首页> 外文期刊>Neural Networks and Learning Systems, IEEE Transactions on >View-Invariant Action Recognition Based on Artificial Neural Networks
【24h】

View-Invariant Action Recognition Based on Artificial Neural Networks

机译:基于人工神经网络的视图不变动作识别

获取原文
获取原文并翻译 | 示例
       

摘要

In this paper, a novel view invariant action recognition method based on neural network representation and recognition is proposed. The novel representation of action videos is based on learning spatially related human body posture prototypes using self organizing maps. Fuzzy distances from human body posture prototypes are used to produce a time invariant action representation. Multilayer perceptrons are used for action classification. The algorithm is trained using data from a multi-camera setup. An arbitrary number of cameras can be used in order to recognize actions using a Bayesian framework. The proposed method can also be applied to videos depicting interactions between humans, without any modification. The use of information captured from different viewing angles leads to high classification performance. The proposed method is the first one that has been tested in challenging experimental setups, a fact that denotes its effectiveness to deal with most of the open issues in action recognition.
机译:提出了一种新的基于神经网络表示和识别的视图不变动作识别方法。动作视频的新颖表现形式是基于使用自组织图学习与空间相关的人体姿势原型的。与人体姿势原型的模糊距离用于生成时不变动作表示。多层感知器用于动作分类。使用多相机设置中的数据对算法进行训练。为了使用贝叶斯框架识别动作,可以使用任意数量的摄像机。所提出的方法也可以不经任何修改地应用于描述人与人之间交互的视频。从不同视角捕获的信息的使用导致了较高的分类性能。所提出的方法是在具有挑战性的实验设置中进行测试的第一个方法,这一事实表明该方法可有效应对动作识别中的大多数未解决问题。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号