Detail publikace

PClines - Line Detection Using Parallel Coordinates

Originální název

PClines - Line Detection Using Parallel Coordinates

Anglický název

PClines - Line Detection Using Parallel Coordinates

Jazyk

en

Originální abstrakt

Detection of lines in raster images is often performed using Hough transform. This paper presents a new parameterization of lines and a modification of the Hough transform - PClines.  PClines are based on parallel coordinates, a coordinate system used mostly or solely for high-dimensional data visualization.  The PClines algorithm is described in the paper; it is evaluated numerically and compared to the commonly used line detectors based on the Hough transform. The results show that PClines outperform the existing approaches in terms of accuracy.  Besides, PClines are computationally extremely efficient, require no floating-point operations, and can be easily accelerated by different hardware architectures.

Anglický abstrakt

Detection of lines in raster images is often performed using Hough transform. This paper presents a new parameterization of lines and a modification of the Hough transform - PClines.  PClines are based on parallel coordinates, a coordinate system used mostly or solely for high-dimensional data visualization.  The PClines algorithm is described in the paper; it is evaluated numerically and compared to the commonly used line detectors based on the Hough transform. The results show that PClines outperform the existing approaches in terms of accuracy.  Besides, PClines are computationally extremely efficient, require no floating-point operations, and can be easily accelerated by different hardware architectures.

BibTex


@inproceedings{BUT76275,
  author="Markéta {Juránková} and Adam {Herout} and Jiří {Havel}",
  title="PClines - Line Detection Using Parallel Coordinates",
  annote="Detection of lines in raster images is often performed using Hough transform.
This paper presents a new parameterization of lines and a modification of the
Hough transform - PClines.  PClines are based on parallel coordinates,
a coordinate system used mostly or solely for high-dimensional data
visualization.  The PClines algorithm is described in the paper; it is evaluated
numerically and compared to the commonly used line detectors based on the Hough
transform. The results show that PClines outperform the existing approaches in
terms of accuracy.  Besides, PClines are computationally extremely efficient,
require no floating-point operations, and can be easily accelerated by different
hardware architectures.",
  address="IEEE Computer Society",
  booktitle="Proceedings of CVPR 2011",
  chapter="76275",
  edition="NEUVEDEN",
  howpublished="print",
  institution="IEEE Computer Society",
  year="2011",
  month="june",
  pages="1489--1494",
  publisher="IEEE Computer Society",
  type="conference paper"
}