Railway Track Monitoring Using Deep Learning Techniques: A Preview

Rail tracks are made up of various components. Maintenance of these components is crucial as it ensures the safety of passengers traveling in trains. The maintenance of the track and track components began with a manual system which involved human labor and was not reliable. Later, with new inventions in technology, railways all over the world were motivated to use smart devices for performing the task. Currently, in some countries, Deep Learning techniques are used to monitor and maintain the condition of rail tracks. Deep Learning techniques provide many benefits over other methods. This paper explores the research work where deep learning techniques are used to monitor and maintain rail track and its components. The various deep learning algorithms used for rail track monitoring includes: Convolutional Neural Network (CNN), Yolo V3, Deep Convolutional Network (DCN), Recurrent Neural Networks (RNNs), Long Short-Term Memory Networks (LSTMs), Stacked Auto-Encoders., Deep Boltzmann Machine (DBM), and Deep Belief Networks (DBN) and Many More by Using Deep Learning Techniques in Maintenance of Rail Track One Can Ensure Defect Free Components Thereby Safety of Rail Passengers