Millimeter wave radar human body tumble detection method based on multi-feature fusion

Through multi-feature fusion methods, adaptive clustering, multipath filtering, deep time series learning and multimodal information are used to solve the problems of high false alarm rate and poor real-time performance of millimeter-wave radar in human fall detection in complex home environments, and achieve high-accuracy and low-resource consumption fall detection.

CN120643202AActive Publication Date: 2025-09-16四川工程职业技术大学
7 Cites 10 Cited by

Patent Information

Application Number
CN202511141685.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-08-15
Publication Date
2025-09-16
Estimated Expiration
2045-08-15

AI Technical Summary

Technical Problem

Existing millimeter-wave radar human fall detection methods have difficulty distinguishing between falls and lying down in complex home environments, have a high false alarm rate, and have limited adaptability to environmental noise and interference. The high resource requirements of deep learning models lead to poor real-time performance.

Method used

A multi-feature fusion method is adopted, including data preprocessing, dynamic clustering, multipath false cluster filtering, time series tracking, deep time series model and posture data fusion. By combining adaptive neighborhood radius density clustering, Kalman filtering, bidirectional LSTM network and multimodal information of visual devices, the detection accuracy and real-time performance are improved.

Benefits of technology

It significantly reduces the false alarm and missed alarm rates, improves detection accuracy and real-time performance in complex environments, reduces the demand for hardware resources, adapts to different heights and fall methods, and achieves fast response and stable fall detection.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a millimeter wave radar human body tumble detection method based on multi-feature fusion, and the method comprises the steps: obtaining an original point cloud frame from each radar, and carrying out the timestamp calibration and space coordinate system conversion; performing noise filtering, ground segmentation and human body point cloud extraction on each frame of point cloud; dividing the preprocessed point cloud into a static cluster and a dynamic cluster; filtering false dynamic clusters; extracting a residual dynamic cluster set, and identifying and tracking the human body dynamic clusters in continuous frames by adopting a tracking algorithm; extracting a corrected time sequence feature from the tracked human body cluster; inputting the time sequence characteristics into a pre-trained deep time sequence network, learning a falling time sequence dependency relationship, and outputting an abnormal index; and performing multi-source fusion with the abnormal index to obtain a comprehensive index to judge whether to trigger an alarm. The method can adapt to a complex home environment, improves the detection accuracy and real-time performance, and reduces the false alarm and missing alarm.
Need to check novelty before this filing date? Find Prior Art