Action Recognition by Fusing Spatial-Temporal Appearance and the Local Distribution of Interest Points
Action Recognition by Fusing Spatial-Temporal Appearance and the Local Distribution of Interest Points
复制标题
DOI：
10.2991/icfcce-14.2014.19
复制
发表时间：
2014-03
期刊：
影响因子：
--
通讯作者：
Mengmeng Lu;Liang Zhang
中科院分区：
文献类型：
--
作者：
Mengmeng Lu;Liang Zhang
传统的词袋（BOW）算法只考虑视觉词的频率，而忽略了它们的时空相关性。已经设计了许多方法来弥补这一缺陷。在本文中，我们提出了一个新的描述符来描述每个点的局部时空分布信息。这个新的描述符，结合HOG3D，被用来描述人类的行为。引入K-means聚类算法生成视觉词的码本，在BOW模型下实现两个特征的融合。最后，利用支持向量机（SVM）进行动作识别。我们在标准Weizmann和KTH动作数据集上广泛测试了我们的方法。结果表明了该方法的有效性和良好的性能。索引术语-动作识别，BOW， SVM，局部时空分布。
The traditional Bag of Words (BOW) algorithm considers the frequency of visual words only, whereas it ignores their spatial and temporal correlations. Many methods have been designed to remedy this defect .In this paper, we propose a new descriptor to describe the local spatio-temporal distribution information of each point. This new descriptor, combined with HOG3D, is used to describe human actions. K-means clustering algorithm is introduced to generate codebook of visual words, achieving the integration of two features under the BOW model. Finally, Support Vector Machine (SVM) is used for action recognition. We extensively test our method on the standard Weizmann and KTH action datasets. The results show its validity and good performance. Index Terms - Action recognition, BOW, SVM, Local spatio- temporal distribution.