• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>IEEE transactions on industrial informatics >Encoding Pose Features to Images With Data Augmentation for 3-D Action Recognition
【24h】

Encoding Pose Features to Images With Data Augmentation for 3-D Action Recognition

机译：编码带有数据增强的图像的姿势特征，用于3-D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

Recently, numerous methods have been introduced for three-dimensional (3-D) action recognition using handcrafted feature descriptors coupled traditional classifiers. However, they cannot learn high-level features of a whole skeleton sequence exhaustively. In this paper, a novel encoding technique-namely, pose feature to image (PoF2I), is introduced to transform the pose features of joint-joint distance and orientation to color pixels. By concatenating the features of all skeleton frames in a sequence, a color image is generated to depict spatial joint correlations and temporal pose dynamics of an action appearance. The strategy of end-to-end fine-tuning a pretrained deep convolutional neural network, which completely capture multiple high-level features at multiscale action representation, is implemented for learning recognition models. We further propose an efficient data augmentation mechanism for informative enrichment and overfitting prevention. The experimental results on six challenging 3-D action recognition datasets demonstrate that the proposed method outperforms state-of-the-art approaches.
机译：最近，使用手工特征描述符耦合传统分类器的三维（3-D）动作识别引入了许多方法。但是，他们无法详尽地学习整个骨架序列的高级功能。本文介绍了一种新颖的编码技术 - 即对图像（POF2i）的姿态特征，以将关节关节距离的姿势特征变换为彩色像素。通过在序列中连接所有骨架帧的特征，产生彩色图像以描绘动作外观的空间关节相关性和时间姿态动态。端到端微调的策略预先训练的深度卷积神经网络，其在多尺度动作表示下完全捕获多个高级功能，用于学习识别模型。我们进一步提出了一种有效的数据增强机制，以获得信息丰富和过度装备预防。六个具有挑战性的3-D动作识别数据集的实验结果表明，所提出的方法优于最先进的方法。

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