Motion history histograms for human action recognition
Motion history histograms for human action recognition
复制标题
用于人类动作识别的运动历史直方图
DOI：
10.1007/978-1-84800-304-0_7
复制
发表时间：
2009
期刊：
影响因子：
--
通讯作者：
Christopher Bailey
中科院分区：
文献类型：
--
作者：
Hongying Meng;Nick E. Pears;M. Freeman;Christopher Bailey
在这一章中，提出了一个紧凑的人类行为识别系统，以期在安全系统、人机交互和智能环境中应用。首先，提出了一种基于支持向量机分类器和紧凑运动特征的嵌入式人体动作识别系统框架。其次，针对已有的运动历史图像的局限性，引入了一种新的运动历史直方图特征来表示视频中的运动信息。MHH不仅提供了丰富的运动信息，而且计算成本也很低。我们将MHI和MHH结合为系统的低维特征向量，与使用无跟踪时间模板运动表示的同类方法相比，在人体动作识别中取得了更好的性能。最后，在可重构的嵌入式计算机视觉系统上实现了一个简单的基于支持向量机和MHI的手势实时识别系统。
In this chapter, a compact human action recognition system is presented with a view to applications in security systems, human-computer interaction, and intelligent environments. There are three main contributions: Firstly, the framework of an embedded human action recognition system based on a support vector machine (SVM) classifier and some compact motion features has been presented. Secondly, the limitations of the well-known motion history image (MHI) are addressed and a new motion history histograms (MHH) feature is introduced to represent the motion information in the video. MHH not only provides rich motion information, but also remains computationally inexpensive. We combine MHI and MHH into a low-dimensional feature vector for the system and achieve improved performance in human action recognition over comparable methods that use tracking-free temporal template motion representations. Finally, a simple system based on SVM and MHI has been implemented on a reconfigurable embedded computer vision architecture for real-time gesture recognition.
DOI：
10.1093/ietisy/e89-d.1.281
发表时间：
2006
期刊：
IEICE Trans. Inf. Syst.
影响因子：
--
作者：
T. Ogata;J. Tan;S. Ishikawa
通讯作者：
T. Ogata;J. Tan;S. Ishikawa
影响因子：
19.5
作者：
Niebles, Juan Carlos;Wang, Hongcheng;Fei-Fei, Li
通讯作者：
Fei-Fei, Li