Multi-Scale Feature Refined Network for Human Pose Estimation
- 9 November 2023
- journal article
- research article
- Published by World Scientific Pub Co Pte Ltd in International Journal of Pattern Recognition and Artificial Intelligence
- Vol. 38 (01)
Abstract
Occlusive keypoints has been a challenge for human pose estimation, especially the mutual occlusion of human bodies. One possible solution to this problem is to utilize multi-scale features, where small scale features are capable of identifying keypoints, while large-scale features can capture the relationship between keypoints. Feature fusion among multi-scale features allows for the exchange of information between keypoints, facilitating the inference of occluded keypoints based on the identified keypoints. However, it’s found that there are invalid features in feature fusion which will interfere valid feature. In this paper, we propose multi-scale feature refined network (MSFRNet) based on HRNet and a new attention module namely multi-resolution attention module (MRAM). The proposed MRAM is designed to strengthen the effective information while suppressing redundant information. It has multiple inputs and outputs and can learn the relationships between keypoints while retaining detailed information. The proposed MSFRNet outperforms HRNet, achieving a 1.4[ ]AP improvement on the COCO dataset with only a marginal computational increase of 0.35 GFLOPs. Additionally, it demonstrates superior performance with a 0.9[ ]AP, 0.7[ ]AP, and 1.8[ ]AP improvement on the MPII, CrowdPose and OCHuman datasets, respectively. Furthermore, compared with the latest attention mechanism PSA, the MSFRNet exhibits lower computational cost while maintaining the same pose-estimation accuracy.Keywords
This publication has 31 references indexed in Scilit:
- Multi-Scale Structure-Aware Network for Human Pose Estimation2018
- CBAM: Convolutional Block Attention Module2018
- Simple Baselines for Human Pose Estimation and Tracking2018
- A Coarse-Fine Network for Keypoint Localization2017
- Feature Pyramid Networks for Object Detection2017
- Multi-context Attention for Human Pose Estimation2017
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Stacked Hourglass Networks for Human Pose Estimation2016
- 2D Human Pose Estimation: New Benchmark and State of the Art Analysis2014
- MODEC: Multimodal Decomposable Models for Human Pose Estimation2013