Inferring the actual urban road environment from traffic sign data using a minimum description length approach

Zoltán Fazekas, Gábor Balázs, László Gerencsér, P. Gáspár

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

In our paper, we focus on a group of traffic signs and use traffic sign logs to statistically infer the type of urban environment in which a car is being driven. The traffic signs are either perceived and logged by a human data entry assistant, or preferably automatically detected and logged by an on-board traffic sign recognition and logging system. An entry in the log-file records the traffic sign type and the along-the-route location of the sign. Furthermore, in case of collecting training data it records also the actual road environment category entered by the data entry assistant. The logs are seen as realizations of an inhomogeneous marked Poisson process, and the minimum description length (MDL) principle is applied to infer the actual environment. The aim of this approach is to encode the current data in the shortest possible way assuming stochastic models derived from data collected earlier and thereby accept the corresponding model and environment as actual. To evaluate the quality of classification, the inferred environment categories are compared to the ground truth data.

Original languageEnglish
Pages (from-to)516-523
Number of pages8
JournalTransportation Research Procedia
Volume27
DOIs
Publication statusPublished - Jan 1 2017

Fingerprint

traffic sign
Traffic signs
road
Data acquisition
assistant
Stochastic models
Railroad cars

Keywords

  • Detection of road environment
  • Marked Poisson point process
  • Minimal description length principle
  • Statistical inference
  • Traffic sign recognition systems

ASJC Scopus subject areas

  • Transportation

Cite this

Inferring the actual urban road environment from traffic sign data using a minimum description length approach. / Fazekas, Zoltán; Balázs, Gábor; Gerencsér, László; Gáspár, P.

In: Transportation Research Procedia, Vol. 27, 01.01.2017, p. 516-523.

Research output: Contribution to journalArticle

@article{aa828a0b018248d7b3c6c81f92b2f849,
title = "Inferring the actual urban road environment from traffic sign data using a minimum description length approach",
abstract = "In our paper, we focus on a group of traffic signs and use traffic sign logs to statistically infer the type of urban environment in which a car is being driven. The traffic signs are either perceived and logged by a human data entry assistant, or preferably automatically detected and logged by an on-board traffic sign recognition and logging system. An entry in the log-file records the traffic sign type and the along-the-route location of the sign. Furthermore, in case of collecting training data it records also the actual road environment category entered by the data entry assistant. The logs are seen as realizations of an inhomogeneous marked Poisson process, and the minimum description length (MDL) principle is applied to infer the actual environment. The aim of this approach is to encode the current data in the shortest possible way assuming stochastic models derived from data collected earlier and thereby accept the corresponding model and environment as actual. To evaluate the quality of classification, the inferred environment categories are compared to the ground truth data.",
keywords = "Detection of road environment, Marked Poisson point process, Minimal description length principle, Statistical inference, Traffic sign recognition systems",
author = "Zolt{\'a}n Fazekas and G{\'a}bor Bal{\'a}zs and L{\'a}szl{\'o} Gerencs{\'e}r and P. G{\'a}sp{\'a}r",
year = "2017",
month = "1",
day = "1",
doi = "10.1016/j.trpro.2017.12.055",
language = "English",
volume = "27",
pages = "516--523",
journal = "Transportation Research Procedia",
issn = "2352-1457",
publisher = "Elsevier BV",

}

TY - JOUR

T1 - Inferring the actual urban road environment from traffic sign data using a minimum description length approach

AU - Fazekas, Zoltán

AU - Balázs, Gábor

AU - Gerencsér, László

AU - Gáspár, P.

PY - 2017/1/1

Y1 - 2017/1/1

N2 - In our paper, we focus on a group of traffic signs and use traffic sign logs to statistically infer the type of urban environment in which a car is being driven. The traffic signs are either perceived and logged by a human data entry assistant, or preferably automatically detected and logged by an on-board traffic sign recognition and logging system. An entry in the log-file records the traffic sign type and the along-the-route location of the sign. Furthermore, in case of collecting training data it records also the actual road environment category entered by the data entry assistant. The logs are seen as realizations of an inhomogeneous marked Poisson process, and the minimum description length (MDL) principle is applied to infer the actual environment. The aim of this approach is to encode the current data in the shortest possible way assuming stochastic models derived from data collected earlier and thereby accept the corresponding model and environment as actual. To evaluate the quality of classification, the inferred environment categories are compared to the ground truth data.

AB - In our paper, we focus on a group of traffic signs and use traffic sign logs to statistically infer the type of urban environment in which a car is being driven. The traffic signs are either perceived and logged by a human data entry assistant, or preferably automatically detected and logged by an on-board traffic sign recognition and logging system. An entry in the log-file records the traffic sign type and the along-the-route location of the sign. Furthermore, in case of collecting training data it records also the actual road environment category entered by the data entry assistant. The logs are seen as realizations of an inhomogeneous marked Poisson process, and the minimum description length (MDL) principle is applied to infer the actual environment. The aim of this approach is to encode the current data in the shortest possible way assuming stochastic models derived from data collected earlier and thereby accept the corresponding model and environment as actual. To evaluate the quality of classification, the inferred environment categories are compared to the ground truth data.

KW - Detection of road environment

KW - Marked Poisson point process

KW - Minimal description length principle

KW - Statistical inference

KW - Traffic sign recognition systems

UR - http://www.scopus.com/inward/record.url?scp=85039959680&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85039959680&partnerID=8YFLogxK

U2 - 10.1016/j.trpro.2017.12.055

DO - 10.1016/j.trpro.2017.12.055

M3 - Article

AN - SCOPUS:85039959680

VL - 27

SP - 516

EP - 523

JO - Transportation Research Procedia

JF - Transportation Research Procedia

SN - 2352-1457

ER -