期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2014
期号：ICIET
页码：292
出版社：S&S Publications
摘要：This paper provides the interrelated topicsof action recognition and detection of Humans. Theforeground clutter is used to segment the human actionfrom the video using the statistical method of AdaptiveBackground Mixture Model. The descriptor can becomputed from drawing the boundary box for the humansin the video and the counting of actions is also displayed.The values for features are calculated from the descriptor.The descriptor allows for the comparison of the underlyingdynamics of two space-time video segments irrespective ofspatial appearance, such as differences induced byclothing, and with robustness to clutter. The calculatedfeature values are taken for extraction of human actions.An associated similarity measure is introduced that admitsefficient exhaustive search for an action template, derivedfrom a single exemplar video, across candidate videosequences also under occlusive conditions the human isdetected using the adaptive filter.
