K-means Clustering Based Pixel-wise Object Tracking

• Item type: Trans(1)
• 公開日: 2008-06-26
• タイトル: K-means Clustering Based Pixel-wise Object Tracking
• タイトル / 言語: en
• タイトル: K-means Clustering Based Pixel-wise Object Tracking
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: 総合論文（推薦）
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_6501
• 資源タイプ: journal article
• 著者所属: Faculty of System Engineering Wakayama University / Presently with the ISIR of Osaka University
• 著者所属: Faculty of System Engineering Wakayama University
• 著者所属: Faculty of System Engineering Wakayama University
• 著者所属: Faculty of System Engineering Wakayama University
• 著者所属(英): en
• 著者所属(英): Faculty of System Engineering, Wakayama University / Presently with the ISIR of Osaka University
• 著者所属(英): en
• 著者所属(英): Faculty of System Engineering, Wakayama University
• 著者所属(英): en
• 著者所属(英): Faculty of System Engineering, Wakayama University
• 著者所属(英): en
• 著者所属(英): Faculty of System Engineering, Wakayama University
• 著者名: Chunsheng, Hua; Haiyuan, Wu; Qian, Chen; Toshikazu, Wada
• 著者名(英): Chunsheng, Hua; Haiyuan, Wu; Qian, Chen; Toshikazu, Wada
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: This paper brings out a robust pixel-wise object tracking algorithm which is based on the K-means clustering algorithm. In order to achieve the robust object tracking under complex condition (such as wired objects cluttered background) a new reliability-based K-means clustering algorithm is applied to remove the noise background pixel (which is neigher similar to the target nor the background samples) from the target object. According to the triangular relationship among an unknown pixle and its two nearest cluster centers (target and background) the normal pixel (target or background one) will be assigned with high reliability value and correctly classified while noise pixels will be given low reliability value and ignored. A radial sampling method is also brought out for improving both the processing speed and the robustness of this algorithm. According to the proposed algorithm we have set up a real video-rate object tracking system. Through the extensive experiments the effectiveness and advantages of this reliability-based K-means tracking algorithm are confirmed.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: This paper brings out a robust pixel-wise object tracking algorithm which is based on the K-means clustering algorithm. In order to achieve the robust object tracking under complex condition (such as wired objects, cluttered background), a new reliability-based K-means clustering algorithm is applied to remove the noise background pixel (which is neigher similar to the target nor the background samples) from the target object. According to the triangular relationship among an unknown pixle and its two nearest cluster centers (target and background), the normal pixel (target or background one) will be assigned with high reliability value and correctly classified, while noise pixels will be given low reliability value and ignored. A radial sampling method is also brought out for improving both the processing speed and the robustness of this algorithm. According to the proposed algorithm, we have set up a real video-rate object tracking system. Through the extensive experiments, the effectiveness and advantages of this reliability-based K-means tracking algorithm are confirmed.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AA11560603
• 書誌情報: 情報処理学会論文誌コンピュータビジョンとイメージメディア（CVIM）; 巻 1, 号 1, p. 20-33, 発行日 2008-06-26
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 1882-7810
• 出版者 / 言語: ja
• 出版者: 情報処理学会