Reducing false alarms in automated target recognition using local sea-floor characteristics

@article{Daniell2014ReducingFA,
  title={Reducing false alarms in automated target recognition using local sea-floor characteristics},
  author={Oliver Daniell and Yvan R. Petillot and Scott Reed and J{\'o}se R. V{\'a}zquez and Andrea Frau},
  journal={2014 Sensor Signal Processing for Defence (SSPD)},
  year={2014},
  pages={1-5}
}
This paper describes the use of local sea-floor characteristics to train a neural network to remove false alarms from an Automatic Target Recognition (ATR) algorithm. We demonstrate that this reduces the Probability of False Alarm (PFA) in difficult areas without impacting the Probability of Detection (PD) in flat areas. The sea-floor characteristics are calculated from the texture and appearance of clutter on the seafloor. Textural characteristics are extracted using a Dual Tree Wavelet (DTW… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-9 of 9 references

Seafloor acoustic anisotropy and complexity assessment towards prediction of ATR performance

  • E. Fakiris, D. Williams, M. Couillard, W. Fox
  • In Proc. Int. Conf. Exhib. Underwater Acoust.,
  • 2013
1 Excerpt

Unsupervised seafloor classification for automatic target recognition

  • O Daniell, Y Petillot, S Reed
  • Proc. International Conf. Remote Sens., (October…
  • 2012
1 Excerpt

Texture recognition in synthetic aperture sonar images with scattering operators

  • N Valeyrie, Y Pailhas, C Capus, Y Petillot
  • In UAM,
  • 2011
1 Excerpt

Cascade of boosted classifiers for rapid detection of underwater objects

  • J Sawas, Y Petillot, Y Pailhas
  • In Proc. Conf. on Underwater Acoustics,
  • 2010
1 Excerpt

Similar Papers

Loading similar papers…