Wang Liang, Suter David
Monash University, Melbourne, Victoria, 3800, Australia.
IEEE Trans Image Process. 2007 Jun;16(6):1646-61. doi: 10.1109/tip.2007.896661.
In this paper, we learn explicit representations for dynamic shape manifolds of moving humans for the task of action recognition. We exploit locality preserving projections (LPP) for dimensionality reduction, leading to a low-dimensional embedding of human movements. Given a sequence of moving silhouettes associated to an action video, by LPP, we project them into a low-dimensional space to characterize the spatiotemporal property of the action, as well as to preserve much of the geometric structure. To match the embedded action trajectories, the median Hausdorff distance or normalized spatiotemporal correlation is used for similarity measures. Action classification is then achieved in a nearest-neighbor framework. To evaluate the proposed method, extensive experiments have been carried out on a recent dataset including ten actions performed by nine different subjects. The experimental results show that the proposed method is able to not only recognize human actions effectively, but also considerably tolerate some challenging conditions, e.g., partial occlusion, low-quality videos, changes in viewpoints, scales, and clothes; within-class variations caused by different subjects with different physical build; styles of motion; etc.
在本文中，我们学习用于动作识别任务的移动人体动态形状流形的显式表示。我们利用局部保持投影（LPP）进行降维，从而得到人体运动的低维嵌入。给定与动作视频相关联的一系列移动轮廓，通过LPP，我们将它们投影到低维空间中，以表征动作的时空特性，并保留大部分几何结构。为了匹配嵌入的动作轨迹，使用中位数豪斯多夫距离或归一化时空相关性作为相似性度量。然后在最近邻框架中实现动作分类。为了评估所提出的方法，我们在一个最近的数据集上进行了广泛的实验，该数据集包括九个不同受试者执行的十种动作。实验结果表明，所提出的方法不仅能够有效地识别人类动作，而且还能在相当程度上容忍一些具有挑战性的条件，例如部分遮挡、低质量视频、视角、尺度和服装的变化；不同身材的不同受试者引起的类内变化；运动风格等。
