Markerless 3D Pose Detection for Interactive Entertainment

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Traditional motion capture systems require intensive calibration and setup processes due to the need for markers on the person's body, limiting their application and use in seamless, immersive entertainment experiences.

Innovation Solution

A system that uses an enhancer to illuminate an area with invisible light, allowing image detectors to capture and process skeletal features without markers, and a self-calibrating method to adjust camera characteristics for accurate pose detection in three dimensions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional motion capture systems use markers placed on the person's body, then pose detection accuracy is improved, but calibration complexity and setup time increase

Engineering Contradiction:
Improvepose detection accuracyVSAvoidcalibration complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent removes the markers from the system entirely, extracting the unnecessary component that caused calibration complexity. The system achieves pose detection without markers by using multiple cameras to capture images from different angles and processing these images to identify skeletal features directly from the person's body geometry.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent replaces the mechanical marker-based detection system with an optical imaging and computational processing system. Instead of detecting physical markers on the body, the system uses multiple cameras to capture visual data and employs image processing algorithms to identify skeletal features and calculate pose information from the captured images.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If markers are accurately positioned on the person's body, then motion capture precision is improved, but setup time and operational complexity increase

Engineering Contradiction:
Improvemotion capture precisionVSAvoidsetup time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs self-calibration by automatically determining camera positions and orientations through image processing of captured frames. The calibration process is embedded within the normal operation, using the captured images themselves to establish the coordinate systems and transformation matrices needed for accurate pose detection, eliminating the need for separate calibration procedures.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system establishes camera calibration parameters and coordinate transformations in advance through automated processing of initial captured images. By pre-computing the necessary transformation matrices and calibration data from the captured image sequences, the system prepares all required parameters before actual pose detection begins, enabling immediate operation without time-consuming setup.

Inventive Principle:
Principle #10Preliminary action

3Measurement precision

If traditional systems require intensive calibration processes, then measurement accuracy is maintained, but ease of operation deteriorates

Engineering Contradiction:
Improvemeasurement accuracyVSAvoidease of operation
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The patent replaces manual calibration procedures with automated computational methods. The system uses image processing algorithms to automatically determine camera positions, orientations, and calibration parameters from captured images, eliminating the need for operators to perform complex manual calibration tasks while maintaining measurement accuracy.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The calibration process is performed automatically by the system itself without requiring operator intervention. The system captures images, processes them to identify feature points, calculates transformation matrices, and establishes coordinate systems autonomously, making the operation as easy as capturing images while maintaining high measurement precision.

Inventive Principle:
Principle #25Self-service

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 seamless, immersive interactive experiences by accurately detecting user poses in virtual environments without the need for physical markers, enhancing user interaction and reducing computational demands.

Implementation Method 1

illuminating, by an enhancer, an area with light having a wavelength invisible to humans

Methodology Applied
Scientific EffectInvisible light illumination: Light

Implementation Method 2

A plurality image detectors receive at least two images of a person in the area including a portion of the light emitted by the enhancer and reflected from the person

Methodology Applied
Scientific EffectLight reflection: Reflection

Data Source

PatentUS20250303272A1Interactive entertainment system
Publication Date: 2025.10.02 DISNEY ENTERPRISES INC
  • US20250303272A1 patent drawing
  • US20250303272A1 patent drawing
  • US20250303272A1 patent drawing

AI summary

The present disclosure describes a method for providing an interactive experience. The method includes illuminating, by an enhancer, an area with light having wavelength invisible to humans. A plurality of image detectors capture at least two images of a person in the area including a portion of the light reflected from the person. A processing element determines a first skeletal feature of the person based on the at least two images. The processing element determines a position characteristic of the first skeletal feature; constructs, from the first skeletal feature, a vector in three dimensions corresponding to the position characteristic; and outputs an interactive effect based on the position characteristic.