Hierarchical Motion Determination Using Temporal Sequences
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing motion determination systems using sensors struggle to accurately identify specific user motions, especially in complex scenarios, as they often rely on simplistic threshold-based methods that fail to differentiate between similar motion patterns.
Innovation Solution
A motion determination apparatus that employs a combination of basic motion detection, temporal sequence recording, and detailed label determination using pre-defined tables and sensors like tri-axial acceleration, gyro, and geo-magnetic sensors to identify and categorize user activities into specific motion scenes and detailed labels.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If threshold-based motion detection methods are used, then the system is simple to implement, but the measurement precision of user motion identification deteriorates
Solution Approach 1:
The patent segments motion determination into multiple hierarchical levels: basic motion determination (e.g., walking, running, standing), motion scene determination (e.g., material handling, assembling, cleaning), and detailed label determination (specific motion variations). This segmentation allows the system to achieve high precision through cumulative classification rather than relying on a single complex threshold-based method.
Solution Approach 2:
The patent employs preliminary action by first determining basic motion types before proceeding to motion scene and detailed label determination. The basic motion determination serves as a preliminary classification that narrows down the search space for subsequent more specific classifications, improving overall measurement precision while maintaining system simplicity.
2Device complexity
If simple motion detection methods are used, then the device complexity is low, but the reliability of motion determination deteriorates
Solution Approach 1:
The patent divides the motion determination process into three separate determination modules: basic motion determination module, motion scene determination module, and detailed label determination module. Each module handles a specific aspect of motion classification, improving reliability through specialized processing while keeping individual module complexity manageable.
Solution Approach 2:
The patent implements feedback mechanisms where determination results from one module inform and constrain the search space of subsequent modules. For example, basic motion determination results guide the motion scene determination, which in turn constrains the detailed label determination, creating a feedback loop that enhances overall determination reliability.
3Measurement precision
If detailed motion classification is implemented, then the measurement precision improves, but the device complexity increases
Solution Approach 1:
The patent segments the complex classification task into three hierarchical levels with distinct determination modules and corresponding determination tables. This segmentation allows detailed motion classification to be achieved while managing complexity through modular design, where each module handles a specific classification level independently.
Solution Approach 2:
The patent adds temporal dimension to motion classification by recording basic motions in temporal sequence and using this historical context for motion scene and detailed label determination. This temporal dimension enables accurate differentiation of similar motion patterns based on their sequence and duration, improving measurement precision without proportionally increasing device complexity.
Data Source
AI summary
In one embodiment, a motion determination apparatus includes: a basic motion determination module determining a basic motion of a user, based on a sensor signal for detecting a motion of the user; a basic motion recording module recording the basic motion in a temporal sequence; a motion scene determination table configured to store the basic motion and a condition under which the basic motion occurs, for each motion scene; a motion scene determination module determining that the basic motion recorded in the temporal sequence corresponds to a certain motion scene, based on the motion scene determination table; a detailed label determination table storing a detailed label indicating a detailed motion in the motion scene, for each motion scene; and a detailed label determination module determining that the basic motion included in the motion scene corresponds to a certain detailed label, based on the detailed label determination table.