Separation of multiple objects in motion images by clustering

Kohei Inoue, Kiichi Urahama

    研究成果: 会議への寄与タイプ学会誌査読

    12 被引用数 (Scopus)

    抄録

    A method is presented for estimating the number of rigid objects moving independently and separating the feature points tracked on a motion image into individual objects by clustering. In the method, feature points are firstly mapped into a low dimensional space suitable for grouping them into each object. In this low dimensional space, clusters are extracted sequentially by a graph spectral method. The number of clusters i.e. objects can be estimated on the basis of the variation in the cohesiveness of extracted clusters. We show by numerical experiments that the present method is robust to moderate measurement noises and distortion by perspective projection.

    本文言語英語
    ページ219-224
    ページ数6
    出版ステータス出版済み - 1月 1 2001
    イベント8th International Conference on Computer Vision - Vancouver, BC, 米国
    継続期間: 7月 9 20017月 12 2001

    その他

    その他8th International Conference on Computer Vision
    国/地域米国
    CityVancouver, BC
    Period7/9/017/12/01

    !!!All Science Journal Classification (ASJC) codes

    • ソフトウェア
    • コンピュータ ビジョンおよびパターン認識

    フィンガープリント

    「Separation of multiple objects in motion images by clustering」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

    引用スタイル