A Survey on Audio-Video Based Defect Detection Through Deep Learning in Railway Maintenance
Within Artificial Intelligence, Deep Learning (DL) represents a paradigm that has been showing unprecedented performance in image and audio processing by supporting or even replacing humans in defect and anomaly detection. The railway sector is expected to benefit from DL applications, especially in...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9795283/ |
| _version_ | 1827348790745497600 |
|---|---|
| author | Lorenzo De Donato Francesco Flammini Stefano Marrone Claudio Mazzariello Roberto Nardone Carlo Sansone Valeria Vittorini |
| author_facet | Lorenzo De Donato Francesco Flammini Stefano Marrone Claudio Mazzariello Roberto Nardone Carlo Sansone Valeria Vittorini |
| author_sort | Lorenzo De Donato |
| collection | DOAJ |
| description | Within Artificial Intelligence, Deep Learning (DL) represents a paradigm that has been showing unprecedented performance in image and audio processing by supporting or even replacing humans in defect and anomaly detection. The railway sector is expected to benefit from DL applications, especially in predictive maintenance applications, where smart audio and video sensors can be leveraged yet kept distinct from safety-critical functions. Such separation is crucial, as it allows for improving system dependability with no impact on its safety certification. This is further supported by the development of DL in other transportation domains, such as automotive and avionics, opening for knowledge transfer opportunities and highlighting the potential of such a paradigm in railways. In order to summarize the recent state-of-the-art while inquiring about future opportunities, this paper reviews DL approaches for the analysis of data generated by acoustic and visual sensors in railway maintenance applications that have been published until August 31st, 2021. In this paper, the current state of the research is investigated and evaluated using a structured and systematic method, in order to highlight promising approaches and successful applications, as well as to identify available datasets, current limitations, open issues, challenges, and recommendations about future research directions. |
| first_indexed | 2024-03-08T00:17:24Z |
| format | Article |
| id | doaj.art-b415c665ef5e4952a6941bb5ff666d17 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-08T00:17:24Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-b415c665ef5e4952a6941bb5ff666d172024-02-17T00:00:08ZengIEEEIEEE Access2169-35362022-01-0110653766540010.1109/ACCESS.2022.31831029795283A Survey on Audio-Video Based Defect Detection Through Deep Learning in Railway MaintenanceLorenzo De Donato0https://orcid.org/0000-0003-4484-6318Francesco Flammini1https://orcid.org/0000-0002-2833-7196Stefano Marrone2https://orcid.org/0000-0001-6852-0377Claudio Mazzariello3https://orcid.org/0000-0001-9864-4610Roberto Nardone4https://orcid.org/0000-0003-4938-9216Carlo Sansone5https://orcid.org/0000-0002-8176-6950Valeria Vittorini6Department of Electrical Engineering and Information Technology, University of Naples Federico II, Naples, ItalyDepartment of Computer Science and Media Technology, Linnaeus University, Växjö, SwedenDepartment of Electrical Engineering and Information Technology, University of Naples Federico II, Naples, ItalyDigital and Data Driven Innovation Unit, Hitachi Rail STS, Naples, ItalyDepartment of Engineering, University of Naples “Parthenope”, Naples, ItalyDepartment of Electrical Engineering and Information Technology, University of Naples Federico II, Naples, ItalyDepartment of Electrical Engineering and Information Technology, University of Naples Federico II, Naples, ItalyWithin Artificial Intelligence, Deep Learning (DL) represents a paradigm that has been showing unprecedented performance in image and audio processing by supporting or even replacing humans in defect and anomaly detection. The railway sector is expected to benefit from DL applications, especially in predictive maintenance applications, where smart audio and video sensors can be leveraged yet kept distinct from safety-critical functions. Such separation is crucial, as it allows for improving system dependability with no impact on its safety certification. This is further supported by the development of DL in other transportation domains, such as automotive and avionics, opening for knowledge transfer opportunities and highlighting the potential of such a paradigm in railways. In order to summarize the recent state-of-the-art while inquiring about future opportunities, this paper reviews DL approaches for the analysis of data generated by acoustic and visual sensors in railway maintenance applications that have been published until August 31st, 2021. In this paper, the current state of the research is investigated and evaluated using a structured and systematic method, in order to highlight promising approaches and successful applications, as well as to identify available datasets, current limitations, open issues, challenges, and recommendations about future research directions.https://ieeexplore.ieee.org/document/9795283/Computer visionmachine learningfault detectioninspectionCNNsmart railways |
| spellingShingle | Lorenzo De Donato Francesco Flammini Stefano Marrone Claudio Mazzariello Roberto Nardone Carlo Sansone Valeria Vittorini A Survey on Audio-Video Based Defect Detection Through Deep Learning in Railway Maintenance IEEE Access Computer vision machine learning fault detection inspection CNN smart railways |
| title | A Survey on Audio-Video Based Defect Detection Through Deep Learning in Railway Maintenance |
| title_full | A Survey on Audio-Video Based Defect Detection Through Deep Learning in Railway Maintenance |
| title_fullStr | A Survey on Audio-Video Based Defect Detection Through Deep Learning in Railway Maintenance |
| title_full_unstemmed | A Survey on Audio-Video Based Defect Detection Through Deep Learning in Railway Maintenance |
| title_short | A Survey on Audio-Video Based Defect Detection Through Deep Learning in Railway Maintenance |
| title_sort | survey on audio video based defect detection through deep learning in railway maintenance |
| topic | Computer vision machine learning fault detection inspection CNN smart railways |
| url | https://ieeexplore.ieee.org/document/9795283/ |
| work_keys_str_mv | AT lorenzodedonato asurveyonaudiovideobaseddefectdetectionthroughdeeplearninginrailwaymaintenance AT francescoflammini asurveyonaudiovideobaseddefectdetectionthroughdeeplearninginrailwaymaintenance AT stefanomarrone asurveyonaudiovideobaseddefectdetectionthroughdeeplearninginrailwaymaintenance AT claudiomazzariello asurveyonaudiovideobaseddefectdetectionthroughdeeplearninginrailwaymaintenance AT robertonardone asurveyonaudiovideobaseddefectdetectionthroughdeeplearninginrailwaymaintenance AT carlosansone asurveyonaudiovideobaseddefectdetectionthroughdeeplearninginrailwaymaintenance AT valeriavittorini asurveyonaudiovideobaseddefectdetectionthroughdeeplearninginrailwaymaintenance AT lorenzodedonato surveyonaudiovideobaseddefectdetectionthroughdeeplearninginrailwaymaintenance AT francescoflammini surveyonaudiovideobaseddefectdetectionthroughdeeplearninginrailwaymaintenance AT stefanomarrone surveyonaudiovideobaseddefectdetectionthroughdeeplearninginrailwaymaintenance AT claudiomazzariello surveyonaudiovideobaseddefectdetectionthroughdeeplearninginrailwaymaintenance AT robertonardone surveyonaudiovideobaseddefectdetectionthroughdeeplearninginrailwaymaintenance AT carlosansone surveyonaudiovideobaseddefectdetectionthroughdeeplearninginrailwaymaintenance AT valeriavittorini surveyonaudiovideobaseddefectdetectionthroughdeeplearninginrailwaymaintenance |