Multi-Objective Performance Evaluation of the Detection of Catenary Support Components Using DCNNs

Conference paper (2018)

Authors

W. Liu Southwest Jiaotong University
Zhigang Liu Southwest Jiaotong University
Alfredo Nunez Railway Engineering - CEG
Liyou Wang Southwest Jiaotong University
Kai Liu Southwest Jiaotong University
Yang Lyu Southwest Jiaotong University
H. Wang Southwest Jiaotong University
Research Group
Railway Engineering (CEG) (TU Delft)
Copyright: © 2018 W. Liu, Zhigang Liu, Alfredo Nunez, Liyou Wang, Kai Liu, Yang Lyu, H. Wang
DOI
help_outline
https://doi.org/10.1016/j.ifacol.2018.07.017
Catenary Railway Systems Multi-Objective Performance Evaluation Deep convolutional neural networks (DCNNs
More Info
expand_more

Published Date

2018

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Civil Engineering & Geosciences

Department

Engineering Structures

Research Group

Railway Engineering

Abstract

The goal of this paper is to evaluate from a multi-objective perspective the performance on the detection of catenary support components when using state-of-the-art deep convolutional neural networks (DCNNs). The detection of components is the first step towards a complete automatized monitoring system that will provide actual information about defects in the catenary support devices. A series of experiments in an unified test environment for detection of components are performed using Faster-CNN, R-FCN, SSD, and YOLOv2. Through the comparison of different assessment indicators, such as precision, recall, average precision and mean average precision, the detection performance of the different DCNNs methods for the components of the catenary support devices is analyzed, discussed and evaluated. The experiment results show that among all considered methods, R-FCN is the more suitable for the detection of catenary support components.