Attention Network for Rail Surface Defect Detection via Consistency of Intersection-over-Union(IoU)-Guided Center-Point Estimation

Rail surface defect inspection based on machine vision faces challenges against the complex background with interference and severe data imbalance. To meet these challenges, in this article, we regard defect detection as a key-point estimation problem and present the proposed attention neural networ...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on industrial informatics 2022-03, Vol.18 (3), p.1694-1705
Main Authors: Ni, Xuefeng, Ma, Ziji, Liu, Jianwei, Shi, Bo, Liu, Hongli
Format: Article
Language:English
Subjects:
Attention
Consistency
convolutional neural network
Estimation
Feature extraction
Informatics
Inspection
Intersections
key-point estimation
Machine vision
Modules
multilevel feature fusion
Neural networks
rail surface defects
Rail transportation
Rails
Scale (ratio)
Surface defects
Surface morphology
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Rail surface defect inspection based on machine vision faces challenges against the complex background with interference and severe data imbalance. To meet these challenges, in this article, we regard defect detection as a key-point estimation problem and present the proposed attention neural network for rail surface defect detection via consistency of Intersection-over-Union(IoU)-guided center-point estimation (CCEANN). The CCEANN contains two crucial components. The two components are the stacked attention Hourglass backbone via cross-stage fusion of multiscale features (CSFA-Hourglass) and the CASIoU-guided center-point estimation head module (CASIoU-CEHM). Furthermore, the CASIoU-guided center-point estimation head module integrating the delicate coordinate compensation mechanism regresses detection boxes flexibly to adapt to defects' large-scale variation, in which the proposed CASIoU loss, a loss regressing the consistency of intersection-over-union (IoU), central-point distance, area ratio, and scale ratio between the targeted defect and the predicted defect, achieves higher regression accuracy than state-of-the-art IoU-based losses. The experiments demonstrate that the CCEANN outperforms competitive deep learning-based methods in four surface defect datasets.
ISSN:1551-3203
1941-0050
DOI:10.1109/TII.2021.3085848