Search research articles

Related Concept Videos

Selected Data About Geographic Locations

Selected Data About Geographic Locations

Geographic Information Systems (GIS) rely on two core types of data: spatial data and attribute data.Spatial DataSpatial data defines the physical location of features within a coordinate system, typically expressed in terms of latitude and longitude. It provides precise positioning for elements like roads, rivers, or buildings.Attribute DataAttribute data complements spatial data by adding descriptive information about these features. For example, a road's spatial data includes its start and...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Quantification of brominated flame retardants in soil.

Journal of veterinary research·2026

Same author

The comparative analysis of selected interleukins and proinflammatory factors in CSF among de novo diagnosed patients with RRMS.

Clinical neurology and neurosurgery·2023

Same author

Outcomes of the two generations of bioresorbable scaffolds (Magmaris vs. Absorb) in acute coronary syndrome in routine clinical practice.

Cardiology journal·2022

Same author

Sex Differences in the Clinical Features and Outcomes of Patients with Acute Coronary Syndrome Treated with Two Generations (Absorb and Magmaris) of Bioresorbable Vascular Scaffolds.

Journal of clinical medicine·2021

Same author

Multiple sclerosis immunomodulatory therapies tested for effectiveness in COVID-19.

Neurologia i neurochirurgia polska·2021

Same author

The 1-Year Safety and Efficacy Outcomes of Magmaris, Novel Magnesium Bioresorbable Vascular Scaffolds in Diabetes Mellitus Patients with Acute Coronary Syndrome.

Journal of clinical medicine·2021

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jul 15, 2025

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

Seeking a Sufficient Data Volume for Railway Infrastructure Component Detection with Computer Vision Models.

Alicja Gosiewska¹, Zuzanna Baran¹, Monika Baran¹

¹Nevomo IoT, 03-828 Warsaw, Poland.

Sensors (Basel, Switzerland)

|September 28, 2023

Summary

Machine learning models for railway infrastructure monitoring can be trained with limited data. A novel background extraction method further reduces the required observations for accurate object detection.

Keywords:

computer vision machine learning object detection railway

More Related Videos

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging

Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging

Published on: April 18, 2025

Related Experiment Videos

Last Updated: Jul 15, 2025

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging

Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging

Published on: April 18, 2025

Area of Science:

Artificial Intelligence
Civil Engineering
Transportation Systems

Background:

Railway infrastructure monitoring is vital for safety and reliability but is labor-intensive and costly.
Current monitoring methods are limited by human efficiency and the availability of labeled data for machine learning.
Machine learning offers a faster, cost-effective, and reproducible alternative for infrastructure evaluation.

Purpose of the Study:

To investigate the feasibility of training machine learning models for railway infrastructure monitoring with limited data.
To develop and evaluate a novel method for background image extraction to improve model training efficiency.
To compare the performance of YOLOv5 and MobileNet architectures in low-data scenarios.

Main Methods:

Training YOLOv5 and MobileNet object-detection architectures on small datasets.
Implementing a novel background image extraction technique for railway imagery.
Comparing model performance with and without background extraction using limited observations.

Main Results:

Accurate object detection models for railway infrastructure can be trained with as few as 120 observations.
The proposed background extraction method further reduces the required data volume to 90 observations.
Both YOLOv5 and MobileNet demonstrated effectiveness in low-data scenarios, enhanced by background extraction.

Conclusions:

Machine learning, particularly with background extraction, significantly reduces data requirements for railway infrastructure monitoring.
This approach enhances the feasibility of implementing AI for cost-effective and efficient railway safety and reliability.
The findings pave the way for more accessible and scalable automated railway inspection systems.