INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2456-4184 | Impact factor: 8.76 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.76 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
Railway track crack detection is a critical aspect of railway infrastructure maintenance, aimed at ensuring passenger and freight safety and preventing potential accidents. The railway department is implementing several creative approaches to improve the efficiency of the inspection procedure. Various technologies, such as the Computer Vision-Based method, have been investigated in the past to detect defects on rail surfaces, but complete automation is still a long way off. Few countries utilize Deep Learning algorithms to monitor and manage the condition of train rails. This project presents a Fault detection system based on machine learning, computer vision and Image Classification based techniques to automate the process of detecting cracks in railway tracks. The methodology involves Transfer Learning using VGG19 and the collection of a diverse dataset of annotated railway track images, including both defective (cracked) and non-defective (crack-free) samples. The Images are pre-processed using various pre-processing techniques and then Machine learning algorithms are applied to train a model on this pre-processed dataset, enabling it to distinguish between defective and non-defective tracks. The proposed system offers several advantages, including early detection of cracks, reduced maintenance costs, and improved safety measures. By automating the crack detection process, the system minimizes the need for manual inspections and enables timely maintenance actions. The results demonstrate the effectiveness of the fault detection system in accurately identifying cracks on railway tracks, thereby contributing to enhanced railway safety and efficient maintenance practices. The results later are compared with RESNET50 and GoogleNet models, to understand which model gives more accurate results. The successful implementation of this system can lead to significant improvements in railway infrastructure management and overall transportation safety.
IndexTerms - Computer Vision, Transfer Learning, Machine Learning, Image Processing, Image Classification.
Keywords:
Computer Vision, Transfer Learning, Machine Learning, Image Processing, Image Classification.
Cite Article:
"FAULT DETECTION IN RAILWAY TRACKS USING IMAGE CLASSIFICATION ", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.8, Issue 11, page no.c518-c539, November-2023, Available :http://www.ijnrd.org/papers/IJNRD2311265.pdf
Downloads:
000118765
ISSN:
2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Facebook Twitter Instagram LinkedIn