Skip to main content

CMOS cameras used to create video pedestrian crossing

The city of Cologne, Germany has installed two CMOS-camera based video pedestrian light systems that will recognise waiting pedestrians and extend the green phase if there are still people crossing after the standard time allocation. The system, implemented by Siemens, uses two Flir cameras. The safe walk camera observes the waiting area. A stereo camera with two CMOS 1/3-inch mono sensors and 3 mm lenses is mounted 3.5 metres above the ground to cover an area of 12 sq m. This camera is set to recognise on
June 11, 2013 Read time: 2 mins
The city of Cologne, Germany has installed two CMOS-camera based video pedestrian light systems that will recognise waiting pedestrians and extend the green phase if there are still people crossing after the standard time allocation.

The system, implemented by 189 Siemens, uses two 6778 FLIR cameras. The safe walk camera observes the waiting area.  A stereo camera with two CMOS 1/3-inch mono sensors and 3 mm lenses is mounted 3.5 metres above the ground to cover an area of 12 sq m. This camera is set to recognise only objects with a height above 50 cm in order to eliminate shading and other distractions on the pavement.

C-walk – the second video system – uses a colour CMOS camera and recognises when not all pedestrians can cross in the minimum green period and sends a signal to the Siemens control unit in order to extend the green phase.

According to an article in Novus Light, the algorithms of the system also recognise the moving direction of pedestrians and can recognise those who only pass through the detection area. In this way, only people waiting at the light trigger a signal to the control unit of the pedestrian light, which, depending on the programming, starts a green phase at certain points in the current phase.

Dr Christoph Roth, product manager in the Road and City Mobility department at the Siemens Infrastructure and Cities Sector, says CMOS sensors were chosen because in traffic detection applications, they deliver more reliable images than CCD sensors and have a higher resistance to blooming from auto headlights at night.

For more information on companies in this article

Related Content

  • Safeguarding cities against wrong-way drivers
    June 10, 2024
    Thermal imaging and artificial intelligence analytics provide the best path towards preventing deadly auto accidents, explains Stefaan Pinck of Flir
  • The benefits of Lidar
    March 21, 2022

    While Lidar is gaining ground in the ITS industry, it has not yet reached the level of mass adoption where it shows up frequently in requests for proposals (RFPs) from cities and DoTs.

  • Daimler’s double take sees machine vision move in-vehicle
    December 13, 2013
    Jason Barnes looks at Daimler’s Intelligent Drive programme to consider how machine vision has advanced the state of the art of vision-based in-vehicle systems. Traditionally, radar was the in-vehicle Driver Assistance System (DAS) technology of choice, particularly for applications such as adaptive cruise control and pre-crash warning generation. Although vision-based technology has made greater inroads more recently, it is not a case of ‘one sensor wins’. Radar and vision are complementary and redundancy
  • In-vehicle intersection violation Warning system
    January 31, 2012
    Mike Schagrin, ITS Joint Program Office, RITA, and John Harding, NHTSA, describe US progress towards an in-vehicle Intersection Violation Warning system. In 2008, there were 37,261 fatalities on US roadways. Of these, 7,772, some 20.8 per cent of the total, were defined as intersection crashes or intersection-related crashes. Through a multi-agency research initiative led by the Research and Innovative Technology Administration (RITA), the US Department of Transportation (USDOT) has developed a prototype In