Human Pose Estimation Based on Lightweight Multi-Scale Coordinate Attention

Heatmap-based traditional approaches for estimating human pose usually suffer from drawbacks such as high network complexity or suboptimal accuracy. Focusing on the issue of multi-person pose estimation without heatmaps, this paper proposes an end-to-end, lightweight human pose estimation network us...

Full description

Saved in:
Bibliographic Details
Published in:Applied sciences 2023-03, Vol.13 (6), p.3614
Main Authors: Li, Xin, Guo, Yuxin, Pan, Weiguo, Liu, Hongzhe, Xu, Bingxin
Format: Article
Language:English
Subjects:
Accuracy
attention mechanism
Datasets
Estimation
Feature maps
human pose estimation
Lightweight
multi-scale feature extraction
Neural networks
Pose estimation
Regularization methods
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Heatmap-based traditional approaches for estimating human pose usually suffer from drawbacks such as high network complexity or suboptimal accuracy. Focusing on the issue of multi-person pose estimation without heatmaps, this paper proposes an end-to-end, lightweight human pose estimation network using a multi-scale coordinate attention mechanism based on the Yolo-Pose network to improve the overall network performance while ensuring the network is lightweight. Specifically, the lightweight network GhostNet was first integrated into the backbone to alleviate the problem of model redundancy and produce a significant number of effective feature maps. Then, by combining the coordinate attention mechanism, the sensitivity of our proposed network to direction and location perception was enhanced. Finally, the BiFPN module was fused to balance the feature information of different scales and further improve the expression ability of convolutional features. Experiments on the COCO 2017 dataset showed that, compared with the baseline method YOLO-Pose, the average accuracy of the proposed network on the COCO 2017 validation dataset was improved by 4.8% while minimizing the amount of network parameters and calculations. The experimental results demonstrated that our proposed method can improve the detection accuracy of human pose estimation while ensuring that the model is lightweight.
ISSN:2076-3417
2076-3417
DOI:10.3390/app13063614