scholarly journals Semi-Dynamic Hypergraph Neural Network for 3D Pose Estimation

2020 ◽  
Author(s):  
Shengyuan Liu ◽  
Pei Lv ◽  
Yuzhen Zhang ◽  
Jie Fu ◽  
Junjin Cheng ◽  
...  
Keyword(s):  
Neural Network ◽  
Pose Estimation ◽  
State Of The Art ◽  
Human Pose Estimation ◽  
Body Structure ◽  
Single Image ◽  
3D Pose Estimation ◽  
Convolutional Networks ◽  
Human Pose ◽  
Fixed Tree

This paper proposes a novel Semi-Dynamic Hypergraph Neural Network (SD-HNN) to estimate 3D human pose from a single image. SD-HNN adopts hypergraph to represent the human body to effectively exploit the kinematic constrains among adjacent and non-adjacent joints. Specifically, a pose hypergraph in SD-HNN has two components. One is a static hypergraph constructed according to the conventional tree body structure. The other is the semi-dynamic hypergraph representing the dynamic kinematic constrains among different joints. These two hypergraphs are combined together to be trained in an end-to-end fashion. Unlike traditional Graph Convolutional Networks (GCNs) that are based on a fixed tree structure, the SD-HNN can deal with ambiguity in human pose estimation. Experimental results demonstrate that the proposed method achieves state-of-the-art performance both on the Human3.6M and MPI-INF-3DHP datasets.

Human pose estimation based on parallel atrous convolution and body structure constraints

2021 ◽  
pp. 1-11
Author(s):  
Min Zhang ◽  
Haijie Yang ◽  
Pengfei Li ◽  
Ming Jiang
Keyword(s):  
Pose Estimation ◽  
The Body ◽  
Human Pose Estimation ◽  
Spatial Relationships ◽  
Body Structure ◽  
Convolutional Network ◽  
In Series ◽  
Human Pose ◽  
Ablation Study ◽  
View Transformation

Human pose estimation is still a challenging task in computer vision, especially in the case of camera view transformation, joints occlusions and overlapping, the task will be of ever-increasing difficulty to achieve success. Most existing methods pass the input through a network, which typically consists of high-to-low resolution sub-networks that are connected in series. Still, during the up-sampling process, the spatial relationships and details might be lost. This paper designs a parallel atrous convolutional network with body structure constraints (PAC-BCNet) to address the problem. Among the mentioned techniques, the parallel atrous convolution (PAC) is constructed to deal with scale changes by connecting multiple different atrous convolution sub-networks in parallel. And it is used to extract features from different scales without reducing the resolution. Besides, the body structure constraints (BC), which enhance the correlation between each keypoint, are constructed to obtain better spatial relationships of the body by designing keypoints constraints sets and improving the loss function. In this work, a comparative experiment of the serial atrous convolution, the parallel atrous convolution, the ablation study with and without body structure constraints are conducted, which reasonably proves the effectiveness of the approach. The model is evaluated on two widely used human pose estimation benchmarks (MPII and LSP). The method achieves better performance on both datasets.

Structure-aware human pose estimation with graph convolutional networks

2020 ◽  
Vol 106 ◽  
pp. 107410 ◽  
Author(s):  
Yanrui Bin ◽  
Zhao-Min Chen ◽  
Xiu-Shen Wei ◽  
Xinya Chen ◽  
Changxin Gao ◽  
...  
Keyword(s):  
Pose Estimation ◽  
Human Pose Estimation ◽  
Convolutional Networks ◽  
Human Pose

scholarly journals A Hybrid Neural Network for Graph-Based Human Pose Estimation From 2D Images

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 52830-52840
Author(s):  
Huynh The Vu ◽  
Richardt H. Wilkinson ◽  
Margaret Lech ◽  
Eva Cheng
Keyword(s):  
Neural Network ◽  
Pose Estimation ◽  
Human Pose Estimation ◽  
Hybrid Neural Network ◽  
Human Pose ◽  
2D Images

Improved Modular Convolution Neural Network for Human Pose Estimation

2019 ◽  
pp. 378-388
Author(s):  
Zhengxuan Zhang ◽  
Jing Dong ◽  
Dongsheng Zhou ◽  
Xiaoyong Fang ◽  
Xiaopeng Wei
Keyword(s):  
Neural Network ◽  
Pose Estimation ◽  
Convolution Neural Network ◽  
Human Pose Estimation ◽  
Human Pose

scholarly journals Global Relation Reasoning Graph Convolutional Networks for Human Pose Estimation

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 38472-38480 ◽  
Author(s):  
Rui Wang ◽  
Chenyang Huang ◽  
Xiangyang Wang
Keyword(s):  
Pose Estimation ◽  
Human Pose Estimation ◽  
Global Relation ◽  
Convolutional Networks ◽  
Human Pose

scholarly journals Human Pose Estimation-Based Real-Time Gait Analysis Using Convolutional Neural Network

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 191542-191550
Author(s):  
Ali Rohan ◽  
Mohammed Rabah ◽  
Tarek Hosny ◽  
Sung-Ho Kim
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Gait Analysis ◽  
Real Time ◽  
Pose Estimation ◽  
Human Pose Estimation ◽  
Human Pose
Sign in / Sign up

Export Citation Format

Share Document