Train Localization Environmental Scenario Identification Using Features Extracted from Historical Data

Tao Zhang; Baigen Cai; Debiao Lu; Jian Wang; Yu Xiao

doi:10.1007/978-981-16-3138-2_2

Train Localization Environmental Scenario Identification Using Features Extracted from Historical Data

Tao Zhang^*, Baigen Cai, Debiao Lu, Jian Wang, Yu Xiao

^*Corresponding author for this work

Mobile Cloud Computing

Beijing Jiaotong University

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

1 Citation (Scopus)

60 Downloads (Pure)

Abstract

The application of Global Navigation Satellite System (GNSS) on the railway greatly reduces the cost on train localization. However, the railway environment is complex and changes with the train movement, buildings, trees, railroad cuts and mountains will block and reflect the GNSS signals, which will bring errors to the GNSS-based train position estimation. This paper proposes a railway scenario identification method based on historical GNSS receiver observation data to identify scenarios along the railway. Firstly, a railway environment scenario parameter model library is established according to Feature of Sky Occlusion (FSO) of typical scenarios, apply historical GNSS observation data along the railway to establish the FSO models of scenario segments, and generate FSO feature sequences. The dynamic time warping algorithm (DTW) is used to match the FSO parameter model of the scenario segment with the FSO model library. This paper collected data from field experiments at Beijing Sanjiadian station to verify the algorithm. The scenario identification results showed that the scenario identification method based on DTW can effectively identify the railway scenarios.

Original language	English
Title of host publication	China Satellite Navigation Conference, CSNC 2021, Proceedings
Editors	Changfeng Yang, Jun Xie
Publisher	Springer
Pages	12-21
Number of pages	10
ISBN (Print)	978-981-16-3137-5
DOIs	https://doi.org/10.1007/978-981-16-3138-2_2
Publication status	Published - 2021
MoE publication type	A4 Conference publication
Event	China Satellite Navigation Conference - Nanchang, China Duration: 22 May 2021 → 25 May 2021 Conference number: 12

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	772 LNEE
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	China Satellite Navigation Conference
Abbreviated title	CSNC
Country/Territory	China
City	Nanchang
Period	22/05/2021 → 25/05/2021

Keywords

Dynamic time warping algorithm
Feature of sky occlusion
GNSS
Scenarios identification
Train localization

Access to Document

10.1007/978-981-16-3138-2_2

ELEC_Zhang_etal_Train_Localization_Environmental_Scenario_CSNC_2021Accepted author manuscript, 743 KB

Cite this

Zhang, T., Cai, B., Lu, D., Wang, J., & Xiao, Y. (2021). Train Localization Environmental Scenario Identification Using Features Extracted from Historical Data. In C. Yang, & J. Xie (Eds.), China Satellite Navigation Conference, CSNC 2021, Proceedings (pp. 12-21). (Lecture Notes in Electrical Engineering; Vol. 772 LNEE). Springer. https://doi.org/10.1007/978-981-16-3138-2_2

@inproceedings{21b377c370e14eaeb54bdc962717fe3c,

title = "Train Localization Environmental Scenario Identification Using Features Extracted from Historical Data",

abstract = "The application of Global Navigation Satellite System (GNSS) on the railway greatly reduces the cost on train localization. However, the railway environment is complex and changes with the train movement, buildings, trees, railroad cuts and mountains will block and reflect the GNSS signals, which will bring errors to the GNSS-based train position estimation. This paper proposes a railway scenario identification method based on historical GNSS receiver observation data to identify scenarios along the railway. Firstly, a railway environment scenario parameter model library is established according to Feature of Sky Occlusion (FSO) of typical scenarios, apply historical GNSS observation data along the railway to establish the FSO models of scenario segments, and generate FSO feature sequences. The dynamic time warping algorithm (DTW) is used to match the FSO parameter model of the scenario segment with the FSO model library. This paper collected data from field experiments at Beijing Sanjiadian station to verify the algorithm. The scenario identification results showed that the scenario identification method based on DTW can effectively identify the railway scenarios.",

keywords = "Dynamic time warping algorithm, Feature of sky occlusion, GNSS, Scenarios identification, Train localization",

author = "Tao Zhang and Baigen Cai and Debiao Lu and Jian Wang and Yu Xiao",

note = "Funding Information: This paper is supported by National Key Research and Development Program of China (2018YFB1201500), Beijing Science Program of Beijing Municipal Science and Technology (Z181100001018032), National Natural Science Foundation of China (U1934222, 61873023), Beijing Natural Science Foundation (L191014), and Beijing Nova Program of Science and Technology (Z191100001119066). Publisher Copyright: {\textcopyright} 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; China Satellite Navigation Conference, CSNC ; Conference date: 22-05-2021 Through 25-05-2021",

year = "2021",

doi = "10.1007/978-981-16-3138-2_2",

language = "English",

isbn = "978-981-16-3137-5",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer",

pages = "12--21",

editor = "Changfeng Yang and Jun Xie",

booktitle = "China Satellite Navigation Conference, CSNC 2021, Proceedings",

address = "Germany",

}

Zhang, T, Cai, B, Lu, D, Wang, J & Xiao, Y 2021, Train Localization Environmental Scenario Identification Using Features Extracted from Historical Data. in C Yang & J Xie (eds), China Satellite Navigation Conference, CSNC 2021, Proceedings. Lecture Notes in Electrical Engineering, vol. 772 LNEE, Springer, pp. 12-21, China Satellite Navigation Conference, Nanchang, China, 22/05/2021. https://doi.org/10.1007/978-981-16-3138-2_2

Train Localization Environmental Scenario Identification Using Features Extracted from Historical Data. / Zhang, Tao; Cai, Baigen; Lu, Debiao et al.
China Satellite Navigation Conference, CSNC 2021, Proceedings. ed. / Changfeng Yang; Jun Xie. Springer, 2021. p. 12-21 (Lecture Notes in Electrical Engineering; Vol. 772 LNEE).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - Train Localization Environmental Scenario Identification Using Features Extracted from Historical Data

AU - Zhang, Tao

AU - Cai, Baigen

AU - Lu, Debiao

AU - Wang, Jian

AU - Xiao, Yu

N1 - Conference code: 12

PY - 2021

Y1 - 2021

N2 - The application of Global Navigation Satellite System (GNSS) on the railway greatly reduces the cost on train localization. However, the railway environment is complex and changes with the train movement, buildings, trees, railroad cuts and mountains will block and reflect the GNSS signals, which will bring errors to the GNSS-based train position estimation. This paper proposes a railway scenario identification method based on historical GNSS receiver observation data to identify scenarios along the railway. Firstly, a railway environment scenario parameter model library is established according to Feature of Sky Occlusion (FSO) of typical scenarios, apply historical GNSS observation data along the railway to establish the FSO models of scenario segments, and generate FSO feature sequences. The dynamic time warping algorithm (DTW) is used to match the FSO parameter model of the scenario segment with the FSO model library. This paper collected data from field experiments at Beijing Sanjiadian station to verify the algorithm. The scenario identification results showed that the scenario identification method based on DTW can effectively identify the railway scenarios.

AB - The application of Global Navigation Satellite System (GNSS) on the railway greatly reduces the cost on train localization. However, the railway environment is complex and changes with the train movement, buildings, trees, railroad cuts and mountains will block and reflect the GNSS signals, which will bring errors to the GNSS-based train position estimation. This paper proposes a railway scenario identification method based on historical GNSS receiver observation data to identify scenarios along the railway. Firstly, a railway environment scenario parameter model library is established according to Feature of Sky Occlusion (FSO) of typical scenarios, apply historical GNSS observation data along the railway to establish the FSO models of scenario segments, and generate FSO feature sequences. The dynamic time warping algorithm (DTW) is used to match the FSO parameter model of the scenario segment with the FSO model library. This paper collected data from field experiments at Beijing Sanjiadian station to verify the algorithm. The scenario identification results showed that the scenario identification method based on DTW can effectively identify the railway scenarios.

KW - Dynamic time warping algorithm

KW - Feature of sky occlusion

KW - GNSS

KW - Scenarios identification

KW - Train localization

UR - http://www.scopus.com/inward/record.url?scp=85111422836&partnerID=8YFLogxK

U2 - 10.1007/978-981-16-3138-2_2

DO - 10.1007/978-981-16-3138-2_2

M3 - Conference article in proceedings

AN - SCOPUS:85111422836

SN - 978-981-16-3137-5

T3 - Lecture Notes in Electrical Engineering

SP - 12

EP - 21

BT - China Satellite Navigation Conference, CSNC 2021, Proceedings

A2 - Yang, Changfeng

A2 - Xie, Jun

PB - Springer

T2 - China Satellite Navigation Conference

Y2 - 22 May 2021 through 25 May 2021

ER -

Train Localization Environmental Scenario Identification Using Features Extracted from Historical Data

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this