Whole-Body Posture Estimation From Smart Shoe Inertial Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for continuously measuring whole body posture, such as motion capture and wearable devices, face challenges in capturing the entire body or requiring multiple sensors, making it difficult to grasp the whole body posture on a daily basis.
Innovation Solution
A posture estimating device and method using a sensor in a smart shoe to measure acceleration and angular velocity, combined with machine learning to estimate whole body posture, allowing continuous monitoring without the need for extensive sensor wear.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If motion capture or moving image method is used to measure whole body posture, then measurement precision is improved, but ease of operation deteriorates because it is difficult to continuously capture the whole body with the whole body always included in the imaging range
Solution Approach 1:
The patent replaces the mechanical/optical measurement system (motion capture cameras, imaging devices) with an inertial sensor-based system. The wearable device uses accelerometers, gyroscopes, and magnetometers to measure body movement, eliminating the need for complex imaging infrastructure and making continuous daily posture measurement practical and easy to operate.
Solution Approach 2:
The patent creates a virtual model of the whole body posture by copying and integrating data from multiple inertial sensors placed on different body parts. The processing circuitry reconstructs the complete body posture from partial sensor measurements, effectively creating a digital replica of the actual physical posture without requiring direct optical capture of the entire body.
2Ease of operation
If wearable device is used to continuously measure posture on daily basis, then ease of operation is improved, but measurement precision deteriorates because only partial posture can be grasped
Solution Approach 1:
The patent merges data from multiple inertial sensors placed on different body parts (e.g., waist, head, arms, legs) into a unified posture estimation. The processing circuitry integrates acceleration, angular velocity, and magnetic field data from all sensors to reconstruct the complete whole body posture, transforming limited partial measurements into comprehensive full-body posture information.
Solution Approach 2:
The patent adds the dimension of data fusion and computational processing to transform limited sensor inputs into complete posture information. By processing sensor data in the computational domain and using the estimation model to infer unmeasured body parts from measured ones, the system achieves whole body posture measurement from partial sensor inputs.
3Measurement precision
If many sensor devices are attached to joint sites and vicinities of ends of body to grasp whole body posture, then measurement precision is improved, but device complexity increases making it difficult to continuously wear
Solution Approach 1:
The patent makes each inertial sensor module multi-functional by equipping it with both sensing capabilities (accelerometer, gyroscope, magnetometer) and processing capabilities (processing circuitry with estimation model). Each sensor unit can independently process its local data and contribute to whole-body posture estimation, reducing the need for additional dedicated sensors at every body joint while maintaining measurement precision.
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
Enables accurate and continuous estimation of whole body posture during daily activities, reducing burden on the user and improving monitoring of walking or running form.
Implementation Method 1
at least one sensor attached to the person to be measured, the at least one sensor acquiring measurement data based on an acceleration of three axes and an angular velocity of the three axes
Implementation Method 2
at least one sensor attached to the person to be measured, the at least one sensor acquiring measurement data based on an acceleration of three axes and an angular velocity of the three axes
Data Source
AI summary
A posture estimating device includes: at least one sensor attached to the person to be measured, the at least one sensor acquiring walking data based on an acceleration of three axes and an angular velocity of the three axes at at least one location of the person to be measured; a processing circuitry that estimates, using an estimation model trained by machine learning, the whole body posture of the person to be measured during the predetermined motion from the walking data acquired by the sensor; and an output device that outputs estimation data. The estimation model is generated in advance by training by machine learning based on the walking data acquired by the sensor during the predetermined motion and based on posture data obtained by measuring the whole body posture of the person to be measured at a timing when the walking data is acquired.