Presentation 2020-12-11
Study of Deep Learning based Object Detection for Automatic Train Operation in Railways
Shiva Krishna Maheshuni, Shimura Takahiro, Yabuki Kohei, Hasegawa Takumi, Takeshi Mizuma,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Real time object detection is already being implemented in systems like autonomous driving in cars, surveillance Cameras, factories, etc. But a very little application is being done in the field of railways. There are already various State of the Art object detectors which are trained on general open source image datasets like Open-Images 2019, MS-COCO , etc. The same object detectors cannot be used in the view point of railways. The aim of this paper is to refine and develop a YOLOv4 Object detector , which can aid in automatic train operation.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Object DetectionConvolutional neural networks(CNN)Deep learningYOLOv4Automatic Train Operation
Paper # DC2020-61
Date of Issue 2020-12-04 (DC)

Conference Information
Committee DC
Conference Date 2020/12/11(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Hiroshi Takahashi(Ehime Univ.)
Vice Chair Tatsuhiro Tsuchiya(Osaka Univ.)
Secretary Tatsuhiro Tsuchiya(Nihon Univ.)
Assistant

Paper Information
Registration To Technical Committee on Dependable Computing
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Study of Deep Learning based Object Detection for Automatic Train Operation in Railways
Sub Title (in English)
Keyword(1) Object DetectionConvolutional neural networks(CNN)Deep learningYOLOv4Automatic Train Operation
1st Author's Name Shiva Krishna Maheshuni
1st Author's Affiliation University of Tokyo(UTokyo)
2nd Author's Name Shimura Takahiro
2nd Author's Affiliation Kyosan Electric Manufacturing Co., Ltd.(Kyosan Electric Mfg)
3rd Author's Name Yabuki Kohei
3rd Author's Affiliation Kyosan Electric Manufacturing Co., Ltd.(Kyosan Electric Mfg)
4th Author's Name Hasegawa Takumi
4th Author's Affiliation Kyosan Electric Manufacturing Co., Ltd.(Kyosan Electric Mfg)
5th Author's Name Takeshi Mizuma
5th Author's Affiliation University of Tokyo(UTokyo)
Date 2020-12-11
Paper # DC2020-61
Volume (vol) vol.120
Number (no) DC-288
Page pp.pp.12-17(DC),
#Pages 6
Date of Issue 2020-12-04 (DC)