The state-of-art image segmentation algorithms can be applied to accurately localize objects by using deep convolutional neural networks (CNN). In this paper, we consider the anomaly detection problem encountered in a train wheel system. We propose a progressive approach to use a multi-target network to segment each component of the considered system sequentially by decoupling the segmentation and the classification task. Moreover, we use the knowledge graph approach to establish a semantic consistency matrix by quantifying the spatial relationship between various components. We show that by establishing a knowledge graph of the normally operating systems, we are able to identify a faulty component effectively.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Knowledge-Graph Based Multi-Target Deep-Learning Models for Train Anomaly Detection


    Contributors:


    Publication date :

    2018-12-01


    Size :

    1771225 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Rail surface anomaly detection based on deep learning

    Shi, Lei / Wu, Junjie / Sun, Yongkui | British Library Conference Proceedings | 2023


    Rail train anomaly detection method and system

    LI JUN / WANG XINYU / SONG YE | European Patent Office | 2015

    Free access

    Rail surface anomaly detection based on deep learning

    Shi, Lei / Wu, Junjie / Sun, Yongkui | SPIE | 2023


    Traffic flow anomaly detection method based on graph contrast learning network

    MA JIAMAN / WU YIZHENG / LUO XILING | European Patent Office | 2024

    Free access