Transfer Learning for Keypoint Detection in Low-Resolution Thermal TUG Test Images

作     者：Chen, Wei-Lun Hsieh, Chia-Yeh Kao, Yu-Hsiang Liu, Kai-Chun Peng, Sheng-Yu Tsao, Yu 

作者机构：Research Center for Information Technology Innovation Academic Sinica Taiwan Graduate Institute of Electrical Engineering National Taiwan University Taiwan Bachelor’s Program in Medical Informatics and Innovative Applications Fu Jen Catholic University Taiwan Department of Electrical Engineering National Taiwan University Taiwan College of Information and Computer Sciences University of Massachusetts AmherstMA01003 United States Department of Electrical Engineering National Taiwan University of Science of Technology Taiwan 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2025年

核心收录：

主　　题：Thermography (imaging) 

摘      要：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. Copyright © 2025, The Authors. All rights reserved.