Image Processing Apparatus for Dynamic Gesture Recognition

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing gesture recognition technologies face challenges in convenience and recognition performance, as they require users to wear or hold specific objects, and individual variations in body shape and color affect recognition accuracy.

Innovation Solution

An image processing apparatus and method that allows gesture recognition using arbitrary target objects, enhancing user convenience and recognition performance by extracting and tracking objects based on predefined movements, without the need for specific tools or objects, and accommodating user-specific body parts as targets.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a target object registered in advance is used for gesture recognition, then recognition performance is enhanced, but user convenience deteriorates because the user must wear or hold the target object without fail

Engineering Contradiction:
Improverecognition performanceVSAvoiduser convenience
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The system dynamically switches between two gesture recognition modes: using a registered target object when available (high recognition performance) and using body parts when the target object is not present (high convenience). This dynamic adaptation resolves the contradiction by allowing the system to optimize for either performance or convenience based on real-time conditions.

Inventive Principle:
Principle #15Dynamics

2Ease of operation

If part of the body of the user is used for gesture recognition, then user convenience is improved, but recognition performance deteriorates due to individual variations in shape and color

Engineering Contradiction:
Improveuser convenienceVSAvoidrecognition performance
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The system dynamically selects the recognition mode based on presence of target object, switching between body-part-based recognition (convenient but less accurate) and target-object-based recognition (accurate but requires carrying object). This resolves the contradiction by allowing optimization for either convenience or performance depending on situational requirements.

Inventive Principle:
Principle #15Dynamics

3Measurement precision

If a specific tool or object is required for gesture recognition, then recognition accuracy is improved, but device complexity and user burden increase

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

Solution Approach 1:

The system is designed to perform multiple functions: it can recognize gestures using either a registered target object or body parts. This multi-functionality allows the system to maintain high recognition accuracy when a target object is available while also being capable of operation without any additional tools, thereby reducing the need for specialized equipment and simplifying the overall system requirements.

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

Data Source

PatentUS8644556B2Image processing apparatus and method and program
Publication Date: 2014.02.04 SONY GROUP CORP
  • US8644556B2 patent drawing
  • US8644556B2 patent drawing
  • US8644556B2 patent drawing

AI summary

An image processing apparatus includes an image input configured to receive image data, a target extraction device configured to extract an object from the image data as a target object based on recognizing a first movement by the object, and a gesture recognition device configured to issue a command based on recognizing a second movement by the target object.