Non-contact Gait Monitoring Using Radar Point Clouds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current gait monitoring technologies face challenges in accurately and continuously detecting gait abnormalities in elderly individuals due to lack of standardized norms, privacy concerns with camera-based systems, and inability to perform permanent measurements in real-life environments, leading to inefficient diagnosis and monitoring of gait-related health issues.
Innovation Solution
A non-contact system using ultra-wideband radar and machine learning to capture and analyze three-dimensional point clouds of user movements, determining gait patterns and abnormalities by calculating centroids, momentary walking velocities, and detecting deviations in gait speed, providing continuous monitoring and instant warnings for abnormal gait behaviors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If camera-based motion capture devices are used for gait monitoring, then gait patterns can be captured, but privacy requirements are violated
Solution Approach 1:
The patent replaces camera-based optical measurement systems with radar-based electromagnetic wave measurement systems. The radar system uses electromagnetic waves to capture gait patterns without visual recording, thereby maintaining measurement precision while eliminating privacy violations associated with camera-based systems.
Solution Approach 2:
The patent introduces radar technology as an intermediary between the monitoring need and the subject. Instead of direct visual capture by cameras, radar waves serve as an intermediary that can measure gait parameters without creating privacy-intrusive visual records, thus resolving the contradiction between measurement capability and privacy protection.
2Measurement precision
If wearable gait analysis devices are used, then gait measurements can be obtained, but permanent measurements in real-life environments are not enabled
Solution Approach 1:
The patent employs machine learning algorithms that automatically learn and adapt to individual gait patterns without requiring manual calibration or configuration. The system performs self-adjustment to accommodate varying real-life environments, enabling permanent measurements across diverse settings without requiring user intervention or device reconfiguration.
Solution Approach 2:
The patent implements dynamic adaptation through machine learning models that continuously learn from incoming data and adjust to changing environmental conditions and individual behaviors. This dynamic capability allows the system to maintain measurement accuracy across varied real-life environments rather than being restricted to controlled settings.
3Measurement precision
If standardized gait norms are established, then gait abnormalities can be detected, but lack of standards makes detection challenging
Solution Approach 1:
The patent performs preliminary action by automatically establishing personalized gait baseline norms through machine learning analysis of collected data. Instead of relying on pre-defined population standards, the system learns individual-specific normal gait patterns first, then uses these personalized norms to detect abnormalities, simplifying the detection process while improving accuracy.
Solution Approach 2:
The patent implements feedback mechanisms where the system continuously monitors gait patterns, compares them against learned norms, and adjusts the norms based on accumulated data. This feedback loop automatically refines the detection standards over time, enabling accurate abnormality detection without requiring complex manual standard-setting procedures.
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 reliable, continuous, and non-invasive gait monitoring, accumulating statistics and patterns, detecting abnormalities, and generating reports and warnings for potential medical issues, improving the detection of gait-related health concerns in elderly populations.
Implementation Method 1
A non-contact system using ultra-wideband radar and machine learning to capture and analyze three-dimensional point clouds of user movements
Data Source
AI summary
Determining gait patterns and abnormalities of a user includes forming a plurality of point clouds corresponding to the user, each of the point clouds being three-dimensional coordinates of moving points, frame by frame, through a data capturing session, determining centroids of the point clouds, determining momentary walking velocities using estimates based on vectors connecting the centroids for adjacent frames captured during walking of the user, determining gait speed for the user based on the momentary walking velocities, determining at least one distribution of gait speeds for the user, and detecting gait abnormalities based on deviation of the gait speed from the at least one distribution of gait speeds. Detecting a plurality of point clouds may include using a tracking device to capture movements of the user. The tracking device may use radar and/or lidar. The system may determine a gait pattern of the user corresponding to routines of the user.