Loading…

Multi-resolution Fusion Network for Human Pose Estimation in Low-resolution Images

2D human pose estimation still faces difficulty in low-resolution images. Most existing top-down approaches scale up the target human bonding box images to the large size and insert the scaled image into the network. Due to up-sampling, artifacts occur in the low-resolution target images, and the de...

Full description

Saved in:
Bibliographic Details
Published in:KSII transactions on Internet and information systems 2022-07, Vol.16 (7), p.2328-2344
Main Authors: Kim, Boeun, Choo, YeonSeung, Jeong, Hea In, Kim, Chung-Il, Shin, Saim, Kim, Jungho
Format: Article
Language:Korean
Subjects:
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:2D human pose estimation still faces difficulty in low-resolution images. Most existing top-down approaches scale up the target human bonding box images to the large size and insert the scaled image into the network. Due to up-sampling, artifacts occur in the low-resolution target images, and the degraded images adversely affect the accurate estimation of the joint positions. To address this issue, we propose a multi-resolution input feature fusion network for human pose estimation. Specifically, the bounding box image of the target human is rescaled to multiple input images of various sizes, and the features extracted from the multiple images are fused in the network. Moreover, we introduce a guiding channel which induces the multi-resolution input features to alternatively affect the network according to the resolution of the target image. We conduct experiments on MS COCO dataset which is a representative dataset for 2D human pose estimation, where our method achieves superior performance compared to the strong baseline HRNet and the previous state-of-the-art methods.
ISSN:1976-7277
1976-7277