Railway Driver Behavior Recognition System Based on Deep Learning Algorithm

For guaranteeing of train operation safety, driver's behavior should comply with the requirements of standardized operating procedures. If the driver is off duty, using mobile phone, failing to deal with commanded operation and other violations during the duty, it may cause a major driving accident. Based on artificial intelligence approaches such as object detection, human posture recognition, graph convolutional neural network, and embedded hardware equipment, this paper develops a intelligent recognition system for railway driving behavior, which is important for ensuring the safe operation of trains and promoting the development of intelligent management and control technologies in the railway industry.