系统工程与电子技术

• 软件、算法与仿真 • 上一篇    下一篇

基于图的半监督目标跟踪

毛盾, 邢昌风, 黎铁冰, 黄傲林   

  1. 海军工程大学电子工程学院, 湖北 武汉 430033
  • 出版日期:2016-01-30 发布日期:2010-01-03

Graph based semi-supervised learning for object tracking

MAO Dun, XING Chang-feng, LI Tie-bing, HUANG Ao-ling   

  1. Electronics Engineering College, Naval University of Engineering, Wuhan 430033, China
  • Online:2016-01-30 Published:2010-01-03

摘要:

针对目标跟踪方法中有限的目标样本对监督分类器的影响,提出一种基于图的在线半监督跟踪方法。首先,根据前几帧的跟踪结果分别提取反映目标当前状态和长期状态的特征以及背景的特征,共同组成标记样本集,再在当前帧通过运动模型采样候选区域作为未标记样本集。然后将每个样本分割成若干部件,以所有样本对应部件构成的集合为节点构建一张图,并独立在每张图上应用基于图的半监督分类方法给出判决分数,各部件的判决结果最终被融合并给出跟踪结果。最后,用新的跟踪结果更新标记样本集。实验证明该方法对目标和背景的动态变化有很强的鲁棒性,满足实时性要求。

Abstract:

In order to alleviate the effect of limited labeled instances on the supervised classifier in object tracking, a new method based on the graph based semisupervised learning framework is proposed for object tracking. Firstly, two kinds of positive instances representing the long term and shortterm information about the object respectively and negative instances representing the background are extracted around the tracking results of the previous few frame. Meanwhile, the candidates are sampled by a particle filter as unlabeled instances. Secondly, each labeled or unlabeled instance is divided into several overlapped patches with a spatial layout. The corresponding patches of all these instances are gathered together to construct a graph. The similarity scores of the candidates are evaluated independently over each graph. Finally, these similarities from all graphs are combined to find the tracking result and update the graphs. Empirical results on challenging video sequences demonstrate the superior performance of the proposed method in robustness and accuracy to state of the art methods in the literature.