电子学报2011，Vol.39Issue(8)：1751-1756,6.
基于时空特征点的非监督姿态建模和行为识别的算法研究
Research of Unsupervised Posture Modeling and Action Recognition Based on Spatial-Temporal Interesting Points
摘要
Abstract
Posture modeling is critical for action description and recognition, a posture modeling and action recognition method is proposed in this paper.Spatial Temporal Interesting Points (STTPs) are extracted from learning samples,in fact,one posture consists of a set of STIPs; a unsupervised clustering method is adopted to classify salient postures from these posture samples, then a GMM model is established for each clustering result; transitional probability among salient postures are calculated, and a Visible state Markov ModeL(VMM) is learnt to describe various actions. BL gram method is put forward for action recognition, Extensive experiments are conducted and the results prove its robustness and validity.关键词
行为识别/姿态建模/时空特征点/二元语法模型Key words
action recogmtion/posture modeling/spatial-temporal interesting points /bi_ gram分类
天文与地球科学引用本文复制引用
王传旭,刘云,厉万庆..基于时空特征点的非监督姿态建模和行为识别的算法研究[J].电子学报,2011,39(8):1751-1756,6.基金项目
山东省自然科学基金(No.ZR2010FL007) （No.ZR2010FL007）
山东省高等学校科技计划项目(No.J10LG23) （No.J10LG23）
