This research compares the performance improvements of image-based sonar target classification algorithms when they are adapted to changing clutter environments. The distribution of seabed pixels in the sonar imagery is modeled as a correlated, K-distributed random variable allowing for a quantitative representation of seabed environments in the various testing scenarios. Parameterized environments comprising various target-like seabed textures are generated synthetically and used to examine adaptive classification performance. Results demonstrate that optimizing classifier parameters respective to specific environments improves overall classification performance compared to optimizing classifier parameters against a pooled dataset that includes all possible environments.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    In Situ Adaptive Feature Extraction for Underwater Target Classification


    Contributors:


    Publication date :

    2007-10-01


    Size :

    614210 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    An adaptive underwater target classification system

    Azimi-Sadjadi, M.R. / Yao, D. / Dobeck, G.J. | Tema Archive | 1999


    Underwater Image Processing and Target Classification

    Desai, M. N. / Pien, H. H. / Bello, M. G. et al. | British Library Conference Proceedings | 1995


    Adaptive classification of underwater transients

    Hermand, J.P. / Nicolas, P. | Tema Archive | 1989


    Autonomous underwater robot propeller fault feature extraction method

    ZHANG MINGJUN / LIU XING / YU DACHENG et al. | European Patent Office | 2020

    Free access