Improved Multi-Person 2D Human Pose Estimation Using Attention Mechanisms and Hard Example Mining

Lixin Zhang, Wenteng Huang, Chenliang Wang and Hui Zeng ()
Additional contact information
Lixin Zhang: School of Intelligence Science and Technology, University of Science and Technology Beijing, Beijing 100083, China
Wenteng Huang: School of Intelligence Science and Technology, University of Science and Technology Beijing, Beijing 100083, China
Chenliang Wang: School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, China
Hui Zeng: School of Intelligence Science and Technology, University of Science and Technology Beijing, Beijing 100083, China

Sustainability, 2023, vol. 15, issue 18, 1-17

Abstract: In recent years, human pose estimation, as a subfield of computer vision and artificial intelligence, has achieved significant performance improvements due to its wide applications in human-computer interaction, virtual reality, and smart security. However, most existing methods are designed for single-person scenes and suffer from low accuracy and long inference time in multi-person scenes. To address this issue, increasing attention has been paid to developing methods for multi-person pose estimation, such as utilizing Partial Affinity Field (PAF)-based bottom-up methods to estimate 2D poses of multiple people. In this study, we propose a method that addresses the problems of low network accuracy and poor estimation of flexible joints. This method introduces the attention mechanism into the network and utilizes the joint point extraction method based on hard example mining. Integrating the attention mechanism into the network improves its overall performance. In contrast, the joint point extraction method improves the localization accuracy of the flexible joints of the network without increasing the complexity. Experimental results demonstrate that our proposed method significantly improves the accuracy of 2D human pose estimation. Our network achieved a notably elevated Average Precision (AP) score of 60.0 and outperformed competing methods on the standard benchmark COCO test dataset, signifying its exceptional performance.

Keywords: multiple person; 2D human pose estimation; hard example mining; part affinity fields (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2023
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2071-1050/15/18/13363/pdf (application/pdf)
https://www.mdpi.com/2071-1050/15/18/13363/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:15:y:2023:i:18:p:13363-:d:1234208

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().