NSCT-based fusion method for forward-looking sonar image mosaic

Jian Zhang, Ferdous Sohel, Mohammed Bennamoun, Hongyu Bian, Senjian An

    Research output: Contribution to journalArticle

    2 Citations (Scopus)
    180 Downloads (Pure)

    Abstract

    To generate a seamless mosaic of a forward-looking sonar (FLS) video sequence, this study proposes a novel fusion method for FLS image mosaic, which includes two main steps from coarse to fine. In the coarse fusion step, the source images are first decomposed into multi-scale sub-bands using the non-subsampled contourlet transform (NSCT), then the sub-bands of the source images are merged, based on the Gabor energy and the local contrast for low and high frequency sub-bands, respectively, to generate the fused sub-bands which are used to produce the fused image by inverse NSCT. In the fine fusion step, a decision map is used to choose the pixels of the fine fused image from the coarsely fused image or one of the source images. This decision map is first constructed by measuring the similarity of the coarsely fused image to the source images, and then processed by a morphological post-processing technique to ensure its continuity and smoothness. Extensive experiments on FLS image fusion and mosaic have been conducted to demonstrate the effectiveness and the superiority of the proposed technique using both a subjective evaluation and objective metrics.

    Original languageEnglish
    Pages (from-to)1512-1522
    Number of pages11
    JournalIET Radar, Sonar and Navigation
    Volume11
    Issue number10
    DOIs
    Publication statusPublished - 1 Oct 2017

    Fingerprint

    Sonar
    Image fusion
    Pixels
    Processing
    Experiments

    Cite this

    Zhang, Jian ; Sohel, Ferdous ; Bennamoun, Mohammed ; Bian, Hongyu ; An, Senjian. / NSCT-based fusion method for forward-looking sonar image mosaic. In: IET Radar, Sonar and Navigation. 2017 ; Vol. 11, No. 10. pp. 1512-1522.
    @article{dbc9bbc3660c4c5387e4bc1a9c12b875,
    title = "NSCT-based fusion method for forward-looking sonar image mosaic",
    abstract = "To generate a seamless mosaic of a forward-looking sonar (FLS) video sequence, this study proposes a novel fusion method for FLS image mosaic, which includes two main steps from coarse to fine. In the coarse fusion step, the source images are first decomposed into multi-scale sub-bands using the non-subsampled contourlet transform (NSCT), then the sub-bands of the source images are merged, based on the Gabor energy and the local contrast for low and high frequency sub-bands, respectively, to generate the fused sub-bands which are used to produce the fused image by inverse NSCT. In the fine fusion step, a decision map is used to choose the pixels of the fine fused image from the coarsely fused image or one of the source images. This decision map is first constructed by measuring the similarity of the coarsely fused image to the source images, and then processed by a morphological post-processing technique to ensure its continuity and smoothness. Extensive experiments on FLS image fusion and mosaic have been conducted to demonstrate the effectiveness and the superiority of the proposed technique using both a subjective evaluation and objective metrics.",
    author = "Jian Zhang and Ferdous Sohel and Mohammed Bennamoun and Hongyu Bian and Senjian An",
    year = "2017",
    month = "10",
    day = "1",
    doi = "10.1049/iet-rsn.2017.0053",
    language = "English",
    volume = "11",
    pages = "1512--1522",
    journal = "IET Radar, Sonar & Navigation",
    issn = "1751-8784",
    publisher = "Inst Engineering Technology-IET",
    number = "10",

    }

    NSCT-based fusion method for forward-looking sonar image mosaic. / Zhang, Jian; Sohel, Ferdous; Bennamoun, Mohammed; Bian, Hongyu; An, Senjian.

    In: IET Radar, Sonar and Navigation, Vol. 11, No. 10, 01.10.2017, p. 1512-1522.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - NSCT-based fusion method for forward-looking sonar image mosaic

    AU - Zhang, Jian

    AU - Sohel, Ferdous

    AU - Bennamoun, Mohammed

    AU - Bian, Hongyu

    AU - An, Senjian

    PY - 2017/10/1

    Y1 - 2017/10/1

    N2 - To generate a seamless mosaic of a forward-looking sonar (FLS) video sequence, this study proposes a novel fusion method for FLS image mosaic, which includes two main steps from coarse to fine. In the coarse fusion step, the source images are first decomposed into multi-scale sub-bands using the non-subsampled contourlet transform (NSCT), then the sub-bands of the source images are merged, based on the Gabor energy and the local contrast for low and high frequency sub-bands, respectively, to generate the fused sub-bands which are used to produce the fused image by inverse NSCT. In the fine fusion step, a decision map is used to choose the pixels of the fine fused image from the coarsely fused image or one of the source images. This decision map is first constructed by measuring the similarity of the coarsely fused image to the source images, and then processed by a morphological post-processing technique to ensure its continuity and smoothness. Extensive experiments on FLS image fusion and mosaic have been conducted to demonstrate the effectiveness and the superiority of the proposed technique using both a subjective evaluation and objective metrics.

    AB - To generate a seamless mosaic of a forward-looking sonar (FLS) video sequence, this study proposes a novel fusion method for FLS image mosaic, which includes two main steps from coarse to fine. In the coarse fusion step, the source images are first decomposed into multi-scale sub-bands using the non-subsampled contourlet transform (NSCT), then the sub-bands of the source images are merged, based on the Gabor energy and the local contrast for low and high frequency sub-bands, respectively, to generate the fused sub-bands which are used to produce the fused image by inverse NSCT. In the fine fusion step, a decision map is used to choose the pixels of the fine fused image from the coarsely fused image or one of the source images. This decision map is first constructed by measuring the similarity of the coarsely fused image to the source images, and then processed by a morphological post-processing technique to ensure its continuity and smoothness. Extensive experiments on FLS image fusion and mosaic have been conducted to demonstrate the effectiveness and the superiority of the proposed technique using both a subjective evaluation and objective metrics.

    UR - http://www.scopus.com/inward/record.url?scp=85029561433&partnerID=8YFLogxK

    U2 - 10.1049/iet-rsn.2017.0053

    DO - 10.1049/iet-rsn.2017.0053

    M3 - Article

    VL - 11

    SP - 1512

    EP - 1522

    JO - IET Radar, Sonar & Navigation

    JF - IET Radar, Sonar & Navigation

    SN - 1751-8784

    IS - 10

    ER -