3D Hand Motion Capture Using Color and Depth Marker Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing motion capture systems are unsuitable for providing an objective and accurate evaluation of motor skills, particularly for neurodegenerative diseases like Parkinson's disease, due to issues such as sensor interference, complexity, illumination sensitivity, and limited accuracy in tracking small articulated body parts like hands.
Innovation Solution
A motion capture system using a wearable device with colored markers and combined color and depth information from a video and range camera to track hand movements, ensuring accurate and real-time kinematic quantification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If non-optical motion capture systems with sensors are used, then motion data can be captured, but the sensors interfere with natural movements and alter test results
Solution Approach 1:
The patent replaces non-optical sensors (magnetic, inertial) that physically interfere with movement with an optical system using cameras and image processing. The wearable device uses colored markers detected by video cameras, eliminating mechanical/physical sensors that alter natural movement patterns while maintaining motion capture capability
Solution Approach 2:
The patent introduces colored markers as intermediaries between the body and the detection system. These markers serve as visual mediators that can be detected by cameras without requiring direct sensor contact with the body, thus avoiding interference with natural movements while enabling accurate motion tracking
2Measurement precision
If marker-based optical systems are used, then motion tracking is enabled, but the systems are complex and require specialized operators
Solution Approach 1:
The patent uses colored markers with distinct color signatures that can be easily differentiated by video cameras. The color-based identification simplifies the tracking process compared to traditional marker systems, enabling automatic detection and reducing the need for specialized operators while maintaining accurate motion tracking
Solution Approach 2:
The system enables autonomous operation where the wearable device with colored markers automatically captures and transmits motion data without requiring specialized operators for positioning or data collection. The color-based detection allows the system to self-calibrate and track movements independently
3Ease of operation
If color-based hand isolation systems are used, then hand tracking is simplified, but the systems are sensitive to illumination changes
Solution Approach 1:
The patent uses multiple distinct color parameters for different markers instead of relying on a single color threshold. This multi-color approach creates broader detection ranges that are less sensitive to illumination variations, as the system can distinguish markers based on their unique color signatures rather than absolute color values that change with lighting
4Ease of manufacture
If standard video cameras are used for motion capture, then the system is cost-effective, but the accuracy for tracking small articulated body parts is limited
Solution Approach 1:
The patent places multiple colored markers at specific locations on the wearable device (different colors on different body parts). This local differentiation allows standard video cameras to accurately track small articulated body parts by detecting the distinct color signatures at each location, improving precision without requiring expensive specialized cameras
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 and accurate tracking of hand movements for neurodegenerative disease assessment, allowing autonomous user operation and low-cost implementation.
Implementation Method 1
range cameras, i.e. cameras capable of detecting the depth of each point of a framed scene, namely its distance from a predefined point of the scene. In order to provide depth information, range cameras exploit different principles, e.g. stereo triangulation, structured light, time-of-flight, interferometry, etc.
Implementation Method 2
a video camera suitable for acquiring a sequence of color frames of a scene comprising the wearable device, the at least two markers being visible in the sequence of color frames
Implementation Method 3
Basically, they reconstruct the movements of the markers in the three-dimensional space using triangulation techniques
Data Source
Figure 1~3
Figure 2a~2b
Figure 4
AI summary
It is disclosed a motion capture system. The system comprises a wearable device (e.g. a glove) suitable for being worn by a user and comprising one or more markers having respective colors. A video camera acquires a sequence of color frames of the user moving while wearing the glove, while a range camera acquires corresponding depth frames of the same scene. A processing unit processes both color frames and depth frames for reconstructing the 3D positions of the markers. In particular, the depth information provided by the depth frames are used for isolating a validity area within the color frames, and the markers are searched based on their colors, exclusively within the validity area of the color frames. The movements of the user are then captured as a sequence of positions of the markers. Combined use of color information and depth information provide a very reliable and accurate motion capture.