Publication detail

Comprehensive Data Set for Automatic Single Camera Visual Speed Measurement

SOCHOR, J. JURÁNEK, R. ŠPAŇHEL, J. MARŠÍK, L. ŠIROKÝ, A. HEROUT, A. ZEMČÍK, P.

Original Title

Comprehensive Data Set for Automatic Single Camera Visual Speed Measurement

English Title

Comprehensive Data Set for Automatic Single Camera Visual Speed Measurement

Type

journal article in Web of Science

Language

en

Original Abstract

In this paper, we focus on traffic camera calibration and visual speed measurement from a single monocular camera, which is an important task of visual traffic surveillance. Existing methods addressing this problem are hard to compare due to a lack of a common dataset with reliable ground truth. Therefore, it is not clear how the methods compare in various aspects and what are the factors affecting their performance. We captured a new dataset of 18 full-HD videos, each around one hour long, captured at 6 different locations. Vehicles in the videos (20 865 instances in total) are annotated with precise speed measurements from optical gates using LIDAR and verified with several reference GPS tracks. We made the dataset available for download and it contains the videos and metadata (calibration, lengths of features in image, annotations, etc.) for future comparison and evaluation. Camera calibration is the most crucial part of the speed measurement; therefore, we provide a brief overview of the methods and analyze a recently published method for fully automatic camera calibration and vehicle speed measurement and report the results on this dataset in detail.

English abstract

In this paper, we focus on traffic camera calibration and visual speed measurement from a single monocular camera, which is an important task of visual traffic surveillance. Existing methods addressing this problem are hard to compare due to a lack of a common dataset with reliable ground truth. Therefore, it is not clear how the methods compare in various aspects and what are the factors affecting their performance. We captured a new dataset of 18 full-HD videos, each around one hour long, captured at 6 different locations. Vehicles in the videos (20 865 instances in total) are annotated with precise speed measurements from optical gates using LIDAR and verified with several reference GPS tracks. We made the dataset available for download and it contains the videos and metadata (calibration, lengths of features in image, annotations, etc.) for future comparison and evaluation. Camera calibration is the most crucial part of the speed measurement; therefore, we provide a brief overview of the methods and analyze a recently published method for fully automatic camera calibration and vehicle speed measurement and report the results on this dataset in detail.

Keywords

dataset, speed measurement, automatic, surveillance, traffic camera calibration

Released

08.05.2018

Publisher

NEUVEDEN

Location

NEUVEDEN

ISBN

1524-9050

Periodical

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS

Year of study

2018

Number

99

State

US

Pages from

1633

Pages to

1643

Pages count

11

URL

Documents

BibTex


@article{BUT147193,
  author="Jakub {Sochor} and Roman {Juránek} and Jakub {Špaňhel} and Lukáš {Maršík} and Adam {Široký} and Adam {Herout} and Pavel {Zemčík}",
  title="Comprehensive Data Set for Automatic Single Camera Visual Speed Measurement",
  annote="In this paper, we focus on traffic camera calibration and visual speed
measurement from a single monocular camera, which is an important task of visual
traffic surveillance. Existing methods addressing this problem are hard to
compare due to a lack of a common dataset with reliable ground truth. Therefore,
it is not clear how the methods compare in various aspects and what are the
factors affecting their performance. We captured a new dataset of 18 full-HD
videos, each around one hour long, captured at 6 different locations. Vehicles in
the videos (20 865 instances in total) are annotated with precise speed
measurements from optical gates using LIDAR and verified with several reference
GPS tracks. We made the dataset available for download and it contains the videos
and metadata (calibration, lengths of features in image, annotations, etc.) for
future comparison and evaluation. Camera calibration is the most crucial part of
the speed measurement; therefore, we provide a brief overview of the methods and
analyze a recently published method for fully automatic camera calibration and
vehicle speed measurement and report the results on this dataset in detail.",
  address="NEUVEDEN",
  chapter="147193",
  doi="10.1109/TITS.2018.2825609",
  edition="NEUVEDEN",
  howpublished="print",
  institution="NEUVEDEN",
  number="99",
  volume="2018",
  year="2018",
  month="may",
  pages="1633--1643",
  publisher="NEUVEDEN",
  type="journal article in Web of Science"
}