• V.Srikanth
• G.Aasritha
• G.AkshayaRani
• G.Lohitha
• K.Maruthi Surya Tarun

Train track infrastructure is crucial for maintaining the safety and efficiency of rail systems, yet traditional manual inspection methods are time-consuming and prone to human error. Recent advancements in machine learning, specifically Convolutional Neural Networks, have significantly improved the accuracy and speed of crack detection on tracks. However, for real-time anomaly detection and classification, further enhancements are necessary. This project proposes the integration of the You Only Look Once algorithm with neural networks to create a robust system capable of real-time crack classification on train tracks. Unlike existing CNN-based systems, which focus on detailed image analysis, the YOLO algorithm excels in fast object detection, enabling quicker recognition of track defects. By combining these approaches, the proposed system aims to enhance both the precision and speed of crack detection, making it highly suitable for real-time applications. To ensure reliability and robustness under various operational conditions, the system will be trained on a diverse dataset of track images captured in different environmental scenarios. This hybrid model is designed to optimize both the accuracy and efficiency of crack detection, facilitating faster response times and more reliable maintenance of rail infrastructure.

Train Track Infrastructure, Deep Learning, Convolutional Neural Networks, Crack Classification, Object Detection.

"Train Track Crack Classification using Convolutional Neural Network", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 3, page no.f136-f142, March-2025, Available :http://www.jetir.org/papers/JETIR2503543.pdf

"Train Track Crack Classification using Convolutional Neural Network", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 3, page no. ppf136-f142, March-2025, Available at : http://www.jetir.org/papers/JETIR2503543.pdf