This article proposes an automatic identification system (AIS) data aided Rayleigh constant false alarm rate (AIS-RCFAR) ship detection algorithm of multiple-target environment in synthetic aperture radar (SAR) images. This method aims to improve the detection performance in complex environment with the aid of AIS data. Traditional CFAR detectors generally use all the samples in the local background window for parameter estimation. However, in multiple-target environment, clutter edges and transition areas, due to the interference of the high-intensity outliers, such as target pixels, ghosts, and other interfering pixels, the parameters are often overestimated, causing degradation of the detection performance. Aiming at solving this problem, AIS-RCFAR designs an adaptive-threshold based clutter trimming method with an adaptive-trimming-depth aided by AIS data to effectively eliminate the high-intensity outliers in the local background window while greatly sustaining the real sea clutter samples. Maximum-likelihood-estimator with a closed-form solution is proposed to precisely estimate the parameters using the adaptively-trimmed clutter samples, the probability density function of the sea clutter following Rayleigh distribution can be accurately modeled. AIS-RCFAR greatly enhances the detection rate in both homogeneous and nonhomogeneous multiple-target environment, it also achieves a very low false alarm rate. In addition, the whole procedure of AIS-RCFAR is simple and efficient. Simulated data and real SAR images with corresponding matched AIS data are used for experiments to validate the superiority and feasibility of AIS-RCFAR.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    AIS Data Aided Rayleigh CFAR Ship Detection Algorithm of Multiple-Target Environment in SAR Images


    Beteiligte:
    Ai, Jiaqiu (Autor:in) / Pei, Zhilin (Autor:in) / Yao, Baidong (Autor:in) / Wang, Zhaocheng (Autor:in) / Xing, Mengdao (Autor:in)


    Erscheinungsdatum :

    2022-04-01


    Format / Umfang :

    9456183 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    DL-CFAR: A Novel CFAR Target Detection Method Based on Deep Learning

    Lin, Chia-Hung / Lin, Yu-Chien / Bai, Yue et al. | IEEE | 2019


    Fuzzy statistical normalization CFAR detector for non-rayleigh data

    Yanwei Xu, / Chaohuan Hou, / Shefeng Yan, et al. | IEEE | 2015


    Automatic Ship Detection Using CFAR Algorithm for Quad-Pol UAV-SAR Imagery

    Mittal, Harshal / Joshi, Ashish | Springer Verlag | 2023


    A Performance Comparison of a CFAR Ship Detection Algorithm Using Envisat, RadarSat, COSMO-SkyMed and TerraSAR-X Images

    Lorenzzetti, J.A. / Paes, R.L. / Gherardi, D.M. et al. | British Library Conference Proceedings | 2010


    2-D CFAR Procedure of Multiple Target Detection for Automotive Radar

    Li, Sen / Bi, Xin / Huang, Libo et al. | British Library Conference Proceedings | 2017