Motion Capture Using Depth Imaging and Parallel Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current motion capture technologies face challenges in capturing human performances and dynamic geometry of real-world actors to create authentic virtual models, especially under uncontrolled recording conditions, due to the complexity of human anatomy and the need for multi-view camera systems.
Innovation Solution
A system utilizing depth-based image data and parallel processing hardware to render and assess multiple orientations or poses of an object, selecting the most appropriate one based on depth values and skeletal constraints, allowing for efficient motion capture even under relaxed imaging conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multi-view camera systems are used to capture full skeletal motion, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent uses depth images as a simplified copy or representation of the scene, capturing essential depth information without requiring multiple view cameras. This depth map serves as a surrogate for complex multi-view data, enabling motion capture with a single sensor while maintaining adequate measurement precision for skeletal motion.
Solution Approach 2:
The invention extracts only the necessary depth information from the scene using a single depth imaging sensor, rather than capturing complete multi-view data. By taking out only the essential depth components needed for motion capture, the system achieves full skeletal motion tracking without the complexity of multiple cameras.
2Measurement precision
If specially controlled recording conditions are implemented, then measurement precision is improved, but ease of operation deteriorates
Solution Approach 1:
The depth imaging sensor automatically captures depth information without requiring manual setup or control of recording conditions. The system self-adjusts to capture motion data in varied environments, eliminating the need for specially controlled recording conditions while maintaining measurement precision through the inherent capabilities of depth sensing.
Solution Approach 2:
The patent changes the operating parameters from controlled recording conditions to uncontrolled real-world environments by using depth imaging technology. This parameter change allows the system to operate under relaxed conditions while maintaining measurement precision through the robustness of depth-based motion capture algorithms.
3Productivity
If depth-based image data with parallel processing is used, then productivity is improved, but manufacturing precision requirements increase
Solution Approach 1:
The patent replaces traditional mechanical multi-camera systems with a depth imaging sensor combined with parallel processing. This substitution uses computational methods (software algorithms running on parallel processing hardware) to achieve real-time motion capture, improving productivity while the depth sensor's inherent precision capabilities meet the manufacturing precision requirements.
Data Source
AI summary
Systems, devices, methods and arrangements are implemented in a variety of embodiments to facilitate motion capture of objects. Consistent with one such system, three-dimensional representations are determined for at least one object. Depth-based image data is used in the system, which includes a processing circuit configured and arranged to render a plurality of orientations for at least one object. Orientations from the plurality of orientations are assessed against the depth-based image data. An orientation is selected from the plurality of orientations as a function of the assessment of orientations from the plurality of orientations.