.png){kind=icon}
.png){kind=icon}
Return
Human Pose Estimation Using Thermal Images
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2023.3264714.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This study addresses the human pose estimation problem on thermal images using Convolutional Neural Networks and Vision Transformer architectures. To do this, eight human pose estimation methods designed for visible images were extended to be applied in the thermal domain. Due to the lack of large, representative datasets containing labeled thermal images, this extension requires transfer learning between the visible and the thermal domain, and a database for fine-tuning the networks in the thermal domain. Thus, it is proposed to train the networks using a grayscale version of the COCO dataset, and then fine-tune them in the thermal domain. Fine-tuning is carried out using the new UCH-Thermal-Pose database presented in this work. This database includes 600 thermal images for training, 200 for validation, and 104 for testing, all of them fully labeled. Moreover, in the paper, a comparative study of the eight extended deep-based methods for human pose detection is carried out. The UCH-Thermal-Pose database is available at https://datos.uchile.cl/dataset.xhtml?persistentId=doi%3A10.34691%2FUCHILE%2F4B6NA3, and the source code of all the methods is available athttps://github.com/jsmithdlc/Thermal-Human-Pose-Estimation.
Keywords:
Detectors
Pose estimation
Training
Databases
Transformers
Transfer learning
Convolutional neural networks
Deep learning
Thermal management
vision transformer
deep neural networks
human pose estimation
thermal images