.png){kind=icon}
返回
Joint relation based human pose estimation
.png){kind=icon}
PRE
AI
DOI：10.1007/s00371-021-02282-4.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
With the increasing application of computer vision technology in real life, human pose estimation task becomes more and more important. However, inferencing accurate coordinates of limb joints or invisible joints is still difficult for even state-of-the-art approaches. The positions of limb joints are diversified, and a percentage of the joints are occluded. In this paper, we aim to solve such problem by proposing joint relation based human pose estimation framework. Joint relation is the spatial relation between selected neighbor joints which can imitate human body structure and localize a complex joint with the help of its neighbor joint. We evaluate the joint relation module on challenging dataset and demonstrate its effectiveness by accuracy and visualization results. The proposed joint relation based human pose estimation method achieves state-of-the-art performance.
Keyword:
Joint relation
Feature moving
Body structure
Human pose estimation
期刊
IF:
2.9
论文数:
4.7K
被引数:
6.5K
机构
引用论文
Convolutional neural networks for crowd behaviour analysis: a survey用于人群行为分析的卷积神经网络: 一项调查.png)
VISUAL COMPUTER
VISUAL COMPUTERIF2.9
PREAI
分享收藏
分享收藏
查看更多内容