Hybrid Motion Capture Posture Correction for Inertial Drift

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Inertial navigation systems suffer from increasing positional errors over time due to the integration of acceleration data, necessitating a method to enhance motion capture accuracy.

Innovation Solution

An information processing apparatus that combines inertial sensor data with image data from a camera to generate corrected skeleton data by performing correction processing based on optical and inertial posture information, improving accuracy by integrating both data types.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If inertial sensor data is used for motion capture, then portability and ease of operation are improved, but measurement precision deteriorates over time due to integration errors

Engineering Contradiction:
ImproveportabilityVSAvoidposition accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The patent combines inertial sensor data (acceleration, angular velocity) with optical camera data to create a hybrid motion capture system. The inertial data provides continuous portable tracking while the optical data periodically corrects drift errors, merging the advantages of both methods to maintain high accuracy over time.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The system uses optical camera feedback to detect and correct accumulated errors in inertial navigation. By comparing inertial-derived position with optically-measured position, the system generates correction signals that compensate for drift, maintaining long-term accuracy.

Inventive Principle:
Principle #23Feedback

2Ease of operation

If inertial navigation system is used to calculate position, then ease of operation is improved, but measurement precision worsens due to error accumulation over time

Engineering Contradiction:
Improveease of useVSAvoidposition accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The optical camera acts as an intermediary correction mechanism. It periodically measures actual position to detect inertial drift errors, which then feed back to correct the inertial navigation system, maintaining accuracy without compromising ease of operation.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Measurement precision

If optical motion capture method is used, then measurement precision is improved, but device complexity increases

Engineering Contradiction:
Improveposition accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

Instead of using a full optical motion capture system with multiple cameras for continuous tracking, the patent uses optical data partially - only for periodic correction of inertial drift. This reduces system complexity while maintaining measurement precision during critical periods.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS12632105B2Information processing apparatus, information processing method, and information processing program
Publication Date: 2026.05.19 SONY GROUP CORP
  • US12632105B2 patent drawing
  • US12632105B2 patent drawing
  • US12632105B2 patent drawing

AI summary

An information processing apparatus (100) according to an embodiment of the present disclosure includes: a first acquisition unit configured to acquire, from an inertial sensor attached to a moving body, inertial information associated with a movement of the moving body; a second acquisition unit configured to acquire first image information obtained by imaging the moving body from a first camera; and a calculation unit configured to calculate third posture information on the basis of first posture information of the moving body obtained on the basis of the inertial information acquired by the first acquisition unit and second posture information of the moving body obtained on the basis of the first image information acquired by the second acquisition unit.