Railway Intrusion Risk Quantification with Track Semantic Segmentation and Spatiotemporal Features

Shanping Ning ^1,2, Feng Ding ¹, Bangbang Chen ¹

⁰School of Mechatronic Engineering, Xi'an Technological University, Xi'an 710016, China.

Sensors (basel, Switzerland) +

|

September 13, 2025

View abstract on PubMed

Summary

This study introduces a new method for quantifying railway intrusion risks using AI-powered track segmentation and spatiotemporal analysis. It enhances train safety by providing data-driven, graded early warnings for potential threats.

Area Of Science

Artificial Intelligence
Railway Engineering
Computer Vision

Background

Foreign object intrusion in railway areas presents significant safety risks.
Current visual detection methods lack quantitative risk assessment capabilities.

Purpose Of The Study

To develop a railway intrusion risk quantification method integrating track semantic segmentation and spatiotemporal features.
To enhance train operation safety through quantitative risk assessment and graded early warnings.

Main Methods

Utilized an improved BiSeNetV2 network for accurate track region extraction.
Constructed physical-constrained risk zones based on railway structure gauge standards.
Developed a lightweight detection architecture with a Dilated Transformer module for improved accuracy, especially for small objects.
Integrated object category weights, lateral risk coefficients, longitudinal distance decay, and velocity compensation for comprehensive risk assessment.

Main Results

Achieved 84.9% mean average precision (mAP) on a proprietary dataset.
Outperformed baseline models by 3.3% in intrusion detection accuracy.
Demonstrated the capability for quantitative intrusion risk assessment and graded early warning.

Conclusions

The proposed method enables data-driven decision support for active train protection systems.
Significantly enhances intelligent railway safety protection capabilities by combining lateral distance detection with multidimensional risk indicators.

Keywords:

foreign object intrusion graded early warning lightweight network risk quantification assessment semantic segmentation spatiotemporal feature fusion