Computational Technology Resources - CCC

L.C. Lai¹, K. Shimono¹, K. Ishii¹, H. Yokomizo¹, Y. Suda¹, T. Iijima², Y. Hatayama², K. Masui² and A. Fujita²

¹Institute of Industrial Science, The University of Tokyo, Japan
²WILLER TRAINS Incorporated, Kyoto, Japan

doi:10.4203/ccc.7.11.2

L.C. Lai, K. Shimono, K. Ishii, H. Yokomizo, Y. Suda, T. Iijima, Y. Hatayama, K. Masui, A. Fujita, "Study on a Deterrent against Deer Collisions in Railway Operation Environment", in J. Pombo, (Editor), "Proceedings of the Sixth International Conference on Railway Technology: Research, Development and Maintenance", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 7, Paper 11.2, 2024, doi:10.4203/ccc.7.11.2

Keywords: railway operation safety, animal collision accident, optical deterrent, deer vision, deer behavior, real railway operation environment, computer vision.

Abstract

This paper introduces a study on the efficacy of a bird deterrent, the “Marine Saponin”, to deer in a real railway operation environment. This deterrent has been developed for years but has not yet been tested in the transportation aspect. A field experiment was conducted using railway vehicles in normal commercial operation on a line in an area with high deer population. Front view videos from the vehicles involved in the experiment were recorded. An original dataset for object recognition model for identification of deer in the videos was constructed mainly using recorded scenes of officially reported deer collisions. With this model, deer that were encountered by the railway vehicles were recognized and categorized. Although the efficacy of “Marine Saponin” was not scientifically verified due to small sample size, it was regarded as a highly potential method. The behavior patterns of deer spotted but not involved in accidents were first obtained by computer vision in this study and contributed to statistical significance tests.

download the full-text of this paper (PDF, 12 pages, 939 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: 7 PROCEEDINGS OF THE SIXTH INTERNATIONAL CONFERENCE ON RAILWAY TECHNOLOGY: RESEARCH, DEVELOPMENT AND MAINTENANCE Edited by: J. Pombo Paper 11.2 Study on a Deterrent against Deer Collisions in Railway Operation Environment L.C. Lai¹, K. Shimono¹, K. Ishii¹, H. Yokomizo¹, Y. Suda¹, T. Iijima², Y. Hatayama², K. Masui² and A. Fujita² ¹Institute of Industrial Science, The University of Tokyo, Japan ²WILLER TRAINS Incorporated, Kyoto, Japan doi:10.4203/ccc.7.11.2 Full Bibliographic Reference for this paper L.C. Lai, K. Shimono, K. Ishii, H. Yokomizo, Y. Suda, T. Iijima, Y. Hatayama, K. Masui, A. Fujita, "Study on a Deterrent against Deer Collisions in Railway Operation Environment", in J. Pombo, (Editor), "Proceedings of the Sixth International Conference on Railway Technology: Research, Development and Maintenance", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 7, Paper 11.2, 2024, doi:10.4203/ccc.7.11.2 Keywords: railway operation safety, animal collision accident, optical deterrent, deer vision, deer behavior, real railway operation environment, computer vision. Abstract This paper introduces a study on the efficacy of a bird deterrent, the “Marine Saponin”, to deer in a real railway operation environment. This deterrent has been developed for years but has not yet been tested in the transportation aspect. A field experiment was conducted using railway vehicles in normal commercial operation on a line in an area with high deer population. Front view videos from the vehicles involved in the experiment were recorded. An original dataset for object recognition model for identification of deer in the videos was constructed mainly using recorded scenes of officially reported deer collisions. With this model, deer that were encountered by the railway vehicles were recognized and categorized. Although the efficacy of “Marine Saponin” was not scientifically verified due to small sample size, it was regarded as a highly potential method. The behavior patterns of deer spotted but not involved in accidents were first obtained by computer vision in this study and contributed to statistical significance tests. download the full-text of this paper (PDF, 12 pages, 939 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