Human Pose Estimation based on HRNet and Feature Pyramids

Authors

  • Fangjie Dong
  • Miaowei Yang
  • Pengshen Yang

DOI:

https://doi.org/10.54097/hset.v39i.6734

Keywords:

Pose Estimation; HRNet; Image Inspection; FPN Feature Pyramid.

Abstract

A popular area of research in the realm of computer vision is human pose estimation, which is the process of recovering human joint points from the given images or videos. Convolutional neural networks, which have great feature representation capabilities, have become a fundamental component of human pose estimation algorithms as a result of the deep learning field's quick development. To enhance feature quality and raise the precision of human pose estimate, in this paper, we propose a new model based on HRNet neural network and feature pyramid to more accurately capture each main part of the human body. The model uses HRNet as the backbone network, taking advantage of its ability to combine low resolution with high resolution, and afterwards adds characteristic pyramids to the HRNetnetwork in order to enhance the capability of detecting small objects by utilizing its ability to solve multi-scale problems. The model can estimate a human's pose accurately, according to experimental results, and on the MPII Human Pose dataset, the addition of the feature pyramid enhances the model's detection performance by 0.05. in order to achieve smoothing after adding feature mapping with different resolutions, the detection performance improves by 0.17 after further improvement by adding  convolution. For the elbow, it improves by almost 0.5. The model's ability to increase the precision of human pose estimate is supported by all of the outcomes.

Downloads

Download data is not yet available.

References

Li Yanping, Liu Ruyi, Wang Xiangyang, Wang Rui. Human pose estimation based on lightweight basicblock [J]. Machine Vision and Applications, 2022, 34(1).

Zhang Xiaona, Wu Qingtao. Top-down human pose estimation algorithm based on deep learning[J]. Electronic Measurement Technology, 2021, 044(009).

B. Xiao, H. Wu, and Y. Wei. Simple baselines for human pose estimation and tracking. In ECCV, pages 472–487, 2018.

Li Jia. Research on bottom-up multi-person attitude estimation Method[D]. University of Science and Technology of China, 2021.

A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks. In NIPS, pages 1106–1114, 2012.

K. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition. In ICLR, 2015.

C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. E. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich. Going deeper with convolutions. In CVPR, pages 1–9, 2015.

K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. In CVPR, pages 770–778, 2016.

K. Sun, B. Xiao, D. Liu, and J. Wang. Deep high-resolution representation learning for human pose estimation. In CVPR, 2019.

T. Lin, P. Dollar, R. B. Girshick, K. He, B. Hariharan, and S. J. Belongie. Feature pyramid networks for object detection. In CVPR, pages 936–944, 2017.

Downloads

Published

01-04-2023