Camera-Based Pose Input for Controller-Free Command Recognition

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing technologies require users to position their fingers over a controller, limiting the user's movement and reducing usability during input operations.

Innovation Solution

A computer system that uses a camera unit to recognize poses and gestures made by a user in real space, allowing input operations without the need for a physical controller, by processing information from sensors to execute commands linked to these gestures.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If a physical controller is used for input operations, then gesture recognition can be performed, but the user's movement is limited and usability is reduced

Engineering Contradiction:
ImproveusabilityVSAvoiduser movement freedom
Core Design Contradiction:
Ease of operationVSAdaptability or versatility

Solution Approach 1:

The patent extracts the input function from the physical controller and implements it through camera-based pose recognition. The system captures images of the user's body movements and processes them to generate input signals, eliminating the need for users to interact with a physical controller and thereby freeing their movement.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent replaces the mechanical controller system with an optical recognition system. Instead of requiring physical contact with a controller, the system uses camera imaging and computational algorithms to detect and interpret user poses, substituting mechanical interaction with optical-field-based recognition.

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

2Reliability

If the controller position is fixed on a desk, then gesture recognition is enabled, but the user's movement freedom is restricted

Engineering Contradiction:
Improvegesture recognition capabilityVSAvoiduser position flexibility
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent creates a universal input system that works across multiple positions and scenarios. The camera-based pose recognition can detect user gestures from various angles and positions in the room, making the system adaptable to different user locations and movements rather than being confined to a single controller position.

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Adaptability or versatility

If full body pose recognition is implemented, then input versatility is improved, but system complexity increases

Engineering Contradiction:
Improveinput operation varietyVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent segments the pose recognition process into distinct functional modules: image acquisition by the camera unit, pose detection through coordinate extraction, gesture recognition through pattern matching, and command execution. This modular segmentation manages system complexity by organizing the comprehensive pose recognition functionality into manageable, independent components.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS20260029853A1Computer system, method, and program
Publication Date: 2026.01.29 SONY INTERACTIVE ENTERTAINMENT LLC
  • US20260029853A1 patent drawing
  • US20260029853A1 patent drawing
  • US20260029853A1 patent drawing

AI summary

Provided is a computer system for control based on input from a user, the computer system including at least one memory for storing a program code and at least one processor for executing an operation in accordance with in which the operation includes acquiring information associated with an imaged field including the user, recognizing a pose formed by a body of the user in a real space and relevant information associated with a feature of the pose, on the basis of the information, and executing a command linked with a combination of the pose and the relevant information beforehand.