基于多特征融合的分块采样粒子滤波算法在人体姿态跟踪中的应用  

Human Pose Tracking Based on Partitioned Sampling Particle Filter and Multiple Cues Fusion

作　　者：刘晨光[1] 刘家锋[1] 黄剑华[1] 唐降龙[1] 

机构地区：[1]哈尔滨工业大学计算机科学与工程系模式识别中心,哈尔滨150001

出　　处：《计算机研究与发展》2011年第12期2359-2368,共10页Journal of Computer Research and Development

基　　金：国家自然科学基金项目(60672090);哈尔滨市科技创新人才研究专项基金项目(2006RFXXG013)

摘　　要：针对单目视频中无标记点的人体姿态跟踪问题,在分块采样粒子滤波算法框架下使用颜色(color)、边缘(edge)和运动(motion)特征相融合构造粒子权值度量函数,并根据肢体间的遮挡情况自适应地选择不同模板和图像特征来进行计算,增加了跟踪过程的鲁棒性,而且成功解决了人体运动中发生的多种形式的自遮挡问题.另外,该方法还提出了一种带约束的2维人体模型,并在此模型基础上使用一种改进的BP算法进行权值的传播,使得在一个关节点上能够同时应用多个人体约束.实验中所用测试视频(室内和室外拍摄)包含复杂背景和运动,实验结果表明该方法具有较强的鲁棒性和较高的跟踪精度.In this paper, we develop a method for tracking markless human pose in monocular video sequences. The number of required particles will grow exponentially when particle filter is applied to high dimensional tracking problems such as tracking human body poses, and particle filter with partitioned sampling is adopted to deal with this problem. We design a 2D human body model with constraints, and put forward a new adaptive way for fusing color, edge and motion cues together to construct the weighing function of particles. When calculating the likelihood function for each particle, we adaptively choose different templates and features according to the occlusion relationship among correlated body limbs. Thus, the proposed algorithm is capable of dealing with complicated occlusions among body limbs. In addition, we introduce a simplified belief propagation （BP） method to propagate the weights of limb observations to the corresponding particles along the edges of the body model, which can make a set of particles carry multiple constraints. Then we test the method on three video sequences which contain heavy background occlusion, complex human motion and self-occlusion, and the experimental results show that our method is effective and robust.

关 键 词：人体姿态跟踪 人体模型 粒子滤波 分块采样 多特征融合 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]