Motion Data Conversion for Detailed Peripheral Joint Capture
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing motion capture systems struggle to capture high-quality motion data for peripheral parts like finger joints due to limitations in recognition accuracy and the need for high-cost setups, leading to unrealistic representations in free viewpoint images.
Innovation Solution
An information processing device employs a motion data conversion unit that uses a motion matching process or an artificial intelligence model to infer and convert low-quality motion data into high-quality data with increased part detail, utilizing captured motion data, attribute information, and positional relationships with other objects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a high-precision motion capture system (e.g., OptiTrack) is used to capture peripheral parts like finger joints, then the quality of motion data for peripheral parts is improved, but the cost and complexity of the system increase significantly
Solution Approach 1:
The motion capture system is divided into two functional segments: a motion capture unit that captures overall body motion and a motion data conversion unit that processes and enhances the data. This segmentation allows the use of a simpler, lower-cost capture system while achieving high-quality peripheral part data through computational processing.
Solution Approach 2:
The motion data conversion unit acts as an intermediary between the low-cost motion capture system and the final high-quality motion data output. It receives basic motion data, applies AI models or motion matching processes, and generates enhanced motion data with detailed peripheral part information without requiring the capture system itself to be high-precision.
2Device complexity
If a low-cost motion capture system using cameras is used, then the system cost is reduced, but the recognition accuracy and quality of motion data for peripheral parts deteriorate
Solution Approach 1:
The patent replaces the mechanical/optical capture mechanism with a computational processing mechanism. Instead of relying on the physical capture system to resolve fine details of peripheral parts, the system uses AI models and motion matching algorithms to computationally generate this information from coarser input data.
Solution Approach 2:
The system changes the parameters of motion data processing by applying AI models and motion matching processes that transform basic motion parameters into detailed peripheral part motion parameters. This parameter transformation allows the system to output high-quality motion data with finger joint information even when the input data lacks such detail.
3Ease of operation
If markerless motion capture is used to reduce cost and complexity, then ease of operation is improved, but the recognition accuracy for peripheral parts deteriorates
Solution Approach 1:
The system performs preliminary action by capturing overall body motion with a simple markerless system, then subsequently processes this data through AI models and motion matching to derive peripheral part information. This two-stage approach maintains ease of operation while achieving high recognition accuracy for peripheral parts through computational enhancement.
Data Source
AI summary
An information processing device according to the present technology includes a motion data conversion unit that receives an input of captured motion data that is motion data acquired with a motion capture system for a movable object, and performs a motion data conversion process to obtain motion data having a larger number of pieces of part data than the captured motion data, through one of a motion matching process based on the captured motion data or an inference process that uses an artificial intelligence model and uses the captured motion data as input data.