Saved in:
Bibliographic Details
Main Authors: Chen, Wei-Lun, Hsieh, Chia-Yeh, Kao, Yu-Hsiang, Liu, Kai-Chun, Peng, Sheng-Yu, Tsao, Yu
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.18453
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915568411475968
author Chen, Wei-Lun
Hsieh, Chia-Yeh
Kao, Yu-Hsiang
Liu, Kai-Chun
Peng, Sheng-Yu
Tsao, Yu
author_facet Chen, Wei-Lun
Hsieh, Chia-Yeh
Kao, Yu-Hsiang
Liu, Kai-Chun
Peng, Sheng-Yu
Tsao, Yu
contents This study presents a novel approach to human keypoint detection in low-resolution thermal images using transfer learning techniques. We introduce the first application of the Timed Up and Go (TUG) test in thermal image computer vision, establishing a new paradigm for mobility assessment. Our method leverages a MobileNetV3-Small encoder and a ViTPose decoder, trained using a composite loss function that balances latent representation alignment and heatmap accuracy. The model was evaluated using the Object Keypoint Similarity (OKS) metric from the COCO Keypoint Detection Challenge. The proposed model achieves better performance with AP, AP50, and AP75 scores of 0.861, 0.942, and 0.887 respectively, outperforming traditional supervised learning approaches like Mask R-CNN and ViTPose-Base. Moreover, our model demonstrates superior computational efficiency in terms of parameter count and FLOPS. This research lays a solid foundation for future clinical applications of thermal imaging in mobility assessment and rehabilitation monitoring.
format Preprint
id arxiv_https___arxiv_org_abs_2501_18453
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Transfer Learning for Keypoint Detection in Low-Resolution Thermal TUG Test Images
Chen, Wei-Lun
Hsieh, Chia-Yeh
Kao, Yu-Hsiang
Liu, Kai-Chun
Peng, Sheng-Yu
Tsao, Yu
Computer Vision and Pattern Recognition
Image and Video Processing
This study presents a novel approach to human keypoint detection in low-resolution thermal images using transfer learning techniques. We introduce the first application of the Timed Up and Go (TUG) test in thermal image computer vision, establishing a new paradigm for mobility assessment. Our method leverages a MobileNetV3-Small encoder and a ViTPose decoder, trained using a composite loss function that balances latent representation alignment and heatmap accuracy. The model was evaluated using the Object Keypoint Similarity (OKS) metric from the COCO Keypoint Detection Challenge. The proposed model achieves better performance with AP, AP50, and AP75 scores of 0.861, 0.942, and 0.887 respectively, outperforming traditional supervised learning approaches like Mask R-CNN and ViTPose-Base. Moreover, our model demonstrates superior computational efficiency in terms of parameter count and FLOPS. This research lays a solid foundation for future clinical applications of thermal imaging in mobility assessment and rehabilitation monitoring.
title Transfer Learning for Keypoint Detection in Low-Resolution Thermal TUG Test Images
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2501.18453