Feature Monitored High-Dimension Endecoder Net for End to End Markless Human Pose Estimation

SHEN Li; CHEN Ying

doi:10.3969/j.issn.0372-2112.2020.08.010

您当前的位置：

首页 >

文章列表页 >

Feature Monitored High-Dimension Endecoder Net for End to End Markless Human Pose Estimation

更新时间：2025-07-16

- Feature Monitored High-Dimension Endecoder Net for End to End Markless Human Pose Estimation
- Acta Electronica Sinica Vol. 48, Issue 8, Pages: 1528-1537(2020)
- 作者机构：
  
  江南大学轻工过程先进控制教育部重点实验室,江苏,无锡,214000
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China (No.61573168)
- DOI：10.3969/j.issn.0372-2112.2020.08.010
  CLC： TP391
- Published Online：25 August 2020，
  
  Published：2020
- 稿件说明：
移动端阅览
SHEN Li, CHEN Ying. Feature Monitored High-Dimension Endecoder Net for End to End Markless Human Pose Estimation[J]. Acta Electronica Sinica, 2020, 48(8): 1528-1537.
DOI：

SHEN Li, CHEN Ying. Feature Monitored High-Dimension Endecoder Net for End to End Markless Human Pose Estimation[J]. Acta Electronica Sinica, 2020, 48(8): 1528-1537. DOI： 10.3969/j.issn.0372-2112.2020.08.010.

摘要

针对点云空间三维信息非结构化和旋转易变性对预测结果的影响，提出一种带特征监控的三维信息编解码卷积神经网络，该网络可实现三维空间下单目深度图的端对端无标记人体姿态估计.所设计的网络由特征监控编解码组件串联而成，该组件第一部分使用三维卷积模块以类似沙漏结构的形式组合设计，实现对特征图的编码和解码；第二部分以不同参数残差块并联，实现对特征图的监控融合，第一部分与第二部分首尾连接构成组件.特征监控编解码组件能根据数据集大小，通过串联的方式搭建不同深度的网络，同时根据数据分辨率，设置组件参数，实现由粗到精的特征学习，最终获得最佳网络.通过ITOP数据库的实验表明，该网络实现了空间三维信息的端到端深度学习，显著提高了系统性能并具有更高的精度.

Abstract

Aiming at the impact of unstructured and rotational variability of three-dimensional information in point cloud on prediction results

a feature-supervised three-dimensional information encoding and decoding convolution deep learning network is proposed. The network is composed of feature monitoring coding and decoding modules in series. In the first part of the module

a three-dimensional convolution module is used in the form of hourglass structure to realize the coding and decoding of the feature map. In the second part

the residual blocks of different parameters are connected in parallel to realize the monitoring and fusion of feature maps. Feature monitored coding and decoding modules can build networks with different depths in series according to the size of data sets. At the same time

according to the data resolution

modules parameters can be set to realize feature learning from rough to fine

and ultimately obtain the best network. The experiment of ITOP database shows that the network achieves the end-to-end deep learning of three-dimensional information

significantly improves the system performance and has higher precision accuracy.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Continual Learning Methods and Applications in Computer Vision

Neural Network Based Image Style Transfer: A Survey

DRHA-UIE: An Underwater Image Enhancement Method Based on Dual Residual Hybrid Attention Block

A Survey on Deep Predictive Learning Based on Unlabeled Videos

A Survey of Generic Object Detection Methods Based on Deep Learning

Related Author

FANG Yan

Wei Yun-chao

Cong Run-min

Zuo Wang-meng

Zhao Yao

WANG Wei

ZHANG Jing-yi

WEN Yu-hui

Related Institution

School of Computer Science and Technology, Beijing Jiaotong University

School of Control Science and Engineering, Shandong University

School of Computer Science and Technology, Harbin Institute of Technology

School of Computer Science and Technology, Beijing Jiaotong University

College of Computer Science and Technology， Jilin University

⁰