TY - GEN
T1 - Human Pose Estimation Using Skeletal Heatmaps
AU - Jun, Jinyoung
AU - Lee, Jae Han
AU - Kim, Chang Su
N1 - Funding Information:
This work was supported by ‘The Cross-Ministry Giga KOREA Project’ grant funded by the Korea government (MSIT) (No. GK20P0200, Development of 4D reconstruction and dynamic deformable action model based hyperrealistic service technology), and by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIP) (No. NRF-2018R1A2B3003896).
Publisher Copyright:
© 2020 APSIPA.
Copyright:
Copyright 2021 Elsevier B.V., All rights reserved.
PY - 2020/12/7
Y1 - 2020/12/7
N2 - We propose a novel skeletal attention module to generate keypoint heatmaps, which exploits skeletal, as well as overall body structure, information for human pose estimation. We first add augmenting convolutional layers to an existing deep neural network in order to yield skeletal heatmaps. These skeletal heatmaps emphasize keypoint relations connected either physically or virtually. By combining the skeletal heatmaps, we generate body attention maps for upper-body, lower-body, and full-body. Then, the skeletal heatmaps and the body attention maps are employed to estimate the heatmap for each keypoint. Finally, we perform weighted inference on the output heatmaps for more precise estimates. Experimental results demonstrate that the proposed algorithm enhances performance on two datasets for human pose estimation.
AB - We propose a novel skeletal attention module to generate keypoint heatmaps, which exploits skeletal, as well as overall body structure, information for human pose estimation. We first add augmenting convolutional layers to an existing deep neural network in order to yield skeletal heatmaps. These skeletal heatmaps emphasize keypoint relations connected either physically or virtually. By combining the skeletal heatmaps, we generate body attention maps for upper-body, lower-body, and full-body. Then, the skeletal heatmaps and the body attention maps are employed to estimate the heatmap for each keypoint. Finally, we perform weighted inference on the output heatmaps for more precise estimates. Experimental results demonstrate that the proposed algorithm enhances performance on two datasets for human pose estimation.
UR - http://www.scopus.com/inward/record.url?scp=85100933554&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85100933554&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85100933554
T3 - 2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2020 - Proceedings
SP - 1287
EP - 1292
BT - 2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2020 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2020
Y2 - 7 December 2020 through 10 December 2020
ER -