Unsupervised segmentation of unknown objects in complex environments

    Research output: Contribution to journalArticle

    8 Citations (Scopus)

    Abstract

    This paper presents a novel object segmentation approach for highly complex indoor scenes. Our approach starts with a novel algorithm which partitions the scene into distinct regions whose boundaries accurately conform to the physical object boundaries in the scene. Next, we propose a novel perceptual grouping algorithm based on local cues (e.g., 3D proximity, co-planarity, and shape convexity) to merge these regions into object hypotheses. Our extensive experimental evaluations demonstrate that our object segmentation results are superior compared to the state-of-the-art methods.
    Original languageEnglish
    Pages (from-to)805-829
    JournalAutonomous Robots
    Volume40
    Issue number5
    Early online date4 Sep 2015
    DOIs
    Publication statusPublished - Jun 2016

    Cite this

    @article{b6754db1d76548e08b1413417782d242,
    title = "Unsupervised segmentation of unknown objects in complex environments",
    abstract = "This paper presents a novel object segmentation approach for highly complex indoor scenes. Our approach starts with a novel algorithm which partitions the scene into distinct regions whose boundaries accurately conform to the physical object boundaries in the scene. Next, we propose a novel perceptual grouping algorithm based on local cues (e.g., 3D proximity, co-planarity, and shape convexity) to merge these regions into object hypotheses. Our extensive experimental evaluations demonstrate that our object segmentation results are superior compared to the state-of-the-art methods.",
    author = "U. Asif and Mohammed Bennamoun and Ferdous Sohel",
    year = "2016",
    month = "6",
    doi = "10.1007/s10514-015-9495-3",
    language = "English",
    volume = "40",
    pages = "805--829",
    journal = "Autonomous Robots",
    issn = "0929-5593",
    publisher = "Springer",
    number = "5",

    }

    Unsupervised segmentation of unknown objects in complex environments. / Asif, U.; Bennamoun, Mohammed; Sohel, Ferdous.

    In: Autonomous Robots, Vol. 40, No. 5, 06.2016, p. 805-829.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Unsupervised segmentation of unknown objects in complex environments

    AU - Asif, U.

    AU - Bennamoun, Mohammed

    AU - Sohel, Ferdous

    PY - 2016/6

    Y1 - 2016/6

    N2 - This paper presents a novel object segmentation approach for highly complex indoor scenes. Our approach starts with a novel algorithm which partitions the scene into distinct regions whose boundaries accurately conform to the physical object boundaries in the scene. Next, we propose a novel perceptual grouping algorithm based on local cues (e.g., 3D proximity, co-planarity, and shape convexity) to merge these regions into object hypotheses. Our extensive experimental evaluations demonstrate that our object segmentation results are superior compared to the state-of-the-art methods.

    AB - This paper presents a novel object segmentation approach for highly complex indoor scenes. Our approach starts with a novel algorithm which partitions the scene into distinct regions whose boundaries accurately conform to the physical object boundaries in the scene. Next, we propose a novel perceptual grouping algorithm based on local cues (e.g., 3D proximity, co-planarity, and shape convexity) to merge these regions into object hypotheses. Our extensive experimental evaluations demonstrate that our object segmentation results are superior compared to the state-of-the-art methods.

    U2 - 10.1007/s10514-015-9495-3

    DO - 10.1007/s10514-015-9495-3

    M3 - Article

    VL - 40

    SP - 805

    EP - 829

    JO - Autonomous Robots

    JF - Autonomous Robots

    SN - 0929-5593

    IS - 5

    ER -