Actions sketch: a novel action representation
Actions sketch: a novel action representation
复制标题
DOI：
10.1109/cvpr.2005.58
复制
发表时间：
2005-06
期刊：
影响因子：
--
通讯作者：
Alper Yilmaz;M. Shah
中科院分区：
文献类型：
--
作者：
Alper Yilmaz;M. Shah
在本文中，我们提出基于执行对象的形状和运动来建模一个动作。当物体在3D中执行动作时，物体外边界上的点在图像平面上投影为2D （x, y）轮廓。这些二维轮廓相对于时间的序列在（x, y, t）中产生一个时空体（STV），可以将其视为（x, y, t）空间中的三维物体。我们通过使用微分几何表面属性来识别捕获空间和时间属性的动作描述符来分析STV。一组动作描述符称为动作草图。我们方法的第一步是通过解决连续帧之间的点对应问题来生成STV。对应关系是用两步图理论方法确定的。生成STV后，通过分析STV的微分几何特性计算动作描述符。最后，利用这些描述符进行动作识别，这也被表述为图论问题。几个实验结果证明了我们的方法。
In this paper, we propose to model an action based on both the shape and the motion of the performing object. When the object performs an action in 3D, the points on the outer boundary of the object are projected as 2D (x, y) contour in the image plane. A sequence of such 2D contours with respect to time generates a spatiotemporal volume (STV) in (x, y, t), which can be treated as 3D object in the (x, y, t) space. We analyze STV by using the differential geometric surface properties to identify action descriptors capturing both spatial and temporal properties. A set of action descriptors is called an action sketch. The first step in our approach is to generate STV by solving the point correspondence problem between consecutive frames. The correspondences are determined using a two-step graph theoretical approach. After the STV is generated, actions descriptors are computed by analyzing the differential geometric properties of STV. Finally, using these descriptors, we perform action recognition, which is also formulated as graph theoretical problem. Several experimental results are presented to demonstrate our approach.