Detail publikace

Real-Time Detection of Lines using Parallel Coordinates and OpenGL

Originální název

Real-Time Detection of Lines using Parallel Coordinates and OpenGL

Anglický název

Real-Time Detection of Lines using Parallel Coordinates and OpenGL

Jazyk

en

Originální abstrakt

Line detection in raster images is frequently performed using the Hough Transform. Hough Transform for line detection is difficult to accelerate using the GPU because it essentially requires rasterization of sinusoids into a highresolution raster of accumulators, which is not a suitable task for GPU. This paper presents a GPU implementation of the PClines - a new parameterization of lines for the Hough Transform. PClines are a point-to-line-mapping and thus the detection of lines uses the graphics processor to rasterize lines into a rectangular frame buffer which is a task very natural and effective on the GPU. The OpenGL 3.3 pipeline is used to efficiently perform the whole of the PClines-based Hough Transform on the GPU. Experimental evaluation shows that even for high-resolution input images with complicated content, the line detector performs easily in real time, which allows for different practical applications.

Anglický abstrakt

Line detection in raster images is frequently performed using the Hough Transform. Hough Transform for line detection is difficult to accelerate using the GPU because it essentially requires rasterization of sinusoids into a highresolution raster of accumulators, which is not a suitable task for GPU. This paper presents a GPU implementation of the PClines - a new parameterization of lines for the Hough Transform. PClines are a point-to-line-mapping and thus the detection of lines uses the graphics processor to rasterize lines into a rectangular frame buffer which is a task very natural and effective on the GPU. The OpenGL 3.3 pipeline is used to efficiently perform the whole of the PClines-based Hough Transform on the GPU. Experimental evaluation shows that even for high-resolution input images with complicated content, the line detector performs easily in real time, which allows for different practical applications.

BibTex


@inproceedings{BUT76391,
  author="Markéta {Juránková} and Jiří {Havel} and Adam {Herout}",
  title="Real-Time Detection of Lines using Parallel Coordinates and OpenGL",
  annote="Line detection in raster images is frequently performed using the Hough
Transform. Hough Transform for line detection is difficult to accelerate using
the GPU because it essentially requires rasterization of sinusoids into
a highresolution raster of accumulators, which is not a suitable task for GPU.
This paper presents a GPU implementation of the PClines - a new parameterization
of lines for the Hough Transform. PClines are a point-to-line-mapping and thus
the detection of lines uses the graphics processor to rasterize lines into
a rectangular frame buffer which is a task very natural and effective on the GPU.
The OpenGL 3.3 pipeline is used to efficiently perform the whole of the
PClines-based Hough Transform on the GPU. Experimental evaluation shows that even
for high-resolution input images with complicated content, the line detector
performs easily in real time, which allows for different practical applications.",
  address="Comenius University in Bratislava",
  booktitle="Proceedings of SCCG 2011",
  chapter="76391",
  edition="NEUVEDEN",
  howpublished="print",
  institution="Comenius University in Bratislava",
  year="2011",
  month="april",
  pages="1--7",
  publisher="Comenius University in Bratislava",
  type="conference paper"
}