We developed AI object detection system for a public transportation system in Hong Kong.
The object detection system trigger an alarm when it detects tiny metal objects such as nails, screws, keys or coins appear at the escalator comb plate. Operation team could then remove the dangerous object before it jam into the running escalator. Thereby reducing maintenance cost, down time and potential accidents.
The solution consist of high resolution cameras, high performance edge computing device and a highly accurate deep learning model. It has been deployed and verified in multiple sites with an accuracy up to 98%.