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.
Original language | English |
---|---|
Title of host publication | Proceedings of 15th IFAC Symposium on Control in Transportation Systems (CTS 2018) |
Subtitle of host publication | Savona, Italy, June 6-8, 2018 |
Editors | Bart De Schutter , Antonella Ferrara |
Pages | 98-105 |
Number of pages | 8 |
Volume | 51 |
Edition | 9 |
DOIs | |
Publication status | Published - 2018 |
Event | 15th IFAC Symposium on Control in Transportation Systems - Savona, Italy Duration: 6 Jun 2018 → 8 Jun 2018 Conference number: 15 http://www.cts2018.unige.it/ |
Publication series
Name | IFAC-PapersOnLine |
---|---|
Publisher | Elsevier |
Number | 9 |
Volume | 51 |
ISSN (Print) | 2405-8963 |
Conference
Conference | 15th IFAC Symposium on Control in Transportation Systems |
---|---|
Abbreviated title | CTS 2018 |
Country/Territory | Italy |
City | Savona |
Period | 6/06/18 → 8/06/18 |
Internet address |
Keywords
- Catenary
- Railway Systems
- Multi-Objective Performance Evaluation
- Deep convolutional neural networks (DCNNs