Accelerometer Gravity Vector Projection for Fall Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for estimating vertical velocities and displacements from accelerometer measurements in fall detectors, particularly those worn as pendants, do not provide sufficiently accurate estimates, leading to a high false alarm rate and reduced fall detection efficiency.
Innovation Solution
A method that estimates vertical velocities and displacements by calculating unit vectors representing acceleration due to gravity, projecting measurement samples onto these vectors, subtracting gravity acceleration, and integrating the results to obtain refined vertical acceleration estimates, which are then used to determine if a fall has occurred.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing methods for estimating vertical velocity and displacement are used in pendant fall detectors, then the device remains lightweight and unobtrusive, but the estimation accuracy is insufficient leading to high false alarm rate
Solution Approach 1:
The patent transforms the accelerometer measurement space by computing unit vectors representing gravity direction and projecting measurements onto these vectors. This changes the parameter representation from raw 3D acceleration components to vertically-projected scalar values, enabling more accurate fall detection while maintaining the lightweight pendant form factor
Solution Approach 2:
The unit vectors representing gravity direction serve as an intermediary that mediates between the raw accelerometer measurements and the fall detection algorithm. By projecting measurements onto these intermediary vectors, the system extracts the vertical component more accurately without adding physical mass to the device
2Measurement precision
If gravity acceleration is not subtracted from measurement samples, then the processing is simpler, but the vertical acceleration estimation is inaccurate
Solution Approach 1:
The patent performs preliminary action by pre-computing unit vectors representing gravity direction from the accelerometer measurements themselves. These unit vectors are then used to project and process subsequent measurements, separating the gravity subtraction step from the raw data processing and enabling more accurate vertical acceleration estimation
Solution Approach 2:
The patent extracts the gravity component from the accelerometer measurements by projecting onto unit vectors and subtracting the known gravity acceleration. This extraction isolates the vertical acceleration due to motion from the constant gravitational field, improving measurement precision while adding only minimal processing complexity
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach significantly improves the accuracy of vertical velocity and displacement estimation, reducing false alarms and enhancing the detection of falls in pendant-type fall detectors while maintaining a high detection probability.
Implementation Method 1
an accelerometer for producing a time series of measurement samples representing the acceleration acting on the fall detector
Implementation Method 2
estimating a corresponding time series of unit vectors representing acceleration due to gravity in the reference frame of the accelerometer from the time series of measurement samples
Data Source
AI summary
A fall detector includes an accelerometer for producing a time series of measurement samples representing the acceleration acting on the fall detector; a processor for estimating a vertical velocity and/or displacement of the fall detector from the measurement samples and using the estimated vertical velocity and/or displacement to determine whether the user has suffered a fall. The processor is configured to estimate a vertical velocity and/or displacement of the fall detector by estimating a corresponding time series of unit vectors representing acceleration due to gravity in the reference frame of the accelerometer from the time series of measurement samples; projecting each measurement sample onto the corresponding unit vector and subtracting acceleration due to gravity to give a series of estimates for the vertical acceleration of the fall detector; and integrating the series of estimates to give a time series of values for the vertical velocity and/or displacement of the fall detector.