Related Experiment Video
Updated: Jun 14, 2025
08:05
Design and Analysis for Fall Detection System Simplification
Published on: April 6, 2020
10.6K
Specifics of Data Collection and Data Processing during Formation of RailVista Dataset for Machine Learning- and Deep
Gulsipat Abisheva1, Nikolaj Goranin2, Bibigul Razakhova1
1Department of Artificial Intelligence Technology, Faculty of Information Technologies, L.N. Gumilyov Eurasian National University, Astana KZ-010000, Kazakhstan.
Sensors (Basel, Switzerland)
|August 29, 2024
Summary
A new dataset, Rail Vista, was created for railway track defect detection using machine learning. This high-quality dataset aids in developing automated systems for enhanced railway safety and maintenance.
Area of Science:
- Computer Vision
- Machine Learning
- Railway Engineering
Background:
- Automated defect detection is crucial for railway safety and maintenance.
- High-quality datasets are essential for training effective machine learning models.
Purpose of the Study:
- To introduce the Rail Vista dataset for railway track defect detection.
- To facilitate the development of advanced machine and deep learning models for railway infrastructure analysis.
Main Methods:
- Collected 200,000 high-resolution images of railway tracks.
- Categorized images into 19 distinct defect classes.
- Employed advanced image capture and distortion techniques for data enrichment.
- Stored data in a secure data warehouse using binary file formats.
Main Results:
- Developed the comprehensive Rail Vista dataset.
- The dataset supports training for diverse railway defect detection models.
- Demonstrated the dataset's utility in advancing automated railway inspection.
Conclusions:
- High-quality datasets are pivotal for machine learning in the railway sector.
- The Rail Vista dataset significantly contributes to automated defect recognition.
- Future work can leverage this dataset to improve railway safety and operational reliability.
