Search research articles

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

Related Concept Videos

You might also read

Related Articles

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

Sort by

Same author

Transcriptomic Analysis Reveals Resistance Mechanisms of Pecan (<i>Carya illinoinensis</i>) to <i>Colletotrichum fructicola</i> and Characterization of a Novel Resistance-Related Gene <i>CiCP12</i>.

Journal of agricultural and food chemistry·2026

Same author

Cytokine Profiling for the Prediction of Lethality and High-Dose Exposure in a Murine Partial Body Irradiation Model.

International journal of molecular sciences·2026

Same author

3D-guided planning enhances safety of laparoscopic resection for special liver segments: A propensity score-matched study.

American journal of surgery·2026

Same author

Characterization of Carbapenem-Resistant <i>Klebsiella pneumoniae</i> in a Tertiary Hospital in the Eastern Coastal Region of Zhejiang, China: Detection of a Novel ST6853 Clone.

Infection and drug resistance·2026

Same author

Monocyte Immunometabolic Axis Linking Type 2 Diabetes to Coronary Artery Disease Revealed by Multi-Omics Integration and Mendelian Randomization.

Circulation journal : official journal of the Japanese Circulation Society·2026

Same author

Pre-Exposure Prophylaxis with Vasculotide Enhances Survival and Alleviates Hematopoietic and Gastrointestinal Injury Following Lethal Total Body Irradiation.

International journal of molecular sciences·2026

Search research articles

Related Experiment Video

Updated: Jun 12, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Foreign object detection in urban rail transit based on deep differentiation segmentation neural network.

Feigang Tan^1,2, Min Zhai³, Cong Zhai⁴

¹School of Traffic and Environment, Shenzhen Institute of Information Technology, Shenzhen, 518172, China.

|September 19, 2024

Summary

A new video-based deep learning system accurately detects foreign objects on urban rail transit platforms, improving safety. This foreign object detection method achieves 95.8% accuracy, outperforming existing technologies.

Keywords:

Deep neural network Differential network Foreign object detection Seam foreign object

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Related Experiment Videos

Last Updated: Jun 12, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Area of Science:

Computer Science
Artificial Intelligence
Transportation Engineering

Background:

Foreign object intrusion is a major safety risk in urban rail transit operations.
Laser-based detection systems have limitations including blind spots and poor visualization.
Existing methods struggle with accuracy and environmental factors.

Purpose of the Study:

To develop a novel video-based deep differentiation segmentation neural network for foreign object detection.
To overcome the limitations of laser-based detection systems in urban rail transit.
To enhance operational safety and efficiency in rail transit environments.

Main Methods:

Transformed foreign object detection into a binary classification problem using image segmentation.
Developed a deep convolutional segmentation network incorporating channel and spatial attention models.
Implemented background image averaging to mitigate airflow disturbance and refined results with morphological operations and thresholding.

Main Results:

Achieved a foreign object detection accuracy of 95.8% on real subway platform data.
Demonstrated superior performance compared to traditional detection methods.
Outperformed recent image segmentation neural networks in foreign object detection.

Conclusions:

The proposed video-based deep segmentation network offers a highly accurate and effective solution for foreign object detection in urban rail transit.
This method significantly improves upon the limitations of existing laser-based systems.
The enhanced deep learning approach contributes to safer and more reliable rail transit operations.