The main bottleneck limiting the use of traditional ship classification methods is the manual extraction of ship images before classification. To solve this problem, a ship classification method based on a convolutional neural network (CNN) is proposed in this paper. A CNN model can autonomously extract image features, avoiding complex feature selection and extraction processes. In view of the problem of an insufficient number of ship samples, transfer learning was applied to train the model using the ImageNet dataset, effectively alleviating the over-fitting phenomenon in the training process. Experiments showed that the CNN model had an accuracy of 98% in ship classification using the SHIP-3 dataset. The CNN was robust to external environmental challenges – such as illumination – the accuracy of ship classification in foggy and night-time conditions reaching 75%, greatly exceeding the performance of traditional machine learning algorithms.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Ship classification based on convolutional neural networks


    Beteiligte:
    Yang, Yang (Autor:in) / Ding, Kaifa (Autor:in) / Chen, Zhuang (Autor:in)

    Erschienen in:

    Ships and Offshore Structures ; 17 , 12 ; 2715-2721


    Erscheinungsdatum :

    02.12.2022


    Format / Umfang :

    7 pages




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Unbekannt




    Ship Model Recognition Based on Convolutional Neural Networks

    Xing, Shihong / Zhang, Shaokang | British Library Conference Proceedings | 2018



    Ship object detection in remote sensing images using convolutional neural networks

    Huang, Jie / Jiang, Zhiguo / Zhang, Haopeng et al. | British Library Online Contents | 2017


    Covert photo classification by deep convolutional neural networks

    Zuo, H. / Lang, H. / Blasch, E. et al. | British Library Online Contents | 2017