Database-Driven Motion Capture Using Accelerometer Pattern Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current motion capture systems are either too expensive, cumbersome, or insufficient in tracking detailed human body motions due to limitations in accelerometer-based systems and the need for accurate positional calculations, which are prone to drift errors.
Innovation Solution
A database-driven motion capture system using a network of lightweight accelerometers integrated into wearable clothing, communicating with a microcontroller and computing device, which processes motion data through wavelet compression and matching against a pre-recorded motion database to recreate movements accurately without direct position calculation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the number of accelerometers is increased to provide detailed motion readings from several body points, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The system divides the body into multiple segments (head, torso, arms, legs) and places accelerometers at key segment locations. This segmentation allows detailed full-body motion capture using a manageable number of sensors rather than requiring dense coverage of every body point.
Solution Approach 2:
The system transitions from direct position measurement to acceleration measurement, then uses database matching in a different dimensional space (acceleration patterns) to identify motions. This dimensional change avoids the drift problem of integration while capturing detailed motion information.
2Measurement precision
If double integration is applied to acceleration readings to calculate position, then positional information is obtained, but measurement precision deteriorates due to continual drift
Solution Approach 1:
Instead of integrating acceleration to get position (which causes drift), the system inverts the approach by directly measuring acceleration patterns and matching them against a database of known motion patterns. This avoids integration entirely while still providing accurate position information through pattern recognition.
Solution Approach 2:
The system performs preliminary action by pre-recording and storing accurate motion capture data from multiple subjects in a database before actual use. During operation, the system simply matches incoming acceleration patterns against this pre-prepared database, avoiding the need for real-time integration and drift correction.
3Measurement precision
If camera based capture systems are used to provide accurate positional readings, then measurement precision is improved, but ease of operation and cost worsen due to complex setup and high expense
Solution Approach 1:
The system replaces the complex mechanical and optical infrastructure of camera-based systems (multiple cameras, infrared bars, reflective markers, synchronized triggering mechanisms) with simple accelerometer sensors that naturally record motion without requiring external instrumentation or complex environmental setup.
Solution Approach 2:
The accelerometer-based system is self-service in that each sensor independently records its own motion data without requiring external cameras to observe it. The sensors autonomously capture acceleration patterns that are then matched against the database, eliminating the need for operators to configure and synchronize multiple camera systems.
4Device complexity
If simple accelerometer systems like Wii Remote are used, then device complexity is reduced, but measurement precision deteriorates due to single point measurement
Solution Approach 1:
The system merges data from multiple accelerometer sensors placed at different body locations into a unified motion representation. By combining the acceleration patterns from head, torso, and limb sensors, the system achieves detailed full-body motion capture while maintaining the simplicity of accelerometer-based measurement.
Solution Approach 2:
The system uses accelerometers universally across multiple body segments rather than employing different sensor types for different locations. This multi-functional approach allows a single sensor type to capture diverse motion information throughout the body, simplifying the system while improving measurement detail.
Data Source
AI summary
There is provided a system and method for database driven action capture. By utilizing low cost, lightweight MEMS devices such as accelerometers, a user friendly, wearable, and cost effective system for motion capture is provided, which relies on a motion database of previously recorded motions to reconstruct the actions of a user. By relying on the motion database, calculation errors such as integration drift are avoided and the need for complex and expensive positional compensation hardware is avoided. The accelerometers may be implemented in an E-textile embodiment using inexpensive off-the-shelf components. In some embodiments, compression techniques may be used to accelerate linear best match searching against the motion database. Adjacent selected motions may also be blended together for improved reconstruction results and visual rendering quality. Various perceivable effects may be triggered in response to the reconstructed motion, such as animating a 3D avatar, playing sounds, or operating a motor.