Open Access iconOpen Access

ARTICLE

crossmark

DAUNet: Detail-Aware U-Shaped Network for 2D Human Pose Estimation

Xi Li1,2, Yuxin Li2, Zhenhua Xiao3,*, Zhenghua Huang1, Lianying Zou1

1 College of Information and Artificial Intelligence, Nanchang Institute of Science and Technology, Nanchang, 330108, China
2 School of Electrical and Information Engineering, Wuhan Institute of Technology, Wuhan, 430205, China
3 School of Computer Science and Technology, Hubei Business College, Wuhan, 430079, China

* Corresponding Author: Zhenhua Xiao. Email: email

Computers, Materials & Continua 2024, 81(2), 3325-3349. https://doi.org/10.32604/cmc.2024.056464

Abstract

Human pose estimation is a critical research area in the field of computer vision, playing a significant role in applications such as human-computer interaction, behavior analysis, and action recognition. In this paper, we propose a U-shaped keypoint detection network (DAUNet) based on an improved ResNet subsampling structure and spatial grouping mechanism. This network addresses key challenges in traditional methods, such as information loss, large network redundancy, and insufficient sensitivity to low-resolution features. DAUNet is composed of three main components. First, we introduce an improved BottleNeck block that employs partial convolution and strip pooling to reduce computational load and mitigate feature loss. Second, after upsampling, the network eliminates redundant features, improving the overall efficiency. Finally, a lightweight spatial grouping attention mechanism is applied to enhance low-resolution semantic features within the feature map, allowing for better restoration of the original image size and higher accuracy. Experimental results demonstrate that DAUNet achieves superior accuracy compared to most existing keypoint detection models, with a mean PCKh@0.5 score of 91.6% on the MPII dataset and an AP of 76.1% on the COCO dataset. Moreover, real-world experiments further validate the robustness and generalizability of DAUNet for detecting human bodies in unknown environments, highlighting its potential for broader applications.

Keywords


Cite This Article

APA Style
Li, X., Li, Y., Xiao, Z., Huang, Z., Zou, L. (2024). Daunet: detail-aware u-shaped network for 2D human pose estimation. Computers, Materials & Continua, 81(2), 3325-3349. https://doi.org/10.32604/cmc.2024.056464
Vancouver Style
Li X, Li Y, Xiao Z, Huang Z, Zou L. Daunet: detail-aware u-shaped network for 2D human pose estimation. Comput Mater Contin. 2024;81(2):3325-3349 https://doi.org/10.32604/cmc.2024.056464
IEEE Style
X. Li, Y. Li, Z. Xiao, Z. Huang, and L. Zou, “DAUNet: Detail-Aware U-Shaped Network for 2D Human Pose Estimation,” Comput. Mater. Contin., vol. 81, no. 2, pp. 3325-3349, 2024. https://doi.org/10.32604/cmc.2024.056464



cc Copyright © 2024 The Author(s). Published by Tech Science Press.
This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 287

    View

  • 126

    Download

  • 0

    Like

Share Link