Investigation on optimal detection position of DC electromagnetic NDT in crack characterization for high-speed rail track

Yuan, Fei; Yu, Yating; Liu, Bowen; Li, Linfeng

doi:10.1109/i2mtc.2019.8827153

Cited by 6 publications

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to prevent accidents and ensure the smooth operation of trains, various methods of defect detection are employed. These methods range from visual inspections [ 1 ] to such technologies as ultrasonic [ 2 ] and electromagnetic testing [ 3 ] and are a part of a vast problematic of defect detection [ 4 ]. With the increasing demand for faster and more efficient rail transportation, the traditional methods are often unable to deliver accurate results while the train is running on the tracks.…”

Section: Introductionmentioning

confidence: 99%

A Hybrid System for Defect Detection on Rail Lines through the Fusion of Object and Context Information

Zhukov,

Rivero,

Benois-Pineau

et al. 2024

Sensors

View full text Add to dashboard Cite

Defect detection on rail lines is essential for ensuring safe and efficient transportation. Current image analysis methods with deep neural networks (DNNs) for defect detection often focus on the defects themselves while ignoring the related context. In this work, we propose a fusion model that combines both a targeted defect search and a context analysis, which is seen as a multimodal fusion task. Our model performs rule-based decision-level fusion, merging the confidence scores of multiple individual models to classify rail-line defects. We call the model “hybrid” in the sense that it is composed of supervised learning components and rule-based fusion. We first propose an improvement to existing vision-based defect detection methods by incorporating a convolutional block attention module (CBAM) in the you only look once (YOLO) versions 5 (YOLOv5) and 8 (YOLOv8) architectures for the detection of defects and contextual image elements. This attention module is applied at different detection scales. The domain-knowledge rules are applied to fuse the detection results. Our method demonstrates improvements over baseline models in vision-based defect detection. The model is open for the integration of modalities other than an image, e.g., sound and accelerometer data.

show abstract