Online mixture of random naïve bayes tracker combined texture with shape feature

作者：Guo Pengyu; Su Ang; Zhang Hongliang; Zhang Xiaohu^*; Yu Qifeng

来源：Acta Optica Sinica, 2015, 35(3).

DOI：10.3788201535.0315002

• Bayes
• Homogeneous method
• Illumination changes
• Partial occlusions
• Posterior probability
• Pyramid histogram of oriented gradients
• Shape features
• Visual tracker

Based on the idea of machine learning and the sufficient appearance, a mixture random Naïve Bayes visual tracker with online texture and shape feature selection is proposed. The texture and shape of global and local region is described with binary feature of intensity and pyramid histogram of oriented gradients using normalized spatial pyramid. An online mixture of Naïve Bayes classifier is designed and realized according to binary and multimodel description. The classifier predicts the class posterior probability to generate the confidence map, then the tracker analyzes the confidence map to track the object, learns the appearance with maximum likelihood estimation, and selects the feature with cross validation. Compared with homogeneous methods, the tracker is evaluated with performance and complexity based on benchmarks. The experimental results show that the tracker has certain adaption to illumination change and partial occlusion, and fast execution speed as well as little memory space.

• 出版日期2015