Neural Network-Based Detection of Ultrasonic Targets with Respect to Noise and Number of Sampling Positions

Patrick K. Kroh, Ralph Simon, Stefan J. Rupitsch

    Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

    Abstract

    A neural network-based approach for detection of sonar targets in air is presented in this contribution. Our approach may facilitate autonomous mobile systems to reliably detect and classify objects in their surrounding by using sonar information. This task might be extremely important in changing as well as unorganized environments. We perform target iden-tification with long short-term memory networks as classifiers. Such are capable of dealing with variable numbers of echoes from multiple positions per input sequence, which facilitates more flexible operation. The impact of the number of recording positions per sequence and of noise is investigated. Furthermore, we demonstrate the improvement in classification performance in comparison to previously obtained results from multi-layer-perceptrons.

    Original languageEnglish
    Title of host publication2019 IEEE International Ultrasonics Symposium (IUS)
    PublisherIEEE Computer Society
    Pages1870-1873
    Number of pages4
    ISBN (Electronic)9781728145969
    DOIs
    Publication statusPublished - 9 Dec 2019
    Event2019 IEEE International Ultrasonics Symposium, IUS 2019 - Glasgow, United Kingdom
    Duration: 6 Oct 20199 Oct 2019

    Publication series

    NameIEEE International Ultrasonics Symposium, IUS
    Volume2019-October
    ISSN (Print)1948-5719
    ISSN (Electronic)1948-5727

    Conference

    Conference2019 IEEE International Ultrasonics Symposium, IUS 2019
    Country/TerritoryUnited Kingdom
    CityGlasgow
    Period6/10/199/10/19

    Keywords

    • feature extraction
    • neural networks
    • sonar detection
    • sonar measurements

    Fingerprint

    Dive into the research topics of 'Neural Network-Based Detection of Ultrasonic Targets with Respect to Noise and Number of Sampling Positions'. Together they form a unique fingerprint.

    Cite this