Multispectral embedding-based deep neural network for three-dimensional human pose recovery

Jialin Yu; Jifeng Sun

首页> 外文期刊>Optical engineering >Multispectral embedding-based deep neural network for three-dimensional human pose recovery

【24h】

Multispectral embedding-based deep neural network for three-dimensional human pose recovery

机译：基于多光谱嵌入的深度神经网络用于三维人体姿态恢复

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

Monocular image-based three-dimensional (3-D) human pose recovery aims to retrieve 3-D poses using the corresponding two-dimensional image features. Therefore, the pose recovery performance highly depends on the image representations. We propose a multispectral embedding-based deep neural network (MSEDNN) to automatically obtain the most discriminative features from multiple deep convolutional neural networks and then embed their penultimate fully connected layers into a low-dimensional manifold. This compact manifold can explore not only the optimum output from multiple deep networks but also the complementary properties of them. Furthermore, the distribution of each hierarchy discriminative manifold is sufficiently smooth so that the training process of our MSEDNN can be effectively implemented only using few labeled data. Our proposed network contains a body joint detector and a human pose regressor that are jointly trained. Extensive experiments conducted on four databases show that our proposed MSEDNN can achieve the best recovery performance compared with the State-of-the-art methods.

机译：基于单眼图像的三维（3-D）人类姿势恢复旨在使用相应的二维图像特征检索3-D姿势。因此，姿势恢复性能高度依赖于图像表示。我们提出了一种基于多光谱嵌入的深度神经网络（MSEDNN），以自动从多个深度卷积神经网络获得最具区别性的特征，然后将其倒数第二个完全连接的层嵌入到低维流形中。这种紧凑的歧管不仅可以探索来自多个深度网络的最佳输出，还可以探索它们的互补特性。此外，每个分层判别流形的分布足够平滑，因此仅使用少量标记数据就可以有效地实施我们的MSEDNN的训练过程。我们建议的网络包含经过联合训练的人体关节检测器和人体姿态回归器。在四个数据库上进行的广泛实验表明，与最新方法相比，我们提出的MSEDNN可以实现最佳的恢复性能。

著录项

来源
《Optical engineering》 |2018年第1期|013107.1-013107.16|共16页
作者
Jialin Yu; Jifeng Sun;
展开▼
作者单位

South China University of Technology, School of Electronic and Information Engineering, Guangzhou, China;

South China University of Technology, School of Electronic and Information Engineering, Guangzhou, China;

展开▼
收录信息美国《科学引文索引》(SCI);美国《工程索引》(EI);
原文格式 PDF
正文语种 eng
中图分类
关键词
human pose recovery; deep learning; convolutional neural network; spectral embedding;

机译：人体姿势恢复;深度学习卷积神经网络频谱嵌入;

相似文献

外文文献
中文文献
专利

1. Deep neural networks for human pose estimation from a very low resolution depth image [J] . Szczuko Piotr Multimedia Tools and Applications . 2019,第20期

机译：用于从极低分辨率深度图像进行人体姿势估计的深度神经网络
2. Modelling Human Body Pose for Action Recognition Using Deep Neural Networks [J] . Li Chengyang, Tong Ruofeng, Tang Min Arabian Journal for Science and Engineering . 2018,第12期

机译：使用深度神经网络为动作识别建模人体姿势
3. Learning Latent Representations of 3D Human Pose with Deep Neural Networks [J] . Isinsu Katircioglu, Bugra Tekin, Mathieu Salzmann, International Journal of Computer Vision . 2018,第12期

机译：学习3D人类姿势与深神经网络的潜在表示
4. Computer vision approaches based on deep learning and neural networks: Deep neural networks for video analysis of human pose estimation [C] . Eralda Nishani, Betim Çiço Mediterranean Conference on Embedded Computing . 2017

机译：基于深度学习和神经网络的计算机视觉方法：用于人体姿势估计的视频分析的深度神经网络
5. Internal and External Feature Engineering Applied to Deep Learning with Convolutional Neural Networks for Monocular Relative Pose Estimation in Visual Odometry and Self-Localization [D] . Parkins, Franz Payton. 2020

机译：内部和外部特征工程应用于卷积神经网络的深度学习，用于视觉测量和自定位中的单眼相对姿态估计
6. HUMANNET—A Two-Tiered Deep Neural Network Architecture for Self-Occluding Humanoid Pose Reconstruction [O] . Audrius Kulikajevas, Rytis Maskeliunas, Robertas Damasevicius, 2021

机译：Humannet-一种双层深度神经网络架构用于自我封闭人形姿势重建
7. Embedding-Based Speaker Adaptive Training of Deep Neural Networks [O] . Cui, Xiaodong, Goel, Vaibhava, Saon, George 2017

机译：基于嵌入式的深度神经网络自适应训练

Multispectral embedding-based deep neural network for three-dimensional human pose recovery

摘要

著录项

相似文献

相关主题

期刊订阅