Gesture Interface Tracking Parallax Error with Visual Feedback

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing systems face challenges in accurately recognizing pointing operations from a distance due to parallax error and technological limitations, making it difficult to interact with user interfaces from more than 3 meters away with precision and feedback.

Innovation Solution

A system and method utilizing a motion and depth sensor camera to track the user's hand position and provide real-time feedback, featuring modules for feature extraction, operator identification, gesture recognition, and virtual screen mapping to accurately identify the target on the screen, allowing multiple users to interact with a user interface from different distances.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If gesture-based user interface operation is performed from a distance greater than 3 meters, then user accessibility and interaction flexibility are improved, but pointing accuracy deteriorates due to parallax error and technological limitations

Engineering Contradiction:
Improveuser accessibilityVSAvoidpointing accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The system displays a visual indicator on the screen showing the detected pointing location and provides real-time feedback to the user. This feedback mechanism allows users to adjust their pointing gesture until the indicator aligns with the intended target, thereby maintaining high pointing accuracy even at distances greater than 3 meters while preserving ease of operation

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent replaces traditional mechanical pointing devices (mice, keyboards) with gesture-based recognition using computer vision and machine learning algorithms. This substitution enables users to interact with the interface from a distance using natural hand gestures, improving accessibility while the system compensates for parallax error through algorithmic correction and visual feedback

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

2Measurement precision

If the system provides real-time feedback and tracking of hand position, then pointing accuracy is improved, but device complexity increases

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

Solution Approach 1:

The system uses the user's own hand as the pointing instrument, eliminating the need for separate pointing devices. The computer vision system automatically tracks hand position and computes pointing location, with the visual indicator serving as self-generated feedback. This self-service approach improves pointing accuracy while avoiding the complexity of additional hardware components

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system integrates multiple functions into a single unified framework: gesture detection, hand tracking, pointing location computation, and visual feedback display all occur within the same system. This multi-functionality approach improves pointing accuracy through integrated real-time processing while avoiding the complexity that would arise from separate independent systems

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

Data Source

PatentEP3136203B1System and method of real-time interactive operation of user interface
Publication Date: 2020.06.17 KONICA MINOLTA SYSTEMS LABORATORY INC
  • EP3136203B1 patent drawingFigure 1
  • EP3136203B1 patent drawingFigure 2
  • EP3136203B1 patent drawingFigure 3

AI summary

A method, a system, and a computer program are disclosed for real-time interaction with a user interface recognizing a gesture. The method including capturing three-dimensional (3D) data on a subject; detecting a pointing action by the subject from the 3D data; computing an initial estimate of a target region from the pointing action, the initial estimate of the target region having a defined radius around a center point; and tracking the pointing action of the subject and performing a series of iterations wherein the defined radius of the target region changes based on the detected pointing action