Smart Platform Connectivity Interface: Train detection and Distance Prediction Using IoT And Machine Learning

Abstract

This research study proposes an intelligent IoT system interface to handle automated and motorized horizontal passenger transfers from one railway platform to another while increasing the overall efficiency of the railway systems. The proposed system employs NodeMCU as the main controller with a motorized rolling stage (interface) for motion control; various LEDs are used for displaying status and alarm signals and one screen display for displaying the incoming train information. Through computerized opening and closing of the platform edges, the passengers are able to have a smooth and secure passage between the platforms. The railway train detection module is implemented in Python with the help of OpenCV and YOLOv5 object detection model. The proposed design also accommodates wheelchair users by providing an accessible transfer platform and enhancing mobility and safety for all passengers. To enable the recognition of trains under diferent environmental conditions, a custom dataset of train images with annotations was developed specifically for training. When the approaching train is detected, the platform interface movement mechanism is activated, and the information on the display together with the signal lights is changed.