TY  - CONF
AU  - Jorge Charco
AU  - Angel Sappa
AU  - Boris X. Vintimilla
A2  - VISAPP
PY  - 2022//
TI  - Human Pose Estimation through a Novel Multi-view Scheme
BT  - 17th International Conference on Computer Vision Theory and Applications (VISAPP 2022)
SP  - 855
EP  - 862
VL  - 5
KW  - Multi-view Scheme
KW  - Human Pose Estimation
KW  - Relative Camera Pose
KW  - Monocular Approach
N2  - This paper presents a multi-view scheme to tackle the challenging problem of the self-occlusion in human pose estimation problem. The proposed approach first obtains the human body joints of a set of images, which are captured from different views at the same time. Then, it enhances the obtained joints by using amulti-view scheme. Basically, the joints from a given view are used to enhance poorly estimated joints from another view, especially intended to tackle the self occlusions cases. A network architecture initially proposed for the monocular case is adapted to be used in the proposed multi-view scheme. Experimental results andcomparisons with the state-of-the-art approaches on Human3.6m dataset are presented showing improvements in the accuracy of body joints estimations.
SN  - 2184-4321
SN  - 978-989-758-555-5
UR  - https://www.scitepress.org/Link.aspx?doi=10.5220/0010899900003124
L1  - http://158.109.8.37/files/CSV2022.pdf
N1  - MSIAU; 600.160
ID  - Jorge Charco2022
ER  -