Results 11 to 20 of about 9,322,993 (252)

Deep probabilistic human pose estimation

IET Computer Vision, 2018
The authors consider the problem of human pose estimation using probabilistic convolutional neural networks. They explore ways to improve human pose estimation accuracy on standard pose estimation benchmarks MPII human pose and Leeds Sports Pose (LSP ...
Ilia Petrov, Vlad Shakhuro, Anton Konushin   +2 more
doaj   +2 more sources

Research Progress of Two-Dimensional Human Pose Estimation Based on Deep Learning [PDF]

Jisuanji gongcheng, 2021
The two-dimensional Human Pose Estimation(HPE) methods based on deep learning have attracted much attention for their application potential.The methods work by constructing a specific neural network architecture,and processing the extracted feature ...
LIU Yong, LI Jie, ZHANG Jianlin, XU Zhiyong, WEI Yuxing
doaj   +1 more source

Pose ResNet: 3D Human Pose Estimation Based on Self-Supervision

Sensors, 2023
The accurate estimation of a 3D human pose is of great importance in many fields, such as human–computer interaction, motion recognition and automatic driving.
Wenxia Bao, Zhongyu Ma, Dong Liang, Xianjun Yang, Tao Niu   +4 more
doaj   +1 more source

Exploring Rare Pose in Human Pose Estimation

IEEE Access, 2020
We tackle the issue of data imbalance between different poses in the human pose estimation problem. We explore unusual poses that are rare which occupy a small portion in a pose dataset.
Jihye Hwang, John Yang, Nojun Kwak
doaj   +1 more source

Human Pose Estimation Using Thermal Images

IEEE Access, 2023
This study addresses the human pose estimation problem on thermal images using Convolutional Neural Networks and Vision Transformer architectures. To do this, eight human pose estimation methods designed for visible images were extended to be applied in ...
Javier Smith, Patricio Loncomilla, Javier Ruiz-Del-Solar   +2 more
doaj   +1 more source

Fast and Lightweight Human Pose Estimation

IEEE Access, 2021
Although achieving significant improvement on pose estimation, the major drawback is that most top-performing methods tend to adopt complex architecture and spend large computational cost to achieve higher performance.
Haopan Ren, Wenming Wang, Kaixiang Zhang, Dejian Wei, Yanyan Gao, Yue Sun   +5 more
doaj   +1 more source

Human pose estimation with heatmap-guided connection

Xi'an Gongcheng Daxue xuebao, 2021
Human pose estimation was an important direction in the field of computer vision, which is widely used in human activity recognition, human-computer interaction, etc, but the accuracy of human pose estimation methods is usually poor.
Wei WANG, Canglong WANG, Zhe PEI, Momeng LIU   +3 more
doaj   +1 more source

Low-resolution human pose estimation

, 2022
Human pose estimation has achieved significant progress on images with high imaging resolution. However, low-resolution imagery data bring nontrivial challenges which are still under-studied. To fill this gap, we start with investigating existing methods
Ge, Shuzhi, Zhang, Feng, ZHU, XIATIAN, Wang, Chen   +3 more
core   +1 more source

Self-Attention Network for Human Pose Estimation

Applied Sciences, 2021
Estimating the positions of human joints from monocular single RGB images has been a challenging task in recent years. Despite great progress in human pose estimation with convolutional neural networks (CNNs), a central problem still exists: the ...
Hailun Xia, Tianyang Zhang
doaj   +1 more source

Motion Capture for Sporting Events Based on Graph Convolutional Neural Networks and Single Target Pose Estimation Algorithms

Applied Sciences, 2023
Human pose estimation refers to accurately estimating the position of the human body from a single RGB image and detecting the location of the body. It serves as the basis for several computer vision tasks, such as human tracking, 3D reconstruction, and ...
Chengpeng Duan, Bingliang Hu, Wei Liu, Jie Song   +3 more
doaj   +1 more source