์๋ฌธ์ ๋ณด
์ด๋ก
์์ด
We purposed to propose a method to analyze the movement during whole-body exercise using a 2D camera. Specifically, we filmed the participants performing a specific whole body movement in front of the 2D camera in a normal state and a Pseudo-Elderly state that imitated the posture of older adults. We used the posture analysis algorithm YOLO to obtain two-dimensional spatial coordinate information for 16 parts of the body and perform a movement analysis for the two states. Consequently, we were unable to identify any significant differences between young people and the Pseudo-Elderly in terms of the total amount of differences in the coordinates of the ๐ฅ-axis (lateral movement) and ๐ฆ-axis (front-back movement) for the 16 parts of the body. However, we could identify significant differences between young people and the Pseudo-Elderly by analyzing each part of the body, such as the head and ankle. Since we suppose that the method proposed in this study can analyze the movement state of whole body movements using a 2D camera that is usually used in daily life, we hope to apply it to a system for monitoring and improving the movement of older adults at home and a system for early detection of diseases with movement disorders in the future.
๋ชฉ์ฐจ
1. Introduction
2. Methods
2.1. Participants
2.2. Experimental method
2.3. Movement task
2.4. Analytical method
3. Result
3.1. Comparison of Younger and Pseudo-Elderly in the backward-forward movement task
3.2. Comparison of Younger and Pseudo-Elderly in the left-right movement task
4. Discussion
5. Conclusion
References
