Publication detail

Fully Automatic Roadside Camera Calibration for Traffic Surveillance

JURÁNKOVÁ, M. HEROUT, A. JURÁNEK, R. SOCHOR, J.

Original Title

Fully Automatic Roadside Camera Calibration for Traffic Surveillance

English Title

Fully Automatic Roadside Camera Calibration for Traffic Surveillance

Type

journal article in Web of Science

Language

en

Original Abstract

This paper deals with automatic calibration of roadside surveillance cameras. We focus on parameters necessary for measurements in traffic surveillance applications. Contrary to the existing solutions, our approach requires no a priori knowledge and it works with a very wide variety of road settings (number of lanes, occlusion, quality of ground marking), and with practically unlimited viewing angles. The main contribution is that our solution works fully automatically - without any per-camera or per-video manual settings or input whatsoever - and it is computationally cheap. Our approach uses tracking of local feature points and analyzes the trajectories in a manner based on Cascaded Hough Transform and parallel coordinates.  An important assumption for the vehicle movement is that at least a part of the vehicle motion is approximately straight -- we discuss the impact of this assumption on the applicability of our approach and show experimentally, that this assumption does not limit the usability of our approach severely.

English abstract

This paper deals with automatic calibration of roadside surveillance cameras. We focus on parameters necessary for measurements in traffic surveillance applications. Contrary to the existing solutions, our approach requires no a priori knowledge and it works with a very wide variety of road settings (number of lanes, occlusion, quality of ground marking), and with practically unlimited viewing angles. The main contribution is that our solution works fully automatically - without any per-camera or per-video manual settings or input whatsoever - and it is computationally cheap. Our approach uses tracking of local feature points and analyzes the trajectories in a manner based on Cascaded Hough Transform and parallel coordinates.  An important assumption for the vehicle movement is that at least a part of the vehicle motion is approximately straight -- we discuss the impact of this assumption on the applicability of our approach and show experimentally, that this assumption does not limit the usability of our approach severely.

Keywords

Hough Transform, Camera Calibration, Diamond Space, Roadside Data

RIV year

2014

Released

09.06.2014

Publisher

NEUVEDEN

Location

NEUVEDEN

Pages from

1

Pages to

10

Pages count

10

BibTex


@article{BUT111600,
  author="Markéta {Juránková} and Adam {Herout} and Roman {Juránek} and Jakub {Sochor}",
  title="Fully Automatic Roadside Camera Calibration for Traffic Surveillance",
  annote="This paper deals with automatic calibration of roadside surveillance cameras. We
focus on parameters necessary for measurements in traffic surveillance
applications. Contrary to the existing solutions, our approach requires no
a priori knowledge and it works with a very wide variety of road settings (number
of lanes, occlusion, quality of ground marking), and with practically unlimited
viewing angles. The main contribution is that our solution works fully
automatically - without any per-camera or per-video manual settings or input
whatsoever - and it is computationally cheap. Our approach uses tracking of local
feature points and analyzes the trajectories in a manner based on Cascaded Hough
Transform and parallel coordinates.  An important assumption for the vehicle
movement is that at least a part of the vehicle motion is approximately straight
-- we discuss the impact of this assumption on the applicability of our approach
and show experimentally, that this assumption does not limit the usability of our
approach severely.",
  address="NEUVEDEN",
  chapter="111600",
  doi="10.1109/TITS.2014.2352854",
  edition="NEUVEDEN",
  howpublished="print",
  institution="NEUVEDEN",
  number="1",
  volume="2014",
  year="2014",
  month="june",
  pages="1--10",
  publisher="NEUVEDEN",
  type="journal article in Web of Science"
}