Graph Based Discriminative Learning for Robust and Efficient Object Tracking

Object tracking is viewed as a two-class 'one-versusrest' classification problem, in which the sample distribution of the target is approximately Gaussian while the background samples are often multimodal. Based on these special properties, we propose a graph embedding based discriminative learning method, in which the topology structures of graphs are carefully designed to reflect the properties of the sample distributions. This method can simultaneously learn the subspace of the target and its local discriminative structure against the background. Moreover, a heuristic negative sample selection scheme is adopted to make the classification more effective. In tracking procedure, the graph based learning is embedded into a Bayesian inference framework cascaded with hierarchical motion estimation, which significantly improves the accuracy and efficiency of the localization. Furthermore, an incremental updating technique for the graphs is developed to capture the changes in bot...

• Type: Conference
• Year: 2007
• Where: ICCV
• Authors: Xiaoqin Zhang, Weiming Hu, Stephen J. Maybank, Xi Li
• Keywords: Computer Vision, Discriminative Learning Method, Graph Based Learning, Heuristic Negative Sample, ICCV 2007, Incremental Updating Technique, Local Discriminative Structure