Using geometric primitives to calibrate traffic scenes

Osama Masoud; Nikolaos P. Papanikolopoulos

doi:10.1016/j.trc.2007.05.005

Using geometric primitives to calibrate traffic scenes

Osama Masoud, Nikolaos P. Papanikolopoulos

Computer Science and Engineering

Research output: Contribution to journal › Article › peer-review

10 Scopus citations

Abstract

In this paper, we address the problem of recovering the intrinsic and extrinsic parameters of a camera or a group of cameras in a setting overlooking a traffic scene. Unlike many other settings, conventional camera calibration techniques are not applicable in this case. We present a method that uses certain geometric primitives commonly found in traffic scenes, such as straight and curved lanes, lane markings, and poles in order to recover calibration parameters. We show experimentally that these primitives provide the needed redundancy and are capable of achieving accurate results suitable for most traffic monitoring applications.

Original language	English (US)
Pages (from-to)	361-379
Number of pages	19
Journal	Transportation Research Part C: Emerging Technologies
Volume	15
Issue number	6
DOIs	https://doi.org/10.1016/j.trc.2007.05.005
State	Published - Dec 2007

Bibliographical note

Funding Information:
This work has been supported in part by the National Science Foundation through Grants #IIS-0219863, #CMS-0127893, #CNS-0324864, and #CNS-0224363, the Minnesota Department of Transportation, and the ITS Institute at the University of Minnesota. We would also like to thank the anonymous reviewers for their valuable comments.

Keywords

Application systems
Calibration
Multi-view reconstruction
Multi-view stereo
Traffic monitoring

Publisher link

10.1016/j.trc.2007.05.005

Find It

Find It at U of M Libraries

Cite this

@article{5b8ad56b84af4ff2ad47c6519bee01cd,

title = "Using geometric primitives to calibrate traffic scenes",

abstract = "In this paper, we address the problem of recovering the intrinsic and extrinsic parameters of a camera or a group of cameras in a setting overlooking a traffic scene. Unlike many other settings, conventional camera calibration techniques are not applicable in this case. We present a method that uses certain geometric primitives commonly found in traffic scenes, such as straight and curved lanes, lane markings, and poles in order to recover calibration parameters. We show experimentally that these primitives provide the needed redundancy and are capable of achieving accurate results suitable for most traffic monitoring applications.",

keywords = "Application systems, Calibration, Multi-view reconstruction, Multi-view stereo, Traffic monitoring",

author = "Osama Masoud and Papanikolopoulos, {Nikolaos P.}",

note = "Funding Information: This work has been supported in part by the National Science Foundation through Grants #IIS-0219863, #CMS-0127893, #CNS-0324864, and #CNS-0224363, the Minnesota Department of Transportation, and the ITS Institute at the University of Minnesota. We would also like to thank the anonymous reviewers for their valuable comments. ",

year = "2007",

month = dec,

doi = "10.1016/j.trc.2007.05.005",

language = "English (US)",

volume = "15",

pages = "361--379",

journal = "Transportation Research Part C: Emerging Technologies",

issn = "0968-090X",

publisher = "Elsevier Ltd",

number = "6",

}

TY - JOUR

T1 - Using geometric primitives to calibrate traffic scenes

AU - Masoud, Osama

AU - Papanikolopoulos, Nikolaos P.

N1 - Funding Information: This work has been supported in part by the National Science Foundation through Grants #IIS-0219863, #CMS-0127893, #CNS-0324864, and #CNS-0224363, the Minnesota Department of Transportation, and the ITS Institute at the University of Minnesota. We would also like to thank the anonymous reviewers for their valuable comments.

PY - 2007/12

Y1 - 2007/12

N2 - In this paper, we address the problem of recovering the intrinsic and extrinsic parameters of a camera or a group of cameras in a setting overlooking a traffic scene. Unlike many other settings, conventional camera calibration techniques are not applicable in this case. We present a method that uses certain geometric primitives commonly found in traffic scenes, such as straight and curved lanes, lane markings, and poles in order to recover calibration parameters. We show experimentally that these primitives provide the needed redundancy and are capable of achieving accurate results suitable for most traffic monitoring applications.

AB - In this paper, we address the problem of recovering the intrinsic and extrinsic parameters of a camera or a group of cameras in a setting overlooking a traffic scene. Unlike many other settings, conventional camera calibration techniques are not applicable in this case. We present a method that uses certain geometric primitives commonly found in traffic scenes, such as straight and curved lanes, lane markings, and poles in order to recover calibration parameters. We show experimentally that these primitives provide the needed redundancy and are capable of achieving accurate results suitable for most traffic monitoring applications.

KW - Application systems

KW - Calibration

KW - Multi-view reconstruction

KW - Multi-view stereo

KW - Traffic monitoring

UR - http://www.scopus.com/inward/record.url?scp=35148820094&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=35148820094&partnerID=8YFLogxK

U2 - 10.1016/j.trc.2007.05.005

DO - 10.1016/j.trc.2007.05.005

M3 - Article

AN - SCOPUS:35148820094

SN - 0968-090X

VL - 15

SP - 361

EP - 379

JO - Transportation Research Part C: Emerging Technologies

JF - Transportation Research Part C: Emerging Technologies

IS - 6

ER -

Using geometric primitives to calibrate traffic scenes

Abstract

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this