A Real-time Train Perception Method for Obstacle Intrusion Based on Front View Projection

In order to improve the obstacle perception ability of automatic train operation in rail transit, it is necessary to increase the train's ability to perceive obstacle intrusion in the operational scenarios. Aiming at addressing the limitations in the commonly used multi-sensor fusion algorithm,...

Full description

Saved in:
Bibliographic Details
Main Authors: HE Qian, JIANG Guotao, DONG Wenbo, PI Zhichao, YANG Hailang, CHEN Meilin
Format: Article
Language:zho
Published: Editorial Office of Control and Information Technology 2023-08-01
Series:Kongzhi Yu Xinxi Jishu
Subjects:
Online Access:http://ctet.csrzic.com/thesisDetails#10.13889/j.issn.2096-5427.2023.04.010
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849224946312544256
author HE Qian
JIANG Guotao
DONG Wenbo
PI Zhichao
YANG Hailang
CHEN Meilin
author_facet HE Qian
JIANG Guotao
DONG Wenbo
PI Zhichao
YANG Hailang
CHEN Meilin
author_sort HE Qian
collection DOAJ
description In order to improve the obstacle perception ability of automatic train operation in rail transit, it is necessary to increase the train's ability to perceive obstacle intrusion in the operational scenarios. Aiming at addressing the limitations in the commonly used multi-sensor fusion algorithm, which include inadequate clearance analysis, poor real-time performance and high computing power demands, this paper proposes a method to perceive encroachment obstacles in real time with cameras and LiDAR as sensors. The proposed method, which applies the information fusion approach based on the two-dimensional projection plane of the front view (FV), involves the establishment of a projection matrix through offline joint calibration, projection of the LiDAR point cloud onto the FV plane, and extraction of track images from cameras, to enable clearance calculation. By incorporating correction of sensor synchronization errors based on point cloud prediction, a judgment regarding track intrusion can be made, dependent on the projected obstacle point cloud and calculated clearance. Data collection and experimental verification were carried out using a train equipped with sensors and a perception system. The experimental results show the practicality of the proposed method on low-power embedded devices, achieving an average algorithm time of 16.2 ms. Moreover, the method is proven effective in real-time detection of track intrusion by obstacles ahead of trains, while simultaneously acquiring their locations and sizes.
format Article
id doaj-art-4dc3f700f41a43c7b27aa4a91b29730e
institution Kabale University
issn 2096-5427
language zho
publishDate 2023-08-01
publisher Editorial Office of Control and Information Technology
record_format Article
series Kongzhi Yu Xinxi Jishu
spelling doaj-art-4dc3f700f41a43c7b27aa4a91b29730e2025-08-25T06:48:42ZzhoEditorial Office of Control and Information TechnologyKongzhi Yu Xinxi Jishu2096-54272023-08-01677241222955A Real-time Train Perception Method for Obstacle Intrusion Based on Front View ProjectionHE QianJIANG GuotaoDONG WenboPI ZhichaoYANG HailangCHEN MeilinIn order to improve the obstacle perception ability of automatic train operation in rail transit, it is necessary to increase the train's ability to perceive obstacle intrusion in the operational scenarios. Aiming at addressing the limitations in the commonly used multi-sensor fusion algorithm, which include inadequate clearance analysis, poor real-time performance and high computing power demands, this paper proposes a method to perceive encroachment obstacles in real time with cameras and LiDAR as sensors. The proposed method, which applies the information fusion approach based on the two-dimensional projection plane of the front view (FV), involves the establishment of a projection matrix through offline joint calibration, projection of the LiDAR point cloud onto the FV plane, and extraction of track images from cameras, to enable clearance calculation. By incorporating correction of sensor synchronization errors based on point cloud prediction, a judgment regarding track intrusion can be made, dependent on the projected obstacle point cloud and calculated clearance. Data collection and experimental verification were carried out using a train equipped with sensors and a perception system. The experimental results show the practicality of the proposed method on low-power embedded devices, achieving an average algorithm time of 16.2 ms. Moreover, the method is proven effective in real-time detection of track intrusion by obstacles ahead of trains, while simultaneously acquiring their locations and sizes.http://ctet.csrzic.com/thesisDetails#10.13889/j.issn.2096-5427.2023.04.010autonomous drivingobstacle perceptionmulti-sensor fusioncameraLiDARrail transit
spellingShingle HE Qian
JIANG Guotao
DONG Wenbo
PI Zhichao
YANG Hailang
CHEN Meilin
A Real-time Train Perception Method for Obstacle Intrusion Based on Front View Projection
Kongzhi Yu Xinxi Jishu
autonomous driving
obstacle perception
multi-sensor fusion
camera
LiDAR
rail transit
title A Real-time Train Perception Method for Obstacle Intrusion Based on Front View Projection
title_full A Real-time Train Perception Method for Obstacle Intrusion Based on Front View Projection
title_fullStr A Real-time Train Perception Method for Obstacle Intrusion Based on Front View Projection
title_full_unstemmed A Real-time Train Perception Method for Obstacle Intrusion Based on Front View Projection
title_short A Real-time Train Perception Method for Obstacle Intrusion Based on Front View Projection
title_sort real time train perception method for obstacle intrusion based on front view projection
topic autonomous driving
obstacle perception
multi-sensor fusion
camera
LiDAR
rail transit
url http://ctet.csrzic.com/thesisDetails#10.13889/j.issn.2096-5427.2023.04.010
work_keys_str_mv AT heqian arealtimetrainperceptionmethodforobstacleintrusionbasedonfrontviewprojection
AT jiangguotao arealtimetrainperceptionmethodforobstacleintrusionbasedonfrontviewprojection
AT dongwenbo arealtimetrainperceptionmethodforobstacleintrusionbasedonfrontviewprojection
AT pizhichao arealtimetrainperceptionmethodforobstacleintrusionbasedonfrontviewprojection
AT yanghailang arealtimetrainperceptionmethodforobstacleintrusionbasedonfrontviewprojection
AT chenmeilin arealtimetrainperceptionmethodforobstacleintrusionbasedonfrontviewprojection
AT heqian realtimetrainperceptionmethodforobstacleintrusionbasedonfrontviewprojection
AT jiangguotao realtimetrainperceptionmethodforobstacleintrusionbasedonfrontviewprojection
AT dongwenbo realtimetrainperceptionmethodforobstacleintrusionbasedonfrontviewprojection
AT pizhichao realtimetrainperceptionmethodforobstacleintrusionbasedonfrontviewprojection
AT yanghailang realtimetrainperceptionmethodforobstacleintrusionbasedonfrontviewprojection
AT chenmeilin realtimetrainperceptionmethodforobstacleintrusionbasedonfrontviewprojection