| 摘要: |
| 提出了一种基于流形学习与隐条件随机场(hidden conditional random fields,简称HCRF)的动作识别方法.算法提取人体剪影作为输入特征,采用有监督的保持邻域嵌入(neighborhood preserving embedding,简称NPE)的子空间学习算法获得高维运动特征的低维流形表示,基于HCRF建模运动特征与动作语义之间的映射关系.在降维过程中,通过保持数据的局部邻接关系,NPE可以获取动作特征在低维流形空间上的本质分布特性.与HMM(hidden Markov model)等产生式模型相比,HCRF侧重从样本数据中抽取共有特征以获取正确的分类边界,不需要假定观测过程条件独立,可以更加自然地对动作的时空邻域关系进行建模.实验结果表明,即便对于特征差异较大或存在噪声干扰的动作序列,算法也能取得较好的识别效果. |
| 关键词: 动作识别 流形学习 判别式模型 隐条件随机场 |
| DOI： |
| 分类号: |
| 基金项目:Supported by the National Natural Science Foundation of China under Grant No.60675021 (国家自然科学基金); the National High-Tech Research and Development Plan of China under Grant No.2006AA01Z120 (国家高技术研究发展计划(863) |
|
| Human Action Recognition Using Manifold Learning and Hidden Conditional Random Fields |
|
LIU Fa-Wang,JIA Yun-De
|
| Abstract: |
| This paper presents a probabilistic method of human action recognition based on manifold learning and Hidden Conditional Random Fields (HCRF). A supervised Neighborhood Preserving Embedding (NPE) is employed for dimensionality reduction by preserving the local neighborhood structure on the data manifold. Most existing approaches to action recognition use a Hidden Markov Model or suitable variant to model actions; a significant limitation of these models is the requirements of conditional independence of observations. In addition, generative models are selected to maximize the likelihood of generating all the examples of a given class and may not uncover the distinctive configuration that sets one class uniquely against others. HCRF relaxes the independence assumption and classifies actions in a discriminative hidden-state formulation. Experimental results on a recent database have demonstrated that this approach can recognize human actions accurately with temporal, intra- and inter-person variations even when noise and other factors such as partial occlusion exist. |
| Key words: action recognition manifold learning discriminative model hidden conditional random fields |
