Due to the inherent unknown image deformation among the training and test samples, performance of the deep convolutional neural network (CNN) will be degraded for Inverse Synthetic Aperture Radar (ISAR) automatic target recognition. Meanwhile, traditional CNN only captures the local spatial information due to small receptive fields, thus, neglects the global information useful for recognition. To tackle these issues, this article proposes the attention-augmented deformation robust ISAR image recognition network, dubbed as ADRISAR-Net. The model adopts the inverse compositional spatial transformer for automatic image deformation adjustment, and performs joint local and global feature extractions by the attention-augmented CNN. Finally, the softmax classifier outputs the recognition results. The proposed ADRISAR-Net is end-to-end trainable, and achieves higher recognition accuracy for the four-satellite and three-airplane ISAR image data sets generated by electromagnetic computing.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Robust ISAR Target Recognition Based on ADRISAR-Net


    Beteiligte:
    Zhou, Xuening (Autor:in) / Bai, Xueru (Autor:in) / Wang, Li (Autor:in) / Zhou, Feng (Autor:in)


    Erscheinungsdatum :

    01.12.2022


    Format / Umfang :

    5455610 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Feature Distribution Transfer Learning for Robust Few-Shot ISAR Space Target Recognition

    Xue, Ruihang / Bai, Xueru / Yang, Minjia et al. | IEEE | 2024


    Target Recognition by Means of Polarimetric ISAR Images

    Martorella, M / Giusti, E / Demi, L et al. | IEEE | 2011


    Automatic recognition of ISAR ship images

    Musman, S. / Kerr, D. / Bachmann, C. | IEEE | 1996


    Automatic recognition of ISAR ship images

    Musman, S. / Kerr, D. / Bachmann, C. | Tema Archiv | 1996