Detecting taxi speeding from sparse and low-sampled trajectory data

Xibo ZHOU; Qiong LUO; Dian ZHANG; Lionel M. NI

doi:10.1007/978-3-319-96893-3_16

Detecting taxi speeding from sparse and low-sampled trajectory data

Xibo ZHOU^*
, Qiong LUO
, Dian ZHANG
, Lionel M. NI

^*Corresponding author for this work

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Referred Conference Paper › peer-review

6 Citations (Scopus)

Abstract

Taxis are a major means of public transportation in large cities, and speeding is a common problem among motor vehicles, including taxis. Unless caught by sensors or patrol officers, many speeding incidents go unnoticed, which pose potential threat to road safety. In this paper, we propose to detect speeding behaviors of individual taxis from taxi trajectory data. Such detection results are useful for driver risk analysis and road safety management. However, the taxi trajectory data are geographically sparse and the sample rate is low. Furthermore, existing methods mainly deal with the estimation of collective road speeds whereas we focus on the speeds of individual vehicles. As such, we propose to use a two-fold collective matrix factorization (CMF)-based model to estimate the individual vehicle speed. We have evaluated our method on real-world datasets, and the results show the effectiveness of our method in detecting taxi speeding behaviors.

Original language	English
Title of host publication	Web and Big Data : Second International Joint Conference, APWeb-WAIM 2018, Macau, China, July 23-25, 2018, Proceedings, Part II
Editors	Yoshiharu ISHIKAWA, Yi CAI, Jianliang XU
Publisher	Springer
Pages	214-222
Number of pages	9
ISBN (Electronic)	9783319968933
ISBN (Print)	9783319968926
DOIs	https://doi.org/10.1007/978-3-319-96893-3_16
Publication status	Published - 2018
Externally published	Yes
Event	2nd Asia Pacific Web and Web-Age Information Management Joint Conference on Web and Big Data, APWeb-WAIM 2018 - Macau, China Duration: 23 Jul 2018 → 25 Jul 2018 http://conferences.cis.umac.mo/apwebwaim2018/

Publication series

Name	Lecture Notes in Computer Science
Number	10988
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	2nd Asia Pacific Web and Web-Age Information Management Joint Conference on Web and Big Data, APWeb-WAIM 2018
Abbreviated title	APWeb-WAIM 2018
Country/Territory	China
City	Macau
Period	23/07/18 → 25/07/18
Internet address	http://conferences.cis.umac.mo/apwebwaim2018/

Bibliographical note

Publisher Copyright:
© 2018, Springer International Publishing AG, part of Springer Nature.

Funding

This work is supported in part by the Guangdong Pre-national project 2014GKXM054 and the Guangdong Province Key Laboratory of Popular High Performance Computers 2017B030314073.

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 11 Sustainable Cities and Communities

Keywords

Collective matrix factorization
Speeding
Trajectory

Access to Document

10.1007/978-3-319-96893-3_16

Cite this

ZHOU, X., LUO, Q., ZHANG, D., & NI, L. M. (2018). Detecting taxi speeding from sparse and low-sampled trajectory data. In Y. ISHIKAWA, Y. CAI, & J. XU (Eds.), Web and Big Data : Second International Joint Conference, APWeb-WAIM 2018, Macau, China, July 23-25, 2018, Proceedings, Part II (pp. 214-222). (Lecture Notes in Computer Science; No. 10988). Springer. https://doi.org/10.1007/978-3-319-96893-3_16

ZHOU, Xibo ; LUO, Qiong ; ZHANG, Dian et al. / Detecting taxi speeding from sparse and low-sampled trajectory data. Web and Big Data : Second International Joint Conference, APWeb-WAIM 2018, Macau, China, July 23-25, 2018, Proceedings, Part II. editor / Yoshiharu ISHIKAWA ; Yi CAI ; Jianliang XU. Springer, 2018. pp. 214-222 (Lecture Notes in Computer Science; 10988).

@inproceedings{41d56bdd3aad404cbce31401c4446017,

title = "Detecting taxi speeding from sparse and low-sampled trajectory data",

abstract = "Taxis are a major means of public transportation in large cities, and speeding is a common problem among motor vehicles, including taxis. Unless caught by sensors or patrol officers, many speeding incidents go unnoticed, which pose potential threat to road safety. In this paper, we propose to detect speeding behaviors of individual taxis from taxi trajectory data. Such detection results are useful for driver risk analysis and road safety management. However, the taxi trajectory data are geographically sparse and the sample rate is low. Furthermore, existing methods mainly deal with the estimation of collective road speeds whereas we focus on the speeds of individual vehicles. As such, we propose to use a two-fold collective matrix factorization (CMF)-based model to estimate the individual vehicle speed. We have evaluated our method on real-world datasets, and the results show the effectiveness of our method in detecting taxi speeding behaviors.",

keywords = "Collective matrix factorization, Speeding, Trajectory",

author = "Xibo ZHOU and Qiong LUO and Dian ZHANG and NI, \{Lionel M.\}",

note = "Publisher Copyright: {\textcopyright} 2018, Springer International Publishing AG, part of Springer Nature.; 2nd Asia Pacific Web and Web-Age Information Management Joint Conference on Web and Big Data, APWeb-WAIM 2018, APWeb-WAIM 2018 ; Conference date: 23-07-2018 Through 25-07-2018",

year = "2018",

doi = "10.1007/978-3-319-96893-3\_16",

language = "English",

isbn = "9783319968926",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

number = "10988",

pages = "214--222",

editor = "Yoshiharu ISHIKAWA and Yi CAI and Jianliang XU",

booktitle = "Web and Big Data : Second International Joint Conference, APWeb-WAIM 2018, Macau, China, July 23-25, 2018, Proceedings, Part II",

url = "http://conferences.cis.umac.mo/apwebwaim2018/",

}

ZHOU, X, LUO, Q, ZHANG, D & NI, LM 2018, Detecting taxi speeding from sparse and low-sampled trajectory data. in Y ISHIKAWA, Y CAI & J XU (eds), Web and Big Data : Second International Joint Conference, APWeb-WAIM 2018, Macau, China, July 23-25, 2018, Proceedings, Part II. Lecture Notes in Computer Science, no. 10988, Springer, pp. 214-222, 2nd Asia Pacific Web and Web-Age Information Management Joint Conference on Web and Big Data, APWeb-WAIM 2018, Macau, China, 23/07/18. https://doi.org/10.1007/978-3-319-96893-3_16

Detecting taxi speeding from sparse and low-sampled trajectory data. / ZHOU, Xibo; LUO, Qiong; ZHANG, Dian et al.
Web and Big Data : Second International Joint Conference, APWeb-WAIM 2018, Macau, China, July 23-25, 2018, Proceedings, Part II. ed. / Yoshiharu ISHIKAWA; Yi CAI; Jianliang XU. Springer, 2018. p. 214-222 (Lecture Notes in Computer Science; No. 10988).

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Referred Conference Paper › peer-review

TY - GEN

T1 - Detecting taxi speeding from sparse and low-sampled trajectory data

AU - ZHOU, Xibo

AU - LUO, Qiong

AU - ZHANG, Dian

AU - NI, Lionel M.

PY - 2018

Y1 - 2018

N2 - Taxis are a major means of public transportation in large cities, and speeding is a common problem among motor vehicles, including taxis. Unless caught by sensors or patrol officers, many speeding incidents go unnoticed, which pose potential threat to road safety. In this paper, we propose to detect speeding behaviors of individual taxis from taxi trajectory data. Such detection results are useful for driver risk analysis and road safety management. However, the taxi trajectory data are geographically sparse and the sample rate is low. Furthermore, existing methods mainly deal with the estimation of collective road speeds whereas we focus on the speeds of individual vehicles. As such, we propose to use a two-fold collective matrix factorization (CMF)-based model to estimate the individual vehicle speed. We have evaluated our method on real-world datasets, and the results show the effectiveness of our method in detecting taxi speeding behaviors.

AB - Taxis are a major means of public transportation in large cities, and speeding is a common problem among motor vehicles, including taxis. Unless caught by sensors or patrol officers, many speeding incidents go unnoticed, which pose potential threat to road safety. In this paper, we propose to detect speeding behaviors of individual taxis from taxi trajectory data. Such detection results are useful for driver risk analysis and road safety management. However, the taxi trajectory data are geographically sparse and the sample rate is low. Furthermore, existing methods mainly deal with the estimation of collective road speeds whereas we focus on the speeds of individual vehicles. As such, we propose to use a two-fold collective matrix factorization (CMF)-based model to estimate the individual vehicle speed. We have evaluated our method on real-world datasets, and the results show the effectiveness of our method in detecting taxi speeding behaviors.

KW - Collective matrix factorization

KW - Speeding

KW - Trajectory

UR - https://www.scopus.com/pages/publications/85051133543

U2 - 10.1007/978-3-319-96893-3_16

DO - 10.1007/978-3-319-96893-3_16

M3 - Conference paper (refereed)

AN - SCOPUS:85051133543

SN - 9783319968926

T3 - Lecture Notes in Computer Science

SP - 214

EP - 222

BT - Web and Big Data : Second International Joint Conference, APWeb-WAIM 2018, Macau, China, July 23-25, 2018, Proceedings, Part II

A2 - ISHIKAWA, Yoshiharu

A2 - CAI, Yi

A2 - XU, Jianliang

PB - Springer

T2 - 2nd Asia Pacific Web and Web-Age Information Management Joint Conference on Web and Big Data, APWeb-WAIM 2018

Y2 - 23 July 2018 through 25 July 2018

ER -

ZHOU X, LUO Q, ZHANG D, NI LM. Detecting taxi speeding from sparse and low-sampled trajectory data. In ISHIKAWA Y, CAI Y, XU J, editors, Web and Big Data : Second International Joint Conference, APWeb-WAIM 2018, Macau, China, July 23-25, 2018, Proceedings, Part II. Springer. 2018. p. 214-222. (Lecture Notes in Computer Science; 10988). Epub 2018 Jul 19. doi: 10.1007/978-3-319-96893-3_16

Detecting taxi speeding from sparse and low-sampled trajectory data

Abstract

Publication series

Conference

Bibliographical note

Funding

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this