Performance Evaluation of a Visual Defects Detection System for Railways Monitoring
SNCF Réseau introduces a novel multi-modal embedded monitoring system, addressing challenges in railway infrastructure maintenance. The design incorporates visual, inertial, and sound sensors, enhancing adaptability, improving overall detection precision, and could reduce operational costs. This stu...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2024-01-01
|
| Series: | ITM Web of Conferences |
| Online Access: | https://www.itm-conferences.org/articles/itmconf/pdf/2024/12/itmconf_maih2024_03002.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841554734244167680 |
|---|---|
| author | Radosavljevic Saša Rivero Alain Rodríguez Flórez Sergio El Ouardi Abdelhafid Michel Pauline Bouamama Belkacem O. Vanheeghe Philippe |
| author_facet | Radosavljevic Saša Rivero Alain Rodríguez Flórez Sergio El Ouardi Abdelhafid Michel Pauline Bouamama Belkacem O. Vanheeghe Philippe |
| author_sort | Radosavljevic Saša |
| collection | DOAJ |
| description | SNCF Réseau introduces a novel multi-modal embedded monitoring system, addressing challenges in railway infrastructure maintenance. The design incorporates visual, inertial, and sound sensors, enhancing adaptability, improving overall detection precision, and could reduce operational costs. This study addresses visual defects detection that can be integrated in a multi-modal monitoring system. The paper details the system’s architecture, synchronisation methods, and decision fusion process to improve the precision of limited mono-modal systems. A deep-learning visual based railway defects inspection was explored. Results show that small CNN (Yolov8 nano) can achieve similar (Yolov8 XL) high precision (mAP@0.5 ≥ 0.89) for a small number of objects (9) while improving implementation capability on embedded systems. |
| format | Article |
| id | doaj-art-d086621d8f4f4ecc86421dfe78595d3f |
| institution | Kabale University |
| issn | 2271-2097 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | ITM Web of Conferences |
| spelling | doaj-art-d086621d8f4f4ecc86421dfe78595d3f2025-01-08T10:58:54ZengEDP SciencesITM Web of Conferences2271-20972024-01-01690300210.1051/itmconf/20246903002itmconf_maih2024_03002Performance Evaluation of a Visual Defects Detection System for Railways MonitoringRadosavljevic Saša0https://orcid.org/0009-0007-1223-8488Rivero Alain1https://orcid.org/0000-0003-1044-4337Rodríguez Flórez Sergio2https://orcid.org/0000-0003-3029-7020El Ouardi Abdelhafid3https://orcid.org/0000-0003-3665-2185Michel Pauline4https://orcid.org/0000-0002-9743-2402Bouamama Belkacem O.5https://orcid.org/0000-0002-7905-0734Vanheeghe Philippe6SNCF RéseauSNCF RéseauUniversité Paris-Saclay, ENS Paris-Saclay, CNRS, SATIEUniversité Paris-Saclay, ENS Paris-Saclay, CNRS, SATIEUniversité Paris-Saclay, ENS Paris-Saclay, CNRS, SATIEUniversité de Lille, CNRS, UMR 9189 - CRIStALUniversité de Lille, CNRS, UMR 9189 - CRIStALSNCF Réseau introduces a novel multi-modal embedded monitoring system, addressing challenges in railway infrastructure maintenance. The design incorporates visual, inertial, and sound sensors, enhancing adaptability, improving overall detection precision, and could reduce operational costs. This study addresses visual defects detection that can be integrated in a multi-modal monitoring system. The paper details the system’s architecture, synchronisation methods, and decision fusion process to improve the precision of limited mono-modal systems. A deep-learning visual based railway defects inspection was explored. Results show that small CNN (Yolov8 nano) can achieve similar (Yolov8 XL) high precision (mAP@0.5 ≥ 0.89) for a small number of objects (9) while improving implementation capability on embedded systems.https://www.itm-conferences.org/articles/itmconf/pdf/2024/12/itmconf_maih2024_03002.pdf |
| spellingShingle | Radosavljevic Saša Rivero Alain Rodríguez Flórez Sergio El Ouardi Abdelhafid Michel Pauline Bouamama Belkacem O. Vanheeghe Philippe Performance Evaluation of a Visual Defects Detection System for Railways Monitoring ITM Web of Conferences |
| title | Performance Evaluation of a Visual Defects Detection System for Railways Monitoring |
| title_full | Performance Evaluation of a Visual Defects Detection System for Railways Monitoring |
| title_fullStr | Performance Evaluation of a Visual Defects Detection System for Railways Monitoring |
| title_full_unstemmed | Performance Evaluation of a Visual Defects Detection System for Railways Monitoring |
| title_short | Performance Evaluation of a Visual Defects Detection System for Railways Monitoring |
| title_sort | performance evaluation of a visual defects detection system for railways monitoring |
| url | https://www.itm-conferences.org/articles/itmconf/pdf/2024/12/itmconf_maih2024_03002.pdf |
| work_keys_str_mv | AT radosavljevicsasa performanceevaluationofavisualdefectsdetectionsystemforrailwaysmonitoring AT riveroalain performanceevaluationofavisualdefectsdetectionsystemforrailwaysmonitoring AT rodriguezflorezsergio performanceevaluationofavisualdefectsdetectionsystemforrailwaysmonitoring AT elouardiabdelhafid performanceevaluationofavisualdefectsdetectionsystemforrailwaysmonitoring AT michelpauline performanceevaluationofavisualdefectsdetectionsystemforrailwaysmonitoring AT bouamamabelkacemo performanceevaluationofavisualdefectsdetectionsystemforrailwaysmonitoring AT vanheeghephilippe performanceevaluationofavisualdefectsdetectionsystemforrailwaysmonitoring |