ccvw.2014.0007

Warning and Prohibitory Traffic Sign Detection based on Edge Orientation Gradients

Darko Jurić and Sven Lončarić

Abstract

A method for traffic sign shape detection is presented, which does not require extensive training and is based on fast template matching suitable for real-time applications. The proposed method is able to detect prohibitory and warning signs. Post processing phase enables detection verification thus drastically increasing detection accuracy. All method parameters, if required, can be tweaked without the need for time-consuming retraining procedures. The method shows robustness to various conditions that often impose problems for color based systems. The proposed method can be used standalone or with already developed methods as a verification layer.

Files

Full Paper as PDF

BibTeX Citation

DOI

10.20532/ccvw.2014.0007

https://doi.org/10.20532/ccvw.2014.0007

BibTeX

@InProceedings{10.20532/ccvw.2014.0007,
  author =       {Darko Juri{\' c} and Sven Lon{\v c}ari{\' c}},
  title =        {Warning and Prohibitory Traffic Sign Detection based
                  on Edge Orientation Gradients},
  booktitle =    {Proceedings of the Croatian Compter Vision Workshop,
                  Year 2},
  pages =        {27-32},
  year =         2014,
  editor =       {Lon{\v c}ari{\' c}, Sven and Suba{\v s}i{\' c},
                  Marko},
  address =      {Zagreb},
  month =        {September},
  organization = {Center of Excellence for Computer Vision},
  publisher =    {University of Zagreb},
  abstract =     {A method for traffic sign shape detection is
                  presented, which does not require extensive training
                  and is based on fast template matching suitable for
                  real-time applications. The proposed method is able
                  to detect prohibitory and warning signs. Post
                  processing phase enables detection verification thus
                  drastically increasing detection accuracy. All
                  method parameters, if required, can be tweaked
                  without the need for time-consuming retraining
                  procedures. The method shows robustness to various
                  conditions that often impose problems for color
                  based systems. The proposed method can be used
                  standalone or with already developed methods as a
                  verification layer.},
  doi =          {10.20532/ccvw.2014.0007},
  url =          {https://doi.org/10.20532/ccvw.2014.0007}
}