Method for railway driver behavior recognition based on CLSTA

Abstract

The invention discloses a method for railway driver behavior recognition based on CLSTA. A CLSTA neural network model is provided, and a CLSTA network is transplanted to an industrial computer. Locomotive driver's behavior is recognized and understood by monitoring video in a driver's room, and locomotive driver's driving behavior and driving state are monitored and intelligently evaluated in realtime. A convolution neural network CNN and a long-short memory neural network LSTM are used to learn spatial and time-order features of video images of the locomotive driver's behaviors. Consideringof single environment in the driver's room, body movements have little change for a whole scene, and aimed at the situation, an improved space-time attention method STA is provided. A neural network model is obtained by training a large number of data sets. Finally, the model is applied to the industrial computer to analyze common and abnormal behaviors of locomotive drivers during driving, such as fatigue driving, mobile phone playing, smoking and so on. Finally, a purpose of understanding locomotive drivers' behavior is achieved.

Description

technical field [0001] The invention relates to the technical field of railway traffic safety detection, in particular to a railway driver behavior recognition method based on CLSTA (ConvolutionalLSTM Networks With Spatial-Temporal Attention LSTM Convolutional Neural Network)). Background technique [0002] my country's railway construction is entering a period of high-speed development characterized by "leap-forward development", and locomotive operation safety technology has put forward higher requirements. How to ensure the smooth operation of locomotives has become the top priority of the railway transportation department, and it has become a top priority to improve and improve the monitoring and management level of the locomotive operation safety in the railway maintenance department. [0003] As we all know, in addition to sudden equipment failures such as axle cutting of locomotives, track breakage, etc., or natural disasters, the biggest threat to train operation saf...

AI Technical Summary

Problems solved by technology

[0004] my country's railway traffic safety monitoring has made great progress in recent years, but there is still a big gap compared with developed countries, mainly reflected in the accuracy and real-time monitoring of various information, and the lack of identification of the driver's personal working status. Alarm, the system function cannot meet the requirements, etc.

Images