Open Access
ARTICLE
Full Scale-Aware Balanced High-Resolution Network for Multi-Person Pose Estimation
Shaohua Li, Haixiang Zhang*, Hanjie Ma, Jie Feng, Mingfeng Jiang
School of Computer Science and Technology, Zhejiang Sci-Tech University, Hangzhou, 310018, China
* Corresponding Author: Haixiang Zhang. Email:
Computers, Materials & Continua 2023, 76(3), 3379-3392. https://doi.org/10.32604/cmc.2023.041538
Received 26 April 2023; Accepted 25 June 2023; Issue published 08 October 2023
Abstract
Scale variation is a major challenge in multi-person pose estimation. In scenes where persons are present at various
distances, models tend to perform better on larger-scale persons, while the performance for smaller-scale persons
often falls short of expectations. Therefore, effectively balancing the persons of different scales poses a significant
challenge. So this paper proposes a new multi-person pose estimation model called FSA Net to improve the model’s
performance in complex scenes. Our model utilizes High-Resolution Network (HRNet) as the backbone and feeds
the outputs of the last stage’s four branches into the DCB module. The dilated convolution-based (DCB) module
employs a parallel structure that incorporates dilated convolutions with different rates to expand the receptive
field of each branch. Subsequently, the attention operation-based (AOB) module performs attention operations
at both branch and channel levels to enhance high-frequency features and reduce the influence of noise. Finally,
predictions are made using the heatmap representation. The model can recognize images with diverse scales and
more complex semantic information. Experimental results demonstrate that FSA Net achieves competitive results
on the MSCOCO and MPII datasets, validating the effectiveness of our proposed approach.
Keywords
Cite This Article
APA Style
Li, S., Zhang, H., Ma, H., Feng, J., Jiang, M. (2023). Full scale-aware balanced high-resolution network for multi-person pose estimation. Computers, Materials & Continua, 76(3), 3379-3392. https://doi.org/10.32604/cmc.2023.041538
Vancouver Style
Li S, Zhang H, Ma H, Feng J, Jiang M. Full scale-aware balanced high-resolution network for multi-person pose estimation. Comput Mater Contin. 2023;76(3):3379-3392 https://doi.org/10.32604/cmc.2023.041538
IEEE Style
S. Li, H. Zhang, H. Ma, J. Feng, and M. Jiang "Full Scale-Aware Balanced High-Resolution Network for Multi-Person Pose Estimation," Comput. Mater. Contin., vol. 76, no. 3, pp. 3379-3392. 2023. https://doi.org/10.32604/cmc.2023.041538