Pose-DWT-Former: An Improved Transformer-Based 3D Human Pose Estimation Model

Yajuan Wei, Chuan Dai, Zhijie Xu*, Minsi Chen, Ying Liu

*Corresponding author for this work

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

Abstract

Human pose estimation (HPE) is the basis of a wide variety of computer vision tasks. However, existing approaches are designed mainly for static 2D images, ignoring the temporal continuity and geometric consistency between video frames. With the aim of resolving the aforementioned issues, Pose-DWT-Former, an enhanced transformer-based approach, was proposed in this paper. The principle is to employ the 2D skeleton-based pose sequences extracted from the video frames and the discrete wavelet domain (DWT) information of those sequences as the network input for the purposes of 3D HPE. The evaluations were performed on two datasets, with good results in speed, accuracy, and robustness against noise, laying a solid foundation for the subsequent use of 3D human posture information for action recognition.

Original languageEnglish
Title of host publicationProceedings of the UNIfied Conference of DAMAS, IncoME and TEPEN Conferences (UNIfied 2023) - Volume 2
EditorsAndrew D. Ball, Zuolu Wang, Huajiang Ouyang, Jyoti K. Sinha
PublisherSpringer Science and Business Media B.V.
Pages41-49
Number of pages9
ISBN (Print)9783031494208
DOIs
Publication statusPublished - 2024
Externally publishedYes
EventUNIfied Conference of International Workshop on Defence Applications of Multi-Agent Systems, DAMAS 2023, International Conference on Maintenance Engineering, IncoME-V 2023, International conference on the Efficiency and Performance Engineering Network, TEPEN 2023 - Huddersfield, United Kingdom
Duration: 29 Aug 20231 Sept 2023

Publication series

NameMechanisms and Machine Science
Volume152 MMS
ISSN (Print)2211-0984
ISSN (Electronic)2211-0992

Conference

ConferenceUNIfied Conference of International Workshop on Defence Applications of Multi-Agent Systems, DAMAS 2023, International Conference on Maintenance Engineering, IncoME-V 2023, International conference on the Efficiency and Performance Engineering Network, TEPEN 2023
Country/TerritoryUnited Kingdom
CityHuddersfield
Period29/08/231/09/23

Keywords

  • DWT
  • HPE
  • Skeleton pose sequences
  • Transformer

Fingerprint

Dive into the research topics of 'Pose-DWT-Former: An Improved Transformer-Based 3D Human Pose Estimation Model'. Together they form a unique fingerprint.

Cite this