Scholarlink

<p>Human pose estimation (HPE) is a critical task in computer vision, with applications spanning human-computer interaction, intelligent surveillance, behavior analysis, virtual reality, and medical diagnosis. However, existing high-resolution networks (HRNet) face challenges due to their large parameter sizes and low computational efficiency, limiting their real-time applicability. To address these issues, this paper introduces Ghost-HRNet, a lightweight HPE network that integrates the efficient feature extraction capabilities of the Ghost module with the multi-scale feature fusion strengths of HRNet. By incorporating depthwise separable convolution and the convolutional block attention module (CBAM), Ghost-HRNet achieves significant reductions in parameter count and computational load while maintaining high accuracy. Experimental results on the COCO and MPII datasets demonstrate that Ghost-HRNet achieves average accuracies of 66% and 87.26%, respectively, while reducing the parameter size by 71.3% and computational load by 79.0% compared to HRNet. This combination of efficiency and accuracy makes Ghost-HRNet particularly suitable for real-time applications, underscoring its potential to advance HPE technology.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Ghost-HRNet: a lightweight high-resolution network for efficient human pose estimation with enhanced multi-scale feature fusion

  • 期刊论文

  • 发表日期：

    2025年5月28日

查看全文
  • Xiaoyu Zheng,
  • Liping Zhuang,
  • Dewang Chen

摘要

Human pose estimation (HPE) is a critical task in computer vision, with applications spanning human-computer interaction, intelligent surveillance, behavior analysis, virtual reality, and medical diagnosis. However, existing high-resolution networks (HRNet) face challenges due to their large parameter sizes and low computational efficiency, limiting their real-time applicability. To address these issues, this paper introduces Ghost-HRNet, a lightweight HPE network that integrates the efficient feature extraction capabilities of the Ghost module with the multi-scale feature fusion strengths of HRNet. By incorporating depthwise separable convolution and the convolutional block attention module (CBAM), Ghost-HRNet achieves significant reductions in parameter count and computational load while maintaining high accuracy. Experimental results on the COCO and MPII datasets demonstrate that Ghost-HRNet achieves average accuracies of 66% and 87.26%, respectively, while reducing the parameter size by 71.3% and computational load by 79.0% compared to HRNet. This combination of efficiency and accuracy makes Ghost-HRNet particularly suitable for real-time applications, underscoring its potential to advance HPE technology.