CN-121971076-A - Flexible pressure array-based attitude stability assessment and fall detection system and method

Abstract

The invention discloses a system and a method for evaluating gesture stability and detecting falling based on a flexible pressure array, and belongs to the technical field of ground sensing and intelligent interaction. The system comprises a flexible pressure sensing array paved below the ground, a data acquisition module, a characteristic extraction and judgment module and a visualization and alarm module. The system extracts the stability characteristics of the pressure center position variation, the pressure distribution envelope area and the average pressure by continuously collecting pressure distribution data formed by the contact of a human body and the ground, comprehensively analyzes the fluctuation degree of the characteristics in a sliding time window, and judges the falling state when the fluctuation degree exceeds a preset threshold value. Compared with the prior art, the method does not depend on wearable equipment or a visual acquisition device, has the advantages of strong privacy, high instantaneity, low calculation complexity, strong adaptability and the like, and is suitable for application scenes such as home-based care, medical care and public safety monitoring.

Inventors

• LUO GE
• XIA ZHENPING
• WU YANSHU
• Zhou Suhan
• FENG TIANYU
• ZHAO GUOHUI

Assignees

• 苏州科技大学

Dates

Publication Date

20260505

Application Date

20260403

Claims (5)

1. 1. A flexible pressure array-based posture stability assessment and fall detection system, comprising: The flexible pressure sensing array is paved below the ground and is used for acquiring pressure distribution data formed by the contact of a human body and the ground; The data acquisition module is used for acquiring and preprocessing the pressure distribution data in real time; The characteristic extraction and judgment module is used for calculating the stability characteristics of the pressure center position variation, the pressure distribution envelope area and the average pressure based on the pressure distribution data, carrying out statistical analysis on the fluctuation degree of the stability characteristics in a sliding time window, and judging the posture state of the human body according to the analysis result; And the visualization and alarm module is used for displaying the pressure distribution and the gesture judgment result in real time and triggering an alarm when the abnormal gesture is detected.
2. 2. The system of claim 1, wherein the stability characteristics include statistics of the amount of change in the center of pressure position calculated over a sliding time window, statistics of the area of the pressure distribution envelope including the mean and standard deviation of the amount of change, and statistics of the average pressure including the mean and standard deviation of the pressure values.
3. 3. The system according to claim 1, wherein the posture states comprise at least a standing state, a walking state and a falling state, the falling state being determined by a fluctuation degree of the stability characteristics exceeding a preset threshold range within a sliding time window and/or by a joint analysis of multi-dimensional stability characteristics.
4. 4. The attitude stability assessment and fall detection method based on the flexible pressure array is characterized by comprising the following steps of: S1, acquiring pressure distribution data formed by human body contact with the ground through a flexible pressure sensing array; s2, preprocessing the pressure distribution data to obtain effective pressure data; S3, extracting a pressure center position, a pressure distribution envelope area and average pressure based on the effective pressure data, and calculating the statistical characteristics of the variation of the pressure center position, the statistical characteristics of the pressure distribution envelope area and the statistical characteristics of the average pressure; S4, judging the human body posture state based on the stability characteristics; and S5, outputting a posture judging result, performing visual display, and triggering an alarm when the abnormal posture is detected.
5. 5. The method according to claim 4, wherein steps S1 to S5 are performed in parallel in a multithreaded manner to achieve real-time coordination of pressure data acquisition, gesture determination, and result display.

Description

Flexible pressure array-based attitude stability assessment and fall detection system and method Technical Field The invention relates to the technical field of ground sensing and intelligent interaction, in particular to a system and a method for evaluating gesture stability and detecting falling based on a flexible pressure array. Background With the increasing aging degree of the population, the safety monitoring demands for the aged and people with limited mobility are increasing. The falling is one of the most common security risks in home and medical care environments, has the characteristics of strong burst and high hazard, and has important significance in timely and accurately detecting falling events. The existing fall detection technology mainly comprises modes of wearable equipment monitoring, visual monitoring, ground pressure sensing and the like. The wearable device is worn for a long time by a user, monitoring continuity is easily affected due to insufficient wearing compliance, a visual monitoring mode is at privacy risk and is easily affected by environmental factors such as illumination and shielding, a ground pressure sensing technology is used for judging states by detecting contact pressure information of a human body and the ground, the wearable device has the advantages of being free of wearing, high in privacy and the like, but the existing scheme depends on a single pressure index, real-time performance and detection accuracy are difficult to achieve, and misjudgment or missed judgment is easily caused in a complex action scene. Therefore, there is a need for a ground sensing system and method that can perform multidimensional analysis on the stability of human body posture while ensuring computational efficiency, and achieve reliable fall detection. Specifically, the conventional fall detection scheme based on ground pressure sensing generally adopts one of the following modes, namely judging based on whether a single-moment pressure amplitude or pressure distribution area exceeds a fixed threshold value, wherein the method is difficult to distinguish normal activities such as falling, sitting, lying and the like, and judging based on the instantaneous offset of the pressure center position, but in dynamic actions such as walking, turning and the like, the short-time offset of the pressure center position is larger, and misjudgment is easy to occur. The method does not fully utilize the evolution information of the pressure characteristic in the time dimension, and is difficult to effectively characterize the process characteristic of the transition of the human body posture from stable to unstable, so that the detection accuracy and the robustness in a complex daily activity scene are insufficient. In addition, the existing ground pressure sensing scheme mostly assumes a rigid structure, and the influence of the flexible paving material on the pressure distribution signal is not fully considered. When the sensing array is laid below the flexible ground material, the pressure distribution characteristics formed by the contact of the human body and the ground are obviously different from those of the rigid ground, and special signal processing and characteristic extraction methods are needed. Disclosure of Invention The invention further aims to construct a multidimensional pressure characteristic description mode capable of representing the change of the posture stability of the human body through the joint analysis of the pressure distribution formed by the contact of the human body and the ground in the space and the time dimension, so that the system can not only recognize different posture states, but also reflect the process characteristic of the change of the posture from stable to unstable, thereby improving the reliability of abnormal posture judgment such as falling. In order to achieve the above purpose, the invention provides a posture stability evaluation and fall detection system based on a flexible pressure array, which comprises a flexible pressure sensing array paved below the ground, a data acquisition module connected with the flexible pressure sensing array, a characteristic extraction and judgment module and a visualization and alarm module. The flexible pressure sensing array is used for acquiring pressure distribution data formed in the process of contacting a human body with the ground, the data acquisition module is used for acquiring and preprocessing the pressure distribution data in real time, the characteristic extraction and judgment module is used for extracting stability characteristics of a pressure center position, a pressure distribution envelope area, average pressure and the like based on the pressure distribution data, comprehensively analyzing fluctuation degrees of the stability characteristics in a sliding time window to judge the posture state of the human body, specifically, the sliding time window covers the pressure distribution data of