Compact hardware realization for Hough based extraction of line segments in image sequences for vehicle guidance

  • Authors:
  • Jörg Schönfeld;Peter Pirsch

  • Affiliations:
  • University of Hannover, Laboratorium für Informationstechnologie, Hannover, Germany;University of Hannover, Laboratorium für Informationstechnologie, Hannover, Germany

  • Venue:
  • ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: plenary, special, audio, underwater acoustics, VLSI, neural networks - Volume I
  • Year:
  • 1993

Quantified Score

Hi-index 0.00

Visualization

Abstract

Important key symbols used in many image processing applications are straight line segments of edges and contours. The real time determination of straight line symbols in video sequences requires high computational rates which call for application specific circuits (ASICs). For a vision based vehicle guidance system a compact image processing unit has been developed which extracts straight lines as symbols for the street boundaries. This unit consists of two specially designed ASICs for the segmentation of symbols and a general programmable micro controller for high level processing. The implemented pipeline of algorithm comprises gradient operation, edge thinning, line verification and Hough transformation. Although the image processing unit is originally developed for vehicle guidance the hardware can be used for other industrial and robotic applications as well.