Robust Tram Speed Alert System

I&T Solution Robust Tram Speed Alert System
(REF : S-0971)
Trial Project
Solution Feature
  • Video camera captures the tram speed from the tram’s speedometer
  • Video footages of tram’s speedometer are converted to images to be processed by the image recognition program on the computer installed next to the tram driver
  • A speedometer’s image is analysed by a convolutional neural network on the tram’s computer to extract the speedometer’s reading to compute the current tram speed (e.g. 20km/h)
  • Tram’s location is detected by a GPS device on the tram, which is compared to the road map to find out the speed limit of the tram’s current location
  • If the tram exceeds the pre-set speed limit, the computer will make the alarm sound, and send the tram’s location, tram’s speed, and speeding alert to Operations Control Centre of Tramways via wireless communication
Trial Application and Expected Outcome
  • Creating image recognition program for speedometer readings on two computers: for each server, build the recognition program by learning a convolutional neural network from speedometer images
  • Installing and testing speedometer recognition systems (SRS) on two trams in the route between Shau Kei Wan and Happy Valley: set up camera pointing at tram’s speedometer, and computers (one month); deploy SRS's (four months); check for errors from computer’s logs and fix any errors
  • Training and real-life testing: train tram drivers to respond to alert signals produced by a SRS; let tram drivers use SRS for ten months; collect survey results from tram drivers on their experience of using a SRS
  • Evaluating real-life trials and updating speedometer recognition system: estimate the range of drivers' reaction time from the survey results; collect relevant diagnostic data from survey results; update a SRS using diagnostic data, e.g. re-compute the threshold for sounding an alarm. (3 months)
  • Expected Outcomes: two trams in the route connecting Shau Kei Wan and Happy Valley will successfully be installed with a SRS for prevention of tram speeding; two tram drivers will have been trained to use a SRS to assist in their driving
Info on I&T Solution Provider
Address:Rm 2, 7/F., Block B, Mai Hing Industrial Building, 16-18 Hing Yip Street, Kwun Tong, Kowloon, Hong Kong
Contact Person:ALEX MAR
Tel: +852-9512-0604

For details of the above I&T solution, please contact the I&T solution provider.