Computational Technology Resources - CCC

K. Nagai, W. Ohnishi, T. Koseki, Y. Setoguchi, T. Yamaguchi, S. Morita, K. Tanaka, "Experimental Validation of Onboard Train Localization Using Marker Detection and Accelerometer", in J. Pombo, (Editor), "Proceedings of the Seventh International Conference on Railway Technology: Research, Development and Maintenance ", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 15, Paper 24.3, 2026, doi:10.4203/ccc.15.24.3

Keywords: train localization, velocity estimation, image recognition, inertial measurement unit, gravity compensation, marker detection.

Abstract

Train position and velocity are essential for preventing collisions and maintaining appropriate train intervals. This study proposes an onboard train position and velocity estimation method combining a camera and an accelerometer. In the proposed method, trackside gradient markers are detected through image recognition and used to correct the estimated position and compensate for gradient effects in the measured acceleration. This improves the accuracy of both position and velocity estimation. In addition, divergence in the estimated states is reduced by correcting the position, velocity, and acceleration during train stops. The proposed method was validated using data collected in field tests on an actual train. The results show that the root mean square error of the velocity estimation was less than 2 km/h, while that of the position estimation was approximately 10 m. These findings indicate that the proposed method can estimate train position and velocity without additional trackside equipment and can be applied effectively using data from actual train operations.

download the full-text of this paper (PDF, 13 pages, 825 Kb)

go to the previous paper
go to the next paper
return to the table of contents
return to the volume description

	Computational & Technology Resources an online resource for computational, engineering & technology publications
	not logged in - login
Front Page Browse CCC CCP CSETS CTR IJRT Other Authors Search Purchase Guide FAQ Contact us	Civil-Comp Conferences ISSN 2753-3239 CCC: 15 PROCEEDINGS OF THE SEVENTH INTERNATIONAL CONFERENCE ON RAILWAY TECHNOLOGY: RESEARCH, DEVELOPMENT AND MAINTENANCE Edited by: J. Pombo Paper 24.3 Experimental Validation of Onboard Train Localization Using Marker Detection and Accelerometer K. Nagai¹, W. Ohnishi¹, T. Koseki¹, Y. Setoguchi², T. Yamaguchi², S. Morita² and K. Tanaka² ¹Graduate School of Engineering, The University of Tokyo, Japan ², NIPPON SIGNAL CO., LTD., Tokyo, Japan doi:10.4203/ccc.15.24.3 Full Bibliographic Reference for this paper K. Nagai, W. Ohnishi, T. Koseki, Y. Setoguchi, T. Yamaguchi, S. Morita, K. Tanaka, "Experimental Validation of Onboard Train Localization Using Marker Detection and Accelerometer", in J. Pombo, (Editor), "Proceedings of the Seventh International Conference on Railway Technology: Research, Development and Maintenance ", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 15, Paper 24.3, 2026, doi:10.4203/ccc.15.24.3 Keywords: train localization, velocity estimation, image recognition, inertial measurement unit, gravity compensation, marker detection. Abstract Train position and velocity are essential for preventing collisions and maintaining appropriate train intervals. This study proposes an onboard train position and velocity estimation method combining a camera and an accelerometer. In the proposed method, trackside gradient markers are detected through image recognition and used to correct the estimated position and compensate for gradient effects in the measured acceleration. This improves the accuracy of both position and velocity estimation. In addition, divergence in the estimated states is reduced by correcting the position, velocity, and acceleration during train stops. The proposed method was validated using data collected in field tests on an actual train. The results show that the root mean square error of the velocity estimation was less than 2 km/h, while that of the position estimation was approximately 10 m. These findings indicate that the proposed method can estimate train position and velocity without additional trackside equipment and can be applied effectively using data from actual train operations. download the full-text of this paper (PDF, 13 pages, 825 Kb) go to the previous paper go to the next paper return to the table of contents return to the volume description
Back to top	©Civil-Comp Limited 2023 - terms & conditions