3-Axis Inertial Gait Step Detection With Abnormal-Phase Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies face challenges in accurately detecting the operation of a user's gait without location limitations, particularly in distinguishing normal gait from abnormal movements.
Innovation Solution
An information processing device and method that utilizes a 3-axis inertial sensor to acquire original acceleration and angular velocity, converting these into global coordinates to detect the start of one step in gait by analyzing a first angle and resultant value, and applying conditions to exclude abnormal gait phases.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If motion capture using inertial measurement unit and multiple cameras is used, then detection accuracy of gait operation is improved, but device complexity and cost increase
Solution Approach 1:
The patent extracts the essential function of gait detection from a complex multi-camera system and implements it using only a single inertial measurement unit. By removing unnecessary components (multiple cameras and complex synchronization systems) while retaining the core detection capability, the system achieves acceptable measurement precision with significantly reduced device complexity.
Solution Approach 2:
The inertial measurement unit performs self-calibration and self-reference operations to maintain detection accuracy without requiring external calibration equipment or multiple reference sensors. The system uses its own internal sensors (accelerometers and gyroscopes) to cross-validate measurements and compensate for drift, enabling accurate gait detection with a single standalone device.
2Measurement precision
If multiple sensors and cameras are deployed for accurate gait detection, then measurement precision is improved, but ease of operation deteriorates
Solution Approach 1:
The patent removes the operational complexity associated with multiple sensors and cameras, leaving only a single inertial measurement unit that can be easily attached to the user. This extraction simplifies the user experience while maintaining the essential detection functionality through intelligent processing of data from the single device.
Solution Approach 2:
The system automatically performs calibration, coordinate system transformation, and gait phase detection without requiring user intervention or setup procedures. The inertial measurement unit self-adjusts to the user's anatomy and movement patterns, eliminating the need for manual configuration and making the system immediately easy to use upon attachment.
3Measurement precision
If complex processing algorithms are applied to distinguish normal gait from abnormal movements, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent transforms the raw acceleration and angular velocity data into different parameter representations (coordinate system transformations, derived kinematic parameters) that reveal gait phase information more clearly. By changing the parameters from which gait is analyzed, the system achieves accurate distinction between normal and abnormal movements using relatively simple threshold-based or pattern-recognition algorithms rather than complex machine learning models.
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
Enhances the accuracy of detecting the start time of one step in normal gait by excluding abnormal movements, allowing precise gait operation analysis without location constraints.
Implementation Method 1
an inertial sensor that detects an angular velocity and an acceleration of each of three axes directions
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An information processing device includes a communication unit and a control unit. An acquisition unit acquires an original acceleration and an original angular velocity from a 3-axis inertial sensor. The control unit certifies start of one step using a first angle and a resultant value. The first angle is an angle with respect to a vertical direction based on the original angular velocity. The resultant value is based on the original acceleration.