Application of semantic segmentation for an autonomous rail tamping assistance system

Gerald Zauner; Tobias Müller; Andreas Theiß; Martin Bürger; Florian Auer

doi:10.2352/ISSN.2470-1173.2019.7.IRIACV-462

Application of semantic segmentation for an autonomous rail tamping assistance system

Gerald Zauner, Tobias Müller, Andreas Theiß, Martin Bürger, Florian Auer

Research Center Wels

Research output: Chapter in Book/Report/Conference proceedings › Conference contribution

3 Citations (Scopus)

Abstract

Safe and comfortable travel on the train is only possible on tracks that are in the correct geometric position. For this reason, track tamping machines are used worldwide that carry out this important track maintenance task. Turnout-ta.mping refers to a complex procedure for the improvement and stabilization of the track situation in turnouts, which is carried out usually by experienced operators. This application paper describes the current state of development of a 3D laser line scanner-based sensor system for a new turnout-tamping assistance system, which is able to support and relieve the operator in complex tamping areas. A central task in this context is digital image processing, which carries out so-called semantic segmentation (based on deep learning algorithms) on the basis of 3D scanner data in order to detect essential and critical rail areas fully automatically.

Original language	English
Title of host publication	IS&T Electronic Imaging 2019
Volume	2019
Edition	7
DOIs	https://doi.org/10.2352/ISSN.2470-1173.2019.7.IRIACV-462
Publication status	Published - 13 Jan 2019
Event	Intelligent Robotics and Industrial Applications using Computer Vision 2019 - San Francisco, United States Duration: 13 Jan 2019 → 17 Jan 2019 https://www.imaging.org/site/IST/Conferences/EI/EI_2019/Conference/C_IRIACV.aspx

Publication series

Name	IS and T International Symposium on Electronic Imaging Science and Technology

Conference

Conference	Intelligent Robotics and Industrial Applications using Computer Vision 2019
Country/Territory	United States
City	San Francisco
Period	13.01.2019 → 17.01.2019
Internet address	https://www.imaging.org/site/IST/Conferences/EI/EI_2019/Conference/C_IRIACV.aspx

Access to Document

10.2352/ISSN.2470-1173.2019.7.IRIACV-462

Cite this

@inproceedings{eb43750ab9af43ada34ae7080b6cd5f9,

title = "Application of semantic segmentation for an autonomous rail tamping assistance system",

abstract = "Safe and comfortable travel on the train is only possible on tracks that are in the correct geometric position. For this reason, track tamping machines are used worldwide that carry out this important track maintenance task. Turnout-ta.mping refers to a complex procedure for the improvement and stabilization of the track situation in turnouts, which is carried out usually by experienced operators. This application paper describes the current state of development of a 3D laser line scanner-based sensor system for a new turnout-tamping assistance system, which is able to support and relieve the operator in complex tamping areas. A central task in this context is digital image processing, which carries out so-called semantic segmentation (based on deep learning algorithms) on the basis of 3D scanner data in order to detect essential and critical rail areas fully automatically.",

author = "Gerald Zauner and Tobias M{\"u}ller and Andreas Thei{\ss} and Martin B{\"u}rger and Florian Auer",

year = "2019",

month = jan,

day = "13",

doi = "10.2352/ISSN.2470-1173.2019.7.IRIACV-462",

language = "English",

volume = "2019",

series = "IS and T International Symposium on Electronic Imaging Science and Technology",

booktitle = "IS&T Electronic Imaging 2019",

edition = "7",

note = "Intelligent Robotics and Industrial Applications using Computer Vision 2019 ; Conference date: 13-01-2019 Through 17-01-2019",

url = "https://www.imaging.org/site/IST/Conferences/EI/EI_2019/Conference/C_IRIACV.aspx",

}

Zauner, G, Müller, T, Theiß, A, Bürger, M & Auer, F 2019, Application of semantic segmentation for an autonomous rail tamping assistance system. in IS&T Electronic Imaging 2019. 7 edn, vol. 2019, IS and T International Symposium on Electronic Imaging Science and Technology, Intelligent Robotics and Industrial Applications using Computer Vision 2019, San Francisco, United States, 13.01.2019. https://doi.org/10.2352/ISSN.2470-1173.2019.7.IRIACV-462

TY - GEN

T1 - Application of semantic segmentation for an autonomous rail tamping assistance system

AU - Zauner, Gerald

AU - Müller, Tobias

AU - Theiß, Andreas

AU - Bürger, Martin

AU - Auer, Florian

PY - 2019/1/13

Y1 - 2019/1/13

N2 - Safe and comfortable travel on the train is only possible on tracks that are in the correct geometric position. For this reason, track tamping machines are used worldwide that carry out this important track maintenance task. Turnout-ta.mping refers to a complex procedure for the improvement and stabilization of the track situation in turnouts, which is carried out usually by experienced operators. This application paper describes the current state of development of a 3D laser line scanner-based sensor system for a new turnout-tamping assistance system, which is able to support and relieve the operator in complex tamping areas. A central task in this context is digital image processing, which carries out so-called semantic segmentation (based on deep learning algorithms) on the basis of 3D scanner data in order to detect essential and critical rail areas fully automatically.

AB - Safe and comfortable travel on the train is only possible on tracks that are in the correct geometric position. For this reason, track tamping machines are used worldwide that carry out this important track maintenance task. Turnout-ta.mping refers to a complex procedure for the improvement and stabilization of the track situation in turnouts, which is carried out usually by experienced operators. This application paper describes the current state of development of a 3D laser line scanner-based sensor system for a new turnout-tamping assistance system, which is able to support and relieve the operator in complex tamping areas. A central task in this context is digital image processing, which carries out so-called semantic segmentation (based on deep learning algorithms) on the basis of 3D scanner data in order to detect essential and critical rail areas fully automatically.

UR - http://www.scopus.com/inward/record.url?scp=85080888728&partnerID=8YFLogxK

U2 - 10.2352/ISSN.2470-1173.2019.7.IRIACV-462

DO - 10.2352/ISSN.2470-1173.2019.7.IRIACV-462

M3 - Conference contribution

VL - 2019

T3 - IS and T International Symposium on Electronic Imaging Science and Technology

BT - IS&T Electronic Imaging 2019

T2 - Intelligent Robotics and Industrial Applications using Computer Vision 2019

Y2 - 13 January 2019 through 17 January 2019

ER -

Application of semantic segmentation for an autonomous rail tamping assistance system

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this