Real-Time Pantograph Anomaly Detection Using Unsupervised Deep Learning and K-Nearest Neighbor Classification
- 27 February 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-13
Abstract
An image-based real-time pantograph anomaly detection method is presented by combining unsupervised deep learning and nearest neighbor classification. The proposed method includes the following key steps. Firstly, an improved DeblurGAN-v2 deblurring algorithm is applied to the input pantograph image if there exists motion blur. Next, deep learning semantic segmentation with hybrid coding that combines lightweight convolutional neural network (CNN) and vision transformer (VIT) is employed to accurately segment the pantograph structure within the image. And multi-scale feature-dense aggregation network based on an attentional feature fusion (AFF) module has been designed to efficiently integrate information from different feature layers. Finally, a K-nearest neighbor classification algorithm with deep pre-trained features from the segmented pantograph mask image has been utilized to detect anomalies in the pantograph. Experimental results demonstrate that the proposed pantograph segmentation network outperforms several general segmentation algorithms, achieving high MIoU of 95.86% with parameter size of 7M and FPS of 81.7. And nearest neighbor classification with deep pre-trained features achieves excellent pantograph anomaly detection performance with area under the receiver operating characteristic curve of 0.987 and area under precision-recall curve of 0.998. It is verified that the proposed pantograph anomaly detection method does not rely on abnormal data, and can achieve a high anomaly detection accuracy of 98.75%.Keywords
Funding Information
- Sichuan Science and Technology Program (2023NSFSC0463, 2023YFG0079)
- National Key Research and Development Program of China (2021ZD0109805)
This publication has 34 references indexed in Scilit:
- A Survey on Audio-Video Based Defect Detection Through Deep Learning in Railway MaintenanceIEEE Access, 2022
- Research on Fault Detection Algorithm of Pantograph Based on Edge Computing Image ProcessingIEEE Access, 2020
- Defect Detection of Pantograph Slider Based on Improved Faster R-CNN2019
- Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Images2019
- Review of pantograph and catenary interactionFrontiers of Mechanical Engineering, 2018
- Anomaly Detection in Vehicle Traffic with Image Processing and Machine LearningProcedia Computer Science, 2018
- Feature Pyramid Networks for Object Detection2017
- Deep Residual Learning for Image Recognition2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- A fast and robust image segmentation using FCM with spatial informationDigital Signal Processing, 2010