首页 | 本学科首页   官方微博 | 高级检索  
     

基于流形学习与隐条件随机场的人体动作识别
引用本文:刘法旺,贾云得.基于流形学习与隐条件随机场的人体动作识别[J].软件学报,2008,19(Z1):69-77.
作者姓名:刘法旺  贾云得
作者单位:北京理工大学 计算机科学技术学院 智能信息技术北京市重点实验室 100081;北京理工大学 计算机科学技术学院 智能信息技术北京市重点实验室 100081
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)
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
收稿时间:5/1/2008 12:00:00 AM
修稿时间:2008/11/25 0:00:00

Human Action Recognition Using Manifold Learning and Hidden Conditional Random Fields
LIU Fa-Wang and JIA Yun-De.Human Action Recognition Using Manifold Learning and Hidden Conditional Random Fields[J].Journal of Software,2008,19(Z1):69-77.
Authors:LIU Fa-Wang and 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.
Keywords:action recognition  manifold learning  discriminative model  hidden conditional random fields
点击此处可从《软件学报》浏览原始摘要信息
点击此处可从《软件学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号