...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Expert Systems with Application >Viewpoint projection based deep feature learning for single and dyadic action recognition
【24h】

Viewpoint projection based deep feature learning for single and dyadic action recognition

机译：基于观点投影的深度特征学习，用于单次和双次动作识别

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Usage of depth data in various computer vision applications gains popularity with cheap depth sensors available on the market. In this study, a method that utilizes Deep Learning is proposed for single human actions and dyadic actions. Depth data of the actions are used to construct a three-dimensional (3D) template. These templates are rotated in different directions and two-dimensional (2D) views from different angles are stored. Acquired 2D images are used in deep feature extraction. AlexNet (Krizhevsky, Sutskever, & Hinton, 2012) pre-trained convolutional neural network is used for deep feature extraction. For all viewpoints, deep features are extracted and concatenated. After that random forest classifier is used for action recognition. The contributions of this paper are as follows. First, a 3D isosurface models is constructed to figure actions sequence. Second, we project 3D shapes into a 2D feature space by taking its snapshots from different views and giving them to a pre-trained CNN as input for feature extraction. We explore more information about the actions by extracting features from different layers of the deep neural network. We compare the results of the deep features extracted from different layers of the pre-trained CNN. Various classifiers are trained with extracted deep features. Because of the complex structure of the 3D shapes, there are a limited number of feature extraction methods. Our method obtains close to state-of-the-art performance on various single and two-person action datasets. (C) 2018 Elsevier Ltd. All rights reserved.
机译：深度数据在各种计算机视觉应用中的使用由于市场上便宜的深度传感器而变得流行。在这项研究中，提出了一种针对单个人类动作和二元动作利用深度学习的方法。动作的深度数据用于构建三维（3D）模板。这些模板沿不同方向旋转，并且存储了来自不同角度的二维（2D）视图。采集的2D图像用于深度特征提取。 AlexNet（Krizhevsky，Sutskever，＆Hinton，2012）预训练卷积神经网络用于深度特征提取。对于所有观点，都提取并连接了深层特征。之后，将随机森林分类器用于动作识别。本文的贡献如下。首先，构建3D等值面模型以计算动作序列。其次，我们通过从不同的视图获取快照并将其提供给预先训练的CNN作为特征提取的输入，将3D形状投影到2D特征空间中。我们通过从深度神经网络的不同层提取特征来探索有关动作的更多信息。我们比较了从预训练的CNN的不同层提取的深层特征的结果。使用提取的深层特征训练各种分类器。由于3D形状的结构复杂，特征提取方法数量有限。我们的方法在各种单人和两人动作数据集上获得了近乎最新的表现。 （C）2018 Elsevier Ltd.保留所有权利。

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