Lane mark segmentation and identification using statistical criteria on compressed video

  • Authors:

  • J. Giralt;L. Rodriguez-Benitez;J. Moreno-Garcia;C. Solana-Cipres;L. Jimenez

  • Affiliations:

  • Information Systems and Technologies Department, University of Castilla-La Mancha, Ciudad Real, Spain;Information Systems and Technologies Department, University of Castilla-La Mancha, Ciudad Real, Spain;Information Systems and Technologies Department, University of Castilla-La Mancha, Ciudad Real, Spain;Information Systems and Technologies Department, University of Castilla-La Mancha, Ciudad Real, Spain;Information Systems and Technologies Department, University of Castilla-La Mancha, Ciudad Real, Spain

  • Venue:
  • Integrated Computer-Aided Engineering
  • Year:
  • 2013

Quantified Score

Hi-index 0.00

Visualization

Abstract

The detection and localization of road lane marks are relevant to many applications of driving assistance and road traffic surveillance. Usually, these techniques work by processing all the pixels in every image, making the computational cost too high. In these situations, the implementation of real-time detection applications is impossible. Processing the video directly in the compressed domain avoids this limitation because the data rate is much reduced and full decoding of the compressed images is unnecessary. The development of a real-time detection systems then becomes possible, even for resource-limited systems like mobile devices. In this paper an approach to the segmentation and recognition of lane marks using only H264/AVC motion vectors is proposed. A new representation of motion vectors is defined in order to detect efficiently the regions or blobs of interest in complex videos captured by moving cameras. Then, a set of mathematical filters are applied removing progressively the blobs detected, depending on their position in the scene, their size, and their shape; and obtaining finally the regions corresponding to the lane marks. The proposed method shows encouraging results in different road traffic video sequences.