Swallowing action recognition method and system based on computer vision
By combining multi-source sensing and deep learning technologies with wide-angle depth-of-field imaging, millimeter-wave vibration sensing, and infrared thermal sensing, accurate monitoring and safety assessment of swallowing movements in the elderly have been achieved. This solves the problems of inefficiency and comfort associated with traditional monitoring methods and supports reliable long-term monitoring of the elderly's eating safety.
CN122182010APending Publication Date: 2026-06-12ZHUNENG TECHNOLOGY (JIAXING) CO LTD
View PDF 0 Cites 0 Cited by
Patent Information
- Application Number
- CN202610043376.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-01-14
- Publication Date
- 2026-06-12
Smart Images
Figure CN122182010A_ABST
Abstract
The present application relates to the technical field of computer vision and biosignal processing, and discloses a swallowing action recognition method and system based on computer vision, which comprises a multi-source perception module, a signal processing and feature extraction module, a multi-modal fusion and decision module, and a risk assessment and feedback module. The system realizes accurate monitoring and risk assessment of swallowing events through multi-source data acquisition such as wide-angle depth imaging, millimeter wave vibration sensing and infrared thermal sensing, combined with time alignment, geometric dynamic characteristic extraction, vibration and thermodynamic analysis. The system adopts a Transformer network for multi-modal fusion, and provides real-time early warning and intervention support through personalized benchmark modeling and dynamic Bayesian inference. The present application can overcome the limitations of single-mode monitoring and is suitable for weak swallowing behavior recognition and safety evaluation in complex environments.
Need to check novelty before this filing date? Find Prior Art