Machine vision applications -  Successful examples from many industries


Successful examples from many industries

Industrial cameras improve track monitoring efficiency for London Underground

STEMMER IMAGING has worked closely with London Underground to develop and deliver 104 industrial camera assemblies that are mounted directly onto passenger trains to provide image data on the condition of the wheel/rail interface and the track itself. By acquiring this data during normal timetable periods, more time is available during the 4-hour night closure period to maintain the network’s 1000 km of track, minimising any disruption to services and helping to make the new weekend extended operating times possible.

The London Underground network, part of Transport for London, has implemented a new Automated Track Monitoring System which requires image data to be acquired from passenger trains. Specialist camera enclosures capable of operating in the harsh environmental conditions were developed with one type mounted on the bogey to provide information on the wheel-rail interface and the other mounted at the end of the carriage to provide a 4’ view of the running rails and conductor rails. The cameras are typically mounted on two trains operating on each line.

The enclosures supplied by STEMMER IMAGING are electrically isolated to protect from EMP spikes and certified to IP65. The sub-assemblies are shock rated to 5G for continuous load (shaking) and 50G for drop. Each camera enclosure contains a high speed Genie camera from Teledyne DALSA equipped with IR filter and capable of operating at 120 fps, an LED IR illumination source operating at 840 nm with integrated controller from Gardasoft, together with fibre optic triggering, and a power management and conditioning system.

By using high speed (40 µs) pulsed illumination, the relative movement between the cameras on the train and the track is eliminated ensuring high quality images are acquired. Triggering is controlled spatially so images are acquired at set distances apart. IR illumination was chosen to avoid interference from ambient light, particularly as a significant part of the rail network is above ground. In addition, because the light is rapidly pulsed, the use of IR illumination will not cause any problems for people nearby, especially those suffering from epilepsy or photosensitivity.

Image data is collected during the passenger train’s normal working hours and uploaded by wi-fi for analysis at night using data recording and image processing methods developed by London Underground. Image data can also be linked to data acquired from other sensors mounted on the train to show, for example, how track wear relates to ride quality.

Mark Williamson, Director – Corporate Market Development at STEMMER IMAGING, said:

“This was a challenging project where we were able to utilise our considerable experience in industrial imaging to ensure that the many critical requirements were achieved at the same time.

The use of very short IR light pulses with sufficient intensity to produce good images required extremely accurate lighting control. Naturally the camera enclosures underwent rigorous testing to ensure that they met all of the LUL safety certifications.”