Application of Computer Vision and Deep Learning in the railway domain for autonomous train stop operation

Mikel Etxeberria-Garcia; Mikel Labayen; Maider Zamalloa; Nestor Arana-Arexolaleiba

doi:10.1109/SII46433.2020.9026246

Application of Computer Vision and Deep Learning in the railway domain for autonomous train stop operation

Mikel Etxeberria-Garcia, Mikel Labayen, Maider Zamalloa, Nestor Arana-Arexolaleiba

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

13 Citations (Scopus)

Abstract

The purpose of this paper is to present the results of the analysis of the application of Deep Learning in the railway domain with a particular focus on a train stop operation. The paper proposes an approach consisting of monocular vision-based and Deep Learning architectures. Even the difficulties imposed by actual regulation, the findings show that Deep Learning architecture can offer promising results in railway localization using techniques like visual odometry, SLAM or pose estimation. Besides, in spite of the many datasets available in the literature needed to train the neural network, none of them have been created for indoor railway environments. Therefore, a new dataset should be created. Furthermore, the paper presents future research and development suggestions for railway applications which contribute to guiding the mid-term research and development.

Original language	English
Title of host publication	Proceedings of the 2020 IEEE/SICE International Symposium on System Integration, SII 2020
Number of pages	6
Publisher	IEEE Signal Processing Society
Publication date	Jan 2020
Pages	943-948
Article number	9026246
ISBN (Electronic)	9781728166674
DOIs	https://doi.org/10.1109/SII46433.2020.9026246
Publication status	Published - Jan 2020
Event	2020 IEEE/SICE International Symposium on System Integration, SII 2020 - Honolulu, United States Duration: 12 Jan 2020 → 15 Jan 2020

Conference

Conference	2020 IEEE/SICE International Symposium on System Integration, SII 2020
Country/Territory	United States
City	Honolulu
Period	12/01/2020 → 15/01/2020

Series	Proceedings of the 2020 IEEE/SICE International Symposium on System Integration, SII 2020

Bibliographical note

Funding Information:
1Ikerlan Technology Research Centre, Dependable Embedded Systems Area, P. J. M. Arizmendiarrieta, 2 20500 Arrasate-Mondragon, Gipuzkoa, Spain {mikel.etxeberria, mzamalloa}@ikerlan.es 2Faculty of Informatics, UPV/EHU, Manuel Lardizabal Ibilbidea, 1, 20018 Donostia, Gipuzkoa, Spain mikel.labayen@ehu.eus 3MGEP, Mondragon Unibertsitatea, Loramendi Kalea, 4 20500 Arrasate-Mondragon Gipuzkoa, Spain narana@mondragon.edu This research is supported by Basque Government through BIKAIN-TEK2018 program and CAF Signalling. In collaboration between Ikerlan, CAF Signalling and Mondragon Unibertsitatea.

Publisher Copyright:
© 2020 IEEE.

Access to Document

10.1109/SII46433.2020.9026246

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

Etxeberria-Garcia, M., Labayen, M., Zamalloa, M., & Arana-Arexolaleiba, N. (2020). Application of Computer Vision and Deep Learning in the railway domain for autonomous train stop operation. In Proceedings of the 2020 IEEE/SICE International Symposium on System Integration, SII 2020 (pp. 943-948). Article 9026246 IEEE Signal Processing Society. https://doi.org/10.1109/SII46433.2020.9026246

Etxeberria-Garcia, Mikel ; Labayen, Mikel ; Zamalloa, Maider et al. / Application of Computer Vision and Deep Learning in the railway domain for autonomous train stop operation. Proceedings of the 2020 IEEE/SICE International Symposium on System Integration, SII 2020. IEEE Signal Processing Society, 2020. pp. 943-948 (Proceedings of the 2020 IEEE/SICE International Symposium on System Integration, SII 2020).

@inproceedings{53ea33616a514057ad19dec2e992565d,

title = "Application of Computer Vision and Deep Learning in the railway domain for autonomous train stop operation",

abstract = "The purpose of this paper is to present the results of the analysis of the application of Deep Learning in the railway domain with a particular focus on a train stop operation. The paper proposes an approach consisting of monocular vision-based and Deep Learning architectures. Even the difficulties imposed by actual regulation, the findings show that Deep Learning architecture can offer promising results in railway localization using techniques like visual odometry, SLAM or pose estimation. Besides, in spite of the many datasets available in the literature needed to train the neural network, none of them have been created for indoor railway environments. Therefore, a new dataset should be created. Furthermore, the paper presents future research and development suggestions for railway applications which contribute to guiding the mid-term research and development.",

author = "Mikel Etxeberria-Garcia and Mikel Labayen and Maider Zamalloa and Nestor Arana-Arexolaleiba",

note = "Funding Information: 1Ikerlan Technology Research Centre, Dependable Embedded Systems Area, P. J. M. Arizmendiarrieta, 2 20500 Arrasate-Mondragon, Gipuzkoa, Spain {mikel.etxeberria, mzamalloa}@ikerlan.es 2Faculty of Informatics, UPV/EHU, Manuel Lardizabal Ibilbidea, 1, 20018 Donostia, Gipuzkoa, Spain mikel.labayen@ehu.eus 3MGEP, Mondragon Unibertsitatea, Loramendi Kalea, 4 20500 Arrasate-Mondragon Gipuzkoa, Spain narana@mondragon.edu This research is supported by Basque Government through BIKAIN-TEK2018 program and CAF Signalling. In collaboration between Ikerlan, CAF Signalling and Mondragon Unibertsitatea. Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE/SICE International Symposium on System Integration, SII 2020 ; Conference date: 12-01-2020 Through 15-01-2020",

year = "2020",

month = jan,

doi = "10.1109/SII46433.2020.9026246",

language = "English",

series = "Proceedings of the 2020 IEEE/SICE International Symposium on System Integration, SII 2020",

pages = "943--948",

booktitle = "Proceedings of the 2020 IEEE/SICE International Symposium on System Integration, SII 2020",

publisher = "IEEE Signal Processing Society",

address = "United States",

}

Etxeberria-Garcia, M, Labayen, M, Zamalloa, M & Arana-Arexolaleiba, N 2020, Application of Computer Vision and Deep Learning in the railway domain for autonomous train stop operation. in Proceedings of the 2020 IEEE/SICE International Symposium on System Integration, SII 2020., 9026246, IEEE Signal Processing Society, Proceedings of the 2020 IEEE/SICE International Symposium on System Integration, SII 2020, pp. 943-948, 2020 IEEE/SICE International Symposium on System Integration, SII 2020, Honolulu, United States, 12/01/2020. https://doi.org/10.1109/SII46433.2020.9026246

Application of Computer Vision and Deep Learning in the railway domain for autonomous train stop operation. / Etxeberria-Garcia, Mikel; Labayen, Mikel; Zamalloa, Maider et al.
Proceedings of the 2020 IEEE/SICE International Symposium on System Integration, SII 2020. IEEE Signal Processing Society, 2020. p. 943-948 9026246 (Proceedings of the 2020 IEEE/SICE International Symposium on System Integration, SII 2020).

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - Application of Computer Vision and Deep Learning in the railway domain for autonomous train stop operation

AU - Etxeberria-Garcia, Mikel

AU - Labayen, Mikel

AU - Zamalloa, Maider

AU - Arana-Arexolaleiba, Nestor

N1 - Funding Information: 1Ikerlan Technology Research Centre, Dependable Embedded Systems Area, P. J. M. Arizmendiarrieta, 2 20500 Arrasate-Mondragon, Gipuzkoa, Spain {mikel.etxeberria, mzamalloa}@ikerlan.es 2Faculty of Informatics, UPV/EHU, Manuel Lardizabal Ibilbidea, 1, 20018 Donostia, Gipuzkoa, Spain mikel.labayen@ehu.eus 3MGEP, Mondragon Unibertsitatea, Loramendi Kalea, 4 20500 Arrasate-Mondragon Gipuzkoa, Spain narana@mondragon.edu This research is supported by Basque Government through BIKAIN-TEK2018 program and CAF Signalling. In collaboration between Ikerlan, CAF Signalling and Mondragon Unibertsitatea. Publisher Copyright: © 2020 IEEE.

PY - 2020/1

Y1 - 2020/1

N2 - The purpose of this paper is to present the results of the analysis of the application of Deep Learning in the railway domain with a particular focus on a train stop operation. The paper proposes an approach consisting of monocular vision-based and Deep Learning architectures. Even the difficulties imposed by actual regulation, the findings show that Deep Learning architecture can offer promising results in railway localization using techniques like visual odometry, SLAM or pose estimation. Besides, in spite of the many datasets available in the literature needed to train the neural network, none of them have been created for indoor railway environments. Therefore, a new dataset should be created. Furthermore, the paper presents future research and development suggestions for railway applications which contribute to guiding the mid-term research and development.

AB - The purpose of this paper is to present the results of the analysis of the application of Deep Learning in the railway domain with a particular focus on a train stop operation. The paper proposes an approach consisting of monocular vision-based and Deep Learning architectures. Even the difficulties imposed by actual regulation, the findings show that Deep Learning architecture can offer promising results in railway localization using techniques like visual odometry, SLAM or pose estimation. Besides, in spite of the many datasets available in the literature needed to train the neural network, none of them have been created for indoor railway environments. Therefore, a new dataset should be created. Furthermore, the paper presents future research and development suggestions for railway applications which contribute to guiding the mid-term research and development.

UR - http://www.scopus.com/inward/record.url?scp=85082612970&partnerID=8YFLogxK

U2 - 10.1109/SII46433.2020.9026246

DO - 10.1109/SII46433.2020.9026246

M3 - Article in proceeding

AN - SCOPUS:85082612970

T3 - Proceedings of the 2020 IEEE/SICE International Symposium on System Integration, SII 2020

SP - 943

EP - 948

BT - Proceedings of the 2020 IEEE/SICE International Symposium on System Integration, SII 2020

PB - IEEE Signal Processing Society

T2 - 2020 IEEE/SICE International Symposium on System Integration, SII 2020

Y2 - 12 January 2020 through 15 January 2020

ER -

Etxeberria-Garcia M, Labayen M, Zamalloa M, Arana-Arexolaleiba N. Application of Computer Vision and Deep Learning in the railway domain for autonomous train stop operation. In Proceedings of the 2020 IEEE/SICE International Symposium on System Integration, SII 2020. IEEE Signal Processing Society. 2020. p. 943-948. 9026246. (Proceedings of the 2020 IEEE/SICE International Symposium on System Integration, SII 2020). doi: 10.1109/SII46433.2020.9026246

Application of Computer Vision and Deep Learning in the railway domain for autonomous train stop operation

Abstract

Conference

Bibliographical note

Access to Document

AUB Link

Other files and links

Fingerprint

Cite this