• Laser & Optoelectronics Progress
  • Vol. 58, Issue 20, 2015004 (2021)
Hong Liu, Jie Ma*, and Yujing Chai
Author Affiliations
  • School of Electronics and Information Engineering, Hebei University of Technology, Tianjin 300401, China
  • show less
    DOI: 10.3788/LOP202158.2015004 Cite this Article Set citation alerts
    Hong Liu, Jie Ma, Yujing Chai. Human Pose Estimation Model Based on Improved Hourglass Network[J]. Laser & Optoelectronics Progress, 2021, 58(20): 2015004 Copy Citation Text show less

    Abstract

    A stacked hourglass network (SHN) is a representative research result in human pose estimation; however, it ignores the local information of joints. Therefore, this study proposes a human pose estimation model based on an improved hourglass network. First, multiple residual modules and convolution layer with a step size of 2 are used to obtain low- to high-level features. In order to highlight the local detailed feature information, the number of residual modules and channels are adjusted as the number of network layers deepens. Then, an online difficult keypoint mining module is integrated to extract local features such as texture and shape of the occluded part. Finally, deconvolution is used to maximize the restoration of the original local features. The experimental results show that the average accuracy of the proposed model on the COCO data set reaches 74.6%. In addition, the total parameter amount is 1.5×10 7, which is 5.1 percentage points higher than the average accuracy of superimposing eight SHN (8-SHN), and its total parameter amount is only 1/3 of 8-SHN.
    Hong Liu, Jie Ma, Yujing Chai. Human Pose Estimation Model Based on Improved Hourglass Network[J]. Laser & Optoelectronics Progress, 2021, 58(20): 2015004
    Download Citation