invoicing.

The hope was that this pilot project, which ran for six months starting in January 2006, would encourage more people to leave their cars behind and use public transportation. The charge was also intended to bring about an overall improvement in the urban environment in Stockholm, particularly in air quality.

In the face of local skepticism and negative media coverage, the Swedish authorities decided to implement road pricing for six months—on a trial basis—and then allow citizens to decide through a referendum whether to make the system permanent.

When the trial ended, the results were so positive, the referendum passed. And the following year, the project was launched.

One of the challenges transportation agencies in many cities face is that, until recent years, there was no way to automate the use of the gigabytes of real-time traffic data being gathered every day. Often, by the time data was received and processed, it no longer presented an accurate picture of the state of the traffic.

But thanks to algorithms and analytics developed at IBM Research, along with a systematic approach to traffic management, these agencies can now visualize traffic patterns in newer, more effective ways.

Today, the benefits from the Stockholm congestion charging scheme are sustainable for the long-term, and similar projects are being planned for Gothenburg, the second largest city, as well as several other sites in Sweden.

 

The Team

Here are some of the IBMers who contributed to this Icon of Progress:

  • Gunnar Johansson Business development executive, IBM Public Sector Nordic
  • Miroslav Holecy Global CTO, IBM Intelligent Transport Systems
  • Ulrika Uhlman Senior project manager and practitioner manager
  • Anders Thornquist Executive IT architect, member of IBM Academy of Technology