Learning Actionlet Ensemble for 3D Human Action Recognition
Learning Actionlet Ensemble for 3D Human Action Recognition
复制标题
DOI：
10.1109/tpami.2013.198
复制
发表时间：
2014-05-01
影响因子：
23.6
通讯作者：
Yuan, Junsong
中科院分区：
文献类型：
--
作者：
Wang, Jiang;Liu, Zicheng;Yuan, Junsong
人体动作识别是一项重要而又具有挑战性的任务。人类行为通常涉及人与物体的交互、高度清晰的运动、高度的类内变化和复杂的时间结构。最近开发的商品深度传感器通过提供场景的3D深度数据开辟了处理这个问题的新可能性。这些信息不仅促进了一个相当强大的人体运动捕捉技术，而且还可以有效地建模人与对象的交互和类内变化。在本文中，我们提出了一种新的actionlet集成模型，它代表了人类关节的一个子集的相互作用，来描述人类的行动。该模型对噪声具有鲁棒性，对平移和时间错位具有不变性，能够同时表征人体运动和人-物交互。我们评估所提出的方法上三个具有挑战性的动作识别数据集捕获的Kinect设备，多视图动作识别数据集捕获的Kinect设备，和一个动作捕捉系统捕获的数据集。实验结果表明，该方法实现了上级性能的国家的最先进的算法。
Human action recognition is an important yet challenging task. Human actions usually involve human-object interactions, highly articulated motions, high intra-class variations, and complicated temporal structures. The recently developed commodity depth sensors open up new possibilities of dealing with this problem by providing 3D depth data of the scene. This information not only facilitates a rather powerful human motion capturing technique, but also makes it possible to efficiently model human-object interactions and intra-class variations. In this paper, we propose to characterize the human actions with a novel actionlet ensemble model, which represents the interaction of a subset of human joints. The proposed model is robust to noise, invariant to translational and temporal misalignment, and capable of characterizing both the human motion and the human-object interactions. We evaluate the proposed approach on three challenging action recognition datasets captured by Kinect devices, a multiview action recognition dataset captured with Kinect device, and a dataset captured by a motion capture system. The experimental evaluations show that the proposed approach achieves superior performance to the state-of-the-art algorithms.