基于典型相关性分析的稀疏表示目标追踪  

Canonical Correlation Analysis Based Sparse Representation Model for Robust Visual Tracking

作　　者：康彬 曹雯雯 颜俊[3] 张索非[1] KANG Bin;CAO Wenwen;YAN Jun;ZHANG Suofei(School of Internet of Things, Nanjing University Posts and Telecommunications, Nanjing 210003, China;Jiangsu Engineering Research Center of Communication and Network Technology, Nanjing University of Posts and Telecommunications, Nanjing 210003, China;School of Communication and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China)

机构地区：[1]南京邮电大学物联网学院,南京210003 [2]南京邮电大学江苏省通信与网络技术工程研究中心,南京210003 [3]南京邮电大学通信与信息工程学院,南京210003

出　　处：《电子与信息学报》2018年第7期1619-1626,共8页Journal of Electronics & Information Technology

基　　金：国家自然科学基金(61771256;61471205;61771258;61701252);江苏省自然科学基金青年基金(BK20170915);江苏省高校自然科学面上项目(17KJD510005);南京邮电大学引进人才启动基金(NY 216023);南京邮电大学江苏省通信与网络技术工程研究中心开放课题~~

摘　　要：传统稀疏表示目标追踪算法首先通过粒子滤波方法对状态粒子进行采样,然后利用灰度特征表征采样粒子观测向量,最后构造基于观测向量的稀疏表示模型来进行目标追踪。与传统稀疏表示模型不同,该文提出一个基于典型相关性分析的稀疏表示模型,此模型首先使用两种特征来表征粒子观测向量,然后对两种观测向量的子空间投影结果进行稀疏建模。所构建的模型可通过在子空间中探究特征间的相关性来实现不同特征的互补融合,提升稀疏表示模型在复杂监控环境下的鲁棒性。In traditional sparse representation based visual tracking, particle sampling is first achieved by particle filter method. Then the particle observations are represented by intensity feature. Finally, the visual tracking is achieved by the intensity feature based sparse representation model. Different from traditional sparse representation model, a canonical correlation analysis based sparse representation model is proposed in this paper. The proposed model first uses two kinds of features to represent the particle observations, then, the projections of particle observations are used to build the sparse representation model. The advantage of the proposed model lies in that it can give a proper multi-feature fusing through canonical correlation analysis, which explores the relation between two features in a latent common subspace.

关 键 词：目标追踪 稀疏表示 典型相关性分析 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]