文献类型：会议论文

英文题名：Graph Based Visual Object Tracking

作者：Zhou Guanling[1];Wang Yuping[1];Dong Nanping[1]

第一作者：Zhou Guanling

通讯作者：Zhou, GL[1]

机构：[1]Beijing Union Univ, Coll Automat, Beijing, Peoples R China

第一机构：北京联合大学城市轨道交通与物流学院

通讯机构：[1]corresponding author), Beijing Union Univ, Coll Automat, Beijing, Peoples R China.|[1141751]北京联合大学城市轨道交通与物流学院;[11417]北京联合大学;

会议论文集：2nd ISECS International Colloquium on Computing, Communication, Control and Management (CCCM 2009)

会议日期：AUG 08-09, 2009

会议地点：Sanya, PEOPLES R CHINA

语种：英文

外文关键词：visual object; tracking algorithm; send-supervised method; multi-modal

摘要：Object tracking is viewed as a two-class "one-versus-rest" classification problem, in which the sample distribution of the target is approximately Gaussian while the background samples are often multi-modal. Based on these special properties, we model the visual appearance via graph approach, which is a semi-supervised approach. The topology structure of graph is carefully designed to reflect the properties of the sample's distribution. The confidence of sample's label is computed via random walk with restart (RWR). The primary advantage of our algorithm is that it keeps the appearance of object via semi-supervised method. Experimental results demonstrate that, compared with two state of the art methods, the proposed tracking algorithm is more effective, especially in dynamically changing and clutter scenes.