• DocumentCode
    396764
  • Title

    Broadband sonar target classification: pool experiments

  • Author

    Jung, J. Bynng ; Jacobs, James H. ; Denny, Gerald F. ; Simpson, Patrick K.

  • Author_Institution
    Sci. Fishery Syst. Inc., Anchorage, AK, USA
  • Volume
    2
  • fYear
    2003
  • fDate
    20-24 July 2003
  • Firstpage
    1307
  • Abstract
    Pool experiments are used to address specific aspects of broadband sonar system performance. In this paper, we describe the results from a set of experiments conducted over a three-day period in a controlled environment. These pool experiments explored the target classification capabilities of the broadband sonar using targets of different sizes and materials. Results obtained on single ping classification demonstrated at least 84.7% correct classification of targets of the same shape but of different size and material. The greatest classification confusion occurred between targets of the same shape and material and was only slightly different in size. When classifying, different materials were compared, we found that the information provided in the spectra was sufficient to provide nearly 99% correct classification. These results indicate that the broadband sonar does have the potential to discriminate between various sizes and materials of the same shape and they further validate the use of broadband sonar as a tool for species and size classification of fish.
  • Keywords
    aquaculture; sonar target recognition; broadband sonar target classification; fish size classification; fish species classification; pool experiments; single ping classification; Aquaculture; Composite materials; Conducting materials; Control systems; Jacobian matrices; Marine animals; Shape; Sonar measurements; System performance; Testing;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Neural Networks, 2003. Proceedings of the International Joint Conference on
  • ISSN
    1098-7576
  • Print_ISBN
    0-7803-7898-9
  • Type

    conf

  • DOI
    10.1109/IJCNN.2003.1223884
  • Filename
    1223884