Deep Learning-based Gait Recognition and Evaluation of the Wounded
The use of AI, particularly deep convolutional neural networks like YOLOv5, shows promise in enabling fast, remote traumatic injury assessment during disaster response. This approach could assist healthcare professionals in identifying injury risks when physical access to patients is restricted, thereby improving triage efficiency and early intervention.
Authors
- Yao Xiao (ORCID: https://orcid.org/0000-0002-0622-1045)
- Yifei Shen (ORCID: https://orcid.org/0000-0002-1401-7183)
- Zhijian He (ORCID: https://orcid.org/0000-0003-4871-5497)
- Feng Zeng (ORCID: https://orcid.org/0000-0003-0171-2045)
- Minghua Liu (ORCID: https://orcid.org/0000-0002-6603-1251)
- Chuanchuan Liu
- Xiangyu Chen (ORCID: https://orcid.org/0000-0002-0711-0275)
- Yi Zhang (ORCID: https://orcid.org/0000-0001-7477-7881)
- Liang Zhang (ORCID: https://orcid.org/0000-0003-1566-4902)
- Zhuo Li (ORCID: https://orcid.org/0000-0002-9937-2669)
- Ling-Hu Cai
Institutions
- Chongqing University of Posts and Telecommunications (CN)
- Army Medical University (CN)
- Lingnan University (HK)
- Hong Kong University of Science and Technology (HK)
- Southwest Hospital (CN)
Publication Details
- Journal
- Disaster Medicine and Public Health Preparedness
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1017/dmp.2025.10179
- Primary Topic
- Autopsy Techniques and Outcomes
- Type
- article
- Field-Weighted Citation Impact
- 0.00