自适应滤波和脉冲质量选择的视频呼吸率测量方法
By employing adaptive filtering and pulse quality selection, optical flow information and Chebyshev filtering are used to remove motion noise and select the optimal sub-region. This solves the problems of ambient lighting and motion artifact interference in existing methods and enables stable respiratory rate measurement in various motion scenarios.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HEFEI UNIV OF TECH
- Filing Date
- 2023-11-09
- Publication Date
- 2026-07-17
AI Technical Summary
Existing non-contact respiratory rate measurement methods are susceptible to changes in ambient light and motion artifacts, and do not fully utilize the noise reduction information from the rigid motion of the human body, which is not respiratory, leading to measurement instability.
An adaptive filtering and pulse quality selection method is adopted. The region of interest is located using the Mediapipe pose tool. Optical flow information is used to generate and denoise the signal. The respiratory signal is extracted by combining Chebyshev filtering and pulse quality selection methods. The optimal sub-region is selected for respiratory rate calculation.
The robustness and accuracy of respiratory measurement were improved in various spontaneous motion scenarios, interference from non-target areas was reduced, and stable respiratory rate extraction was achieved.
Smart Images
Figure CN117462111B_ABST