Discriminative human action recognition in the learned hierarchical manifold space
Discriminative human action recognition in the learned hierarchical manifold space
复制标题
学习的分层流形空间中的判别性人类行为识别
DOI：
10.1016/j.imavis.2009.08.003
复制
发表时间：
2010-05-01
影响因子：
4.7
通讯作者：
Jia, Yunde
中科院分区：
文献类型：
--
作者：
Han, Lei;Wu, Xinxiao;Jia, Yunde
在本文中，我们提出了一个分层判别的方法来识别人体动作。它包括特征提取与相互运动模式分析和歧视性的行动建模在分层流形空间。分层高斯过程隐变量模型（HGPLVM）学习的分层流形空间中提取的运动模式。级联CRF也被提出来估计相应的流形子空间中的运动模式，并且训练好的SVM分类器预测当前观察的动作标签。使用运动捕捉数据，我们测试我们的方法，并评估身体部位对人体动作识别的影响。我们的合成图像的测试集上的结果也展示了鲁棒性。(C)2009 Elsevier B.V.保留所有权利。
In this paper, we propose a hierarchical discriminative approach for human action recognition. It consists of feature extraction with mutual motion pattern analysis and discriminative action modeling in the hierarchical manifold space. Hierarchical Gaussian Process Latent Variable Model (HGPLVM) is employed to learn the hierarchical manifold space in which motion patterns are extracted. A cascade CRF is also presented to estimate the motion patterns in the corresponding manifold subspace, and the trained SVM classifier predicts the action label for the current observation. Using motion capture data, we test our method and evaluate how body parts make effect on human action recognition. The results on our test set of synthetic images are also presented to demonstrate the robustness. (C) 2009 Elsevier B.V. All rights reserved.