Multi-Agent Deep Reinforcement Learning for Online 3D Human Poses Estimation
Most multi-view based human pose estimation techniques assume the cameras are fixed. While in dynamic scenes, the cameras should be able to move and seek the best views to avoid occlusions and extract 3D information of the target collaboratively. In this paper, we address the problem of online view...
Main Authors: | Zhen Fan, Xiu Li, Yipeng Li |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-10-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/13/19/3995 |
Similar Items
-
3D human pose detection using nano sensor and multi-agent deep reinforcement learning
by: Yangjie Sun, et al.
Published: (2023-01-01) -
The Progress of Human Pose Estimation: A Survey and Taxonomy of Models Applied in 2D Human Pose Estimation
by: Tewodros Legesse Munea, et al.
Published: (2020-01-01) -
Multi-Person Pose Estimation using an Orientation and Occlusion Aware Deep Learning Network
by: Yanlei Gu, et al.
Published: (2020-03-01) -
Research Progress of Deep Learning Methods in Two-dimensional Human Pose Estimation
by: ZHANG Guo-ping, MA Nan, Guan Huai-guang, WU Zhi-xuan
Published: (2022-12-01) -
A New Multi-Person Pose Estimation Method Using the Partitioned CenterPose Network
by: Jiahua Wu, et al.
Published: (2021-05-01)