Orientation-Independent Activity Recognition Using Orthogonal Inertial Sensors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Inertial sensors face challenges in accurately measuring human motion due to sensitivity to shock, temperature, and electrical noise, and require calibration to account for arbitrary offsets and scale factors, while also lacking a subject's frame of reference, limiting their use in unconstrained environments.
Innovation Solution
An activity recognition system utilizing a sensor unit with orthogonal linear and rotational motion sensors, supported by a subject with arbitrary orientation, processes signals from accelerometers and gyroscopes to determine activity independently of sensor orientation, employing methods like autocorrelation and Viterbi algorithm for motion signature matching.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If inertial sensors are used to measure human motion, then the ability to measure motion without extensive modifications is improved, but measurement precision deteriorates due to sensitivity to shock, temperature, and electrical noise
Solution Approach 1:
The patent combines multiple inertial sensors (accelerometers and gyroscopes) into an integrated sensor unit to measure both linear and rotational motion. By merging complementary sensor types that measure different aspects of motion, the system achieves more complete and accurate motion capture while maintaining ease of use without extensive modifications to clothing or equipment.
Solution Approach 2:
The sensor unit is designed to function in multiple orientations and measurement modes, capable of detecting both linear acceleration and rotational velocity simultaneously. This multi-functional design allows the same sensor unit to accurately measure various types of human motion regardless of how it is positioned on or with the subject, resolving the contradiction between ease of use and measurement precision.
2Ease of operation
If inertial sensors are used without calibration, then ease of operation is improved, but measurement precision deteriorates due to arbitrary offsets and scale factors
Solution Approach 1:
The patent implements a calibration process that is performed beforehand to determine offset and scale factors for each sensor. By conducting calibration in advance under known conditions, the system establishes reference values that compensate for sensor imperfections, enabling accurate measurements during actual use without requiring repeated calibration and maintaining ease of operation.
3Adaptability or versatility
If sensors are attached with arbitrary orientation, then adaptability is improved, but device complexity increases due to the need for orientation-independent processing
Solution Approach 1:
The patent measures both linear acceleration and rotational velocity, effectively adding a rotational dimension to the motion measurement. By capturing motion in multiple dimensions (linear and rotational), the system can process signals from sensors in any orientation and still accurately determine human activity, achieving orientation independence without excessive complexity.
4Device complexity
If only linear motion sensors are used, then device complexity is reduced, but measurement precision deteriorates due to inability to capture rotational motion
Solution Approach 1:
The patent combines linear motion sensors (accelerometers) and rotational motion sensors (gyroscopes) into an integrated sensor unit. This merging of complementary sensor types enables complete measurement of human motion including both linear and rotational components, achieving high measurement precision while maintaining reasonable device complexity through integrated design.
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 flexible and accurate activity recognition without preconditions on sensor orientation, effectively classifying human activities in various contexts using inertial sensors, even in mobile and unconstrained scenarios.
Implementation Method 1
a plurality of linear motion sensors configured to detect linear motions
Implementation Method 2
a plurality of rotational motion sensors configured to detect rotational motions
Data Source
AI summary
There is provided an activity recognition apparatus for detecting an activity of a subject. The apparatus includes: a sensor unit including a plurality of linear motion sensors configured to detect linear motions and a plurality of rotational motion sensors, the linear motions being orthogonal to each other, the rotational motions being orthogonal to each other; and a computational unit configured to receive and process signals from the sensors included in the sensor unit so as to detect an activity of the subject. The sensor unit is directly or indirectly supported by the subject with an arbitrary orientation with respect to the subject. The computational unit performs a calculation that uses the signals from both linear motion sensors and rotational motion sensors to determine the activity of the subject independent of the orientation of the sensor unit.