Action recognition via local descriptors and holistic features
Action recognition via local descriptors and holistic features
复制标题
DOI：
10.1109/cvprw.2009.5204255
复制
发表时间：
2009-06
期刊：
影响因子：
--
通讯作者：
Xinghua Sun;Ming-yu Chen;Alexander Hauptmann
中科院分区：
文献类型：
--
作者：
Xinghua Sun;Ming-yu Chen;Alexander Hauptmann
在本文中，我们提出了一个统一的动作识别框架融合局部描述符和整体特征。动机是局部描述符和整体特征强调动作的不同方面，并且适合于不同类型的动作数据库。提出的统一框架是基于帧差分，词袋和特征融合。我们提取两种局部描述符，即2D和3D SIFT特征描述符，都是基于2D SIFT兴趣点。我们应用Zernike矩提取两种整体特征，一种是基于单帧的，另一种是基于运动能量图像。我们在KTH和Weizmann数据库上进行动作识别实验，使用支持向量机。我们应用留一出和伪留N出设置，并比较我们提出的方法与国家的最先进的结果。实验表明，该方法是有效的。与其他方法相比，我们的方法更强大，更通用，更容易计算和更简单的理解。
In this paper we propose a unified action recognition framework fusing local descriptors and holistic features. The motivation is that the local descriptors and holistic features emphasize different aspects of actions and are suitable for the different types of action databases. The proposed unified framework is based on frame differencing, bag-of-words and feature fusion. We extract two kinds of local descriptors, i.e. 2D and 3D SIFT feature descriptors, both based on 2D SIFT interest points. We apply Zernike moments to extract two kinds of holistic features, one is based on single frames and the other is based on motion energy image. We perform action recognition experiments on the KTH and Weizmann databases, using Support Vector Machines. We apply the leave-one-out and pseudo leave-N-out setups, and compare our proposed approach with state-of-the-art results. Experiments show that our proposed approach is effective. Compared with other approaches our approach is more robust, more versatile, easier to compute and simpler to understand.