一种洗手间跌倒检测方法
By using dynamic point cloud and micro-motion point cloud layering processing, combined with Doppler characteristics and high layering features, and employing the N/M criterion and interference confidence adaptive adjustment, the multipath interference and water flow interference problems in restroom fall detection are solved, achieving accurate detection with low false alarms and low false negatives.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SHANGHAI SONGCHUNGUO HEALTH TECH CO LTD
- Filing Date
- 2026-06-17
- Publication Date
- 2026-07-17
AI Technical Summary
Existing fall detection methods in restrooms based on millimeter-wave radar struggle to achieve both low false alarms and low false negatives when faced with multipath interference, water flow interference, and complex movement patterns. They are also susceptible to interference sources that can lead to false positives or false negatives.
By employing dynamic point cloud and micro-motion point cloud layering processing, combined with Doppler characteristics and height layering features, and adaptively adjusting the N/M criterion and interference confidence, accurate detection of fall behavior is achieved.
It can effectively penetrate glass partitions to obtain obstructed human body signals, reduce missed detections and false alarms, and improve the accuracy and reliability of fall detection in complex restroom environments.
Smart Images
Figure CN122410474A_ABST