Human Pose Estimation Based on Efficient and Lightweight High-Resolution Network (EL-HRNet)
Open Access
Abstract
As an important direction in computer vision, human pose estimation has received extensive attention in recent years. A High-Resolution Network (HRNet) can achieve effective estimation results as a classical human pose estimation method. However, the complex structure of the model is not conducive to deployment under limited computer resources. Therefore, an improved Efficient and Lightweight HRNet (EL-HRNet) model is proposed. In detail, point-wise and grouped convolutions were used to construct a lightweight residual module, replacing the original 3 × 3 module to reduce the parameters. To compensate for the information loss caused by the network’s lightweight nature, the Convolutional Block Attention Module (CBAM) is introduced after the new lightweight residual module to construct the Lightweight Attention Basicblock (LA-Basicblock) module to achieve high-precision human pose estimation. To verify the effectiveness of the proposed EL-HRNet, experiments were carried out using the COCO2017 and MPII datasets. The experimental results show that the EL-HRNet model requires only 5 million parameters and 2.0 GFlops calculations and achieves an AP score of 67.1% on the COCO2017 validation set. In addition, PCKh@0.5mean is 87.7% on the MPII validation set, and EL-HRNet shows a good balance between model complexity and human pose estimation accuracy.Keywords
Funding Information
- Open Foundation of the National Key Laboratory of UAV Special Technology (2022-JCJQ-LB-071, 2022MD723841)
- China Postdoctoral Science Foundation (2022-JCJQ-LB-071, 2022MD723841)
This publication has 30 references indexed in Scilit:
- CBAM: Convolutional Block Attention Module2018
- Squeeze-and-Excitation Networks2018
- Cascaded Pyramid Network for Multi-person Pose Estimation2018
- Stacked Hourglass Networks for Human Pose Estimation2016
- Deep Residual Learning for Image Recognition2016
- DeepPose: Human Pose Estimation via Deep Neural Networks2014
- 2D Human Pose Estimation: New Benchmark and State of the Art Analysis2014
- Microsoft COCO: Common Objects in Context2014
- Articulated Pose Estimation Using Discriminative Armlet Classifiers2013
- Articulated pose estimation with flexible mixtures-of-parts2011