Marker-Free Gait Analysis Using Video-Based Spatio-Temporal Modeling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current walking analysis processes require the presence of a qualified professional, making them expensive and limiting the frequency of assessments, especially for diagnosing and monitoring diseases like Parkinson's.
Innovation Solution
A marker-free analysis process that uses a model-based approach to analyze an individual's gait without the need for sensors, allowing for the quantification of gait parameters such as stride length, pace, and support times, which can be performed by a non-expert practitioner.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual or automatic segmentation based on gait-related signals is used, then accurate gait measurement is achieved, but the presence of a trained professional is required, increasing cost and limiting assessment frequency
Solution Approach 1:
The system performs automatic segmentation of the gait cycle using computational algorithms that analyze video data without requiring manual intervention or professional expertise. The method automatically detects key gait events (heel strike, toe-off) and calculates gait parameters, enabling the system to serve itself and eliminate the need for trained professionals while maintaining measurement accuracy
Solution Approach 2:
The patent replaces the mechanical system of manual professional assessment with an automated computational system that uses video analysis and algorithms to perform gait segmentation and parameter extraction. This substitution transforms the assessment process from a human-dependent mechanical operation to an automated digital system
2Reliability
If a trained professional performs gait analysis, then accurate diagnosis and monitoring is achieved, but the cost increases and assessment frequency is limited
Solution Approach 1:
The automated system performs reliable gait analysis independently without requiring professional intervention, enabling frequent assessments to be conducted routinely. The system can process multiple assessments over time, providing continuous monitoring capability that increases productivity while maintaining diagnostic reliability through consistent algorithmic application
Solution Approach 2:
The system enables continuous and frequent gait assessments by automating the analysis process. Multiple assessments can be performed in sequence without the constraints of professional availability, allowing for continuous monitoring of gait parameters over time to track disease progression or treatment effects
3Device complexity
If marker-free model-based method is used, then cost and complexity are reduced, but measurement precision may be compromised
Solution Approach 1:
The patent replaces complex mechanical marker systems with a model-based computational approach that uses video data and mathematical models to estimate gait parameters. This substitution simplifies the physical system while maintaining measurement precision through sophisticated algorithms that compensate for the absence of physical markers
Solution Approach 2:
The method changes the measurement parameters from direct physical marker tracking to model-based estimation using video data. By transforming the measurement approach from direct observation to computational inference, the system achieves accurate gait parameter extraction without requiring complex marker systems
Data Source
Figure 1~3
Figure 4~6
Figure 7~8
AI summary
The invention relates to a method for analysing the gait of an individual comprising at least the following steps: i. acquiring a stream of images of the individual walking, ii. determining the position of the right foot and the position of the left foot of the individual, then iii. performing spatio-temporal modelling of the gait of the individual, this comprising: a. for each foot, constructing a graphical representation (3, 4) of the path of the foot using a model in which each phase of placing weight on the foot is represented differently and separately from two other phases, namely a preceding phase of deceleration of the foot and a subsequent phase of acceleration of the foot, b. placing the representations 3 and 4 constructed for the left foot and for the right foot in spatio-temporal alignment with each other, then c. computing at least one parameter of the gait of the individual on the basis of the two aligned representations.