计算机工程与应用2016，Vol.52Issue(20)：214-220,7.DOI:10.3778/j.issn.1002-8331.1604-0284
利用骨架模型和格拉斯曼流形的3D人体动作识别
3D Human action recognition method using joint point model and Grassmann manifold
摘要
Abstract
In order to effectively describe human skeleton movement by geometrical characteristics and build 3D human action recognition system, a modeling algorithm based on 3D bone joint is proposed. Firstly, Auto Regressive& Moving Average(ARMA)is used to describe each trajectory over time, which successfully captures the information of temporal and spatial motion. Meanwhile, the model view matrix generated subspace generated from view matrix of the model is being as a point on Grassmann manifold. Then, the mean of each class is described by learning Control Tangent(CT), during the mapping learning process, observed variables to all the control tangents is being formed Local Tangent Bundle(LTB). And the LTB manifold data points can be directly used to classify in the classifier. Finally, the proposed method uses the SVM classifier to complete training and classification. The effectiveness of the proposed algorithm is verified by experimental results on three databases MSR-action 3D, Weizmann and UCF-Kinect. Compared with several algorithms based on depth data, proposed algorithm not only has achieved the highest recognition rate, but also performs best in terms of latency, and the recognition rate is 97.91%when the number of frames is 30, so it achieves the desired recognition rate when the delay is high.关键词
动作识别/格拉斯曼流形/骨骼关节/回归和移动平均模型/控制切线Key words
action recognition/Grassmann manifold/bone joint/auto regressive&moving average/control tangent分类
信息技术与安全科学引用本文复制引用
吴珍珍,邓辉舫..利用骨架模型和格拉斯曼流形的3D人体动作识别[J].计算机工程与应用,2016,52(20):214-220,7.基金项目
湖南省教育厅科学研究青年项目（No.13B055）。 （）
