Gait Analysis Using 3D Depth Sensor and Eigenvector Curvature
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current gait analysis systems are costly, require dedicated spaces and trained technicians, and are limited in their ability to simulate real-life mobility, while sensor-based solutions face issues with noise, signal drift, and patient discomfort, making them less applicable for traditional setups and limiting their clinical use.
Innovation Solution
A system utilizing a 3D motion sensor, noise cleaning module, and processor to track ankle coordinates and calculate gait parameters using eigenvector-based curvature analysis, measuring static single limb stance duration for postural balance assessment, which can be deployed at home and is unobtrusive.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If expensive gait analysis systems like GAITRite or Vicon are used, then measurement precision is improved, but device cost and operational complexity increase
Solution Approach 1:
The patent uses a depth camera to capture optical copies of the patient's movement and processes these visual data to extract gait parameters, replacing the need for expensive physical measurement systems like GAITRite mats or Vicon motion capture systems while maintaining measurement capability
Solution Approach 2:
The patent replaces mechanical gait analysis systems (GAITRite electronic mat, Vicon motion capture) with a computer vision-based system using depth imaging and image processing algorithms to detect and analyze gait parameters
2Ease of operation
If accelerometer and gyroscope sensors are used, then device portability and cost are improved, but measurement reliability deteriorates due to noise and signal drift
Solution Approach 1:
The patent replaces inertial sensors (accelerometers and gyroscopes) that suffer from drift and noise with a vision-based system using depth cameras and image processing, eliminating the need for body-mounted sensors while maintaining portability
Solution Approach 2:
The patent introduces an intermediary processing layer that uses depth image data and image processing algorithms to indirectly measure gait parameters, avoiding direct use of unreliable sensor data from accelerometers and gyroscopes
3Measurement precision
If multiple sensors are attached to the body for monitoring, then measurement precision is improved, but patient comfort deteriorates
Solution Approach 1:
The patent captures visual copies of the patient's body movements through depth imaging, eliminating the need to attach physical sensors to the patient's body while still enabling accurate gait parameter extraction from the visual data
Solution Approach 2:
The patent extracts gait parameter information directly from depth image data and skeleton tracking, removing the need for physical sensor attachments to the patient's body
Data Source
Figure 1
Figure 2
Figure 3~3b
AI summary
A method and system is provided for finding and analyzing gait parameters and postural balance of a person using a Kinect system. The system is easy to use and can be installed at home as well as in clinic. The system includes a Kinect sensor, a software development kit (SDK) and a processor. The temporal skeleton information obtained from the Kinect sensor to evaluate gait parameters including stride length, stride time, stance time and swing time. Eigenvector based curvature detection is used to analyze the gait pattern with different speeds. In another embodiment, Eigenvector based curvature detection is employed to detect static single limb stance (SLS) duration along with gait variables for evaluating body balance.