Selection of Characteristic Frames in Video for Efficient Action Recognition
Selection of Characteristic Frames in Video for Efficient Action Recognition
复制标题
DOI：
10.1587/transinf.e95.d.2514
复制
发表时间：
2012-10
期刊：
影响因子：
--
通讯作者：
Guoliang Lu;Mineichi Kudo;J. Toyama
中科院分区：
文献类型：
--
作者：
Guoliang Lu;Mineichi Kudo;J. Toyama
基于视觉的人体动作识别是近年来一个活跃的研究领域。范例匹配是该领域的一种重要而流行的方法，然而，以往的工作大多是对整个输入视频片段进行范例匹配以进行识别。这样的策略在计算上是昂贵的，并且限制了它的实际使用。在本文中，我们提出了一种不需要任何先验知识就可以从输入视频剪辑中选择特征帧的鞅框架。动作识别是在这些选定的特征帧上进行的。在WEIZMANN数据集的10个研究动作上的实验表明，在达到相同的识别精度的同时，计算效率显著提高（降低54%）。关键词：范例匹配，动作识别，特征框架
Vision based human action recognition has been an active research field in recent years. Exemplar matching is an important and popular methodology in this field, however, most previous works perform exemplar matching on the whole input video clip for recognition. Such a strategy is computationally expensive and limits its practical usage. In this paper, we present a martingale framework for selection of characteristic frames from an input video clip without requiring any prior knowledge. Action recognition is operated on these selected characteristic frames. Experiments on 10 studied actions from WEIZMANN dataset demonstrate a significant improvement in computational efficiency (54% reduction) while achieving the same recognition precision. key words: exemplar matching, action recognition, characteristic frames