AI Driven Railway Track Crack Detection And Classification With YOLOV

Abstract: The Railway Track Crack Detection system is an intelligent deep learning–based solution designed to automatically detect cracks and defects in railway tracks using image data. The system utilizes advanced computer vision techniques and the YOLOv5 object detection model to identify crack regions with high accuracy and speed. It integrates data collection, preprocessing, image annotation using tools like LabelImg, model training, testing, and real-time detection into a unified workflow. The trained model detects cracks in input images by generating bounding boxes along with confidence scores, enabling clear visualization of defects. The system also includes performance evaluation, parameter tuning, and optimization to improve accuracy and reduce false detections. In addition, it supports real-time monitoring through continuous analysis of images or video frames, making it suitable for practical railway inspection scenarios. Compared to traditional manual inspection methods, this approach reduces human effort, minimizes errors, and enables early detection of potential failures. By leveraging deep learning and object detection techniques, the project provides a cost-effective, scalable, and efficient solution for improving railway safety and maintenance.

Keywords: Railway Track Crack Detection, YOLOv5, Deep Learning, Computer Vision, Object Detection, Image Processing, Defect Detection, Real-Time Monitoring, Railway Safety, Predictive Maintenance