Two-Stage Hand Gesture Input for Intentional GUI Activation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing virtual and augmented reality systems face challenges in accurately distinguishing between hand gestures, leading to unintentional activation of graphical user interface elements, which can disrupt user interactions.

Innovation Solution

A two-stage hand gesture input method is introduced, where a first-stage gesture is recognized, followed by an affordance cueing a second-stage gesture, to ensure intentional activation of GUI elements, reducing false positives.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If single-stage hand gesture recognition is used, then the interface response speed is fast, but the accuracy of user intent recognition deteriorates leading to unintentional activations

Engineering Contradiction:
Improveuser intent recognition accuracyVSAvoidgesture input structure
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The gesture recognition process is divided into two distinct stages: a first-stage gesture (e.g., hand swipe) followed by a second-stage gesture (e.g., hand click). This segmentation allows the system to break down a single complex recognition task into multiple simpler, more reliable detection steps, thereby improving user intent recognition accuracy without requiring overly complex single-stage gesture structures.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The first-stage gesture serves as a preliminary action that prepares the system for the second-stage gesture. By requiring the user to perform the first-stage gesture first (e.g., swiping to activate a virtual keyboard), the system preliminarily establishes the context and reduces the likelihood of unintentional activations before the final action (hand click) is executed.

Inventive Principle:
Principle #10Preliminary action

2Reliability

If two-stage hand gesture input is implemented, then the user intent discernment is improved, but the interaction time increases

Engineering Contradiction:
Improveuser intent discernmentVSAvoidgesture interaction time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The two-stage gesture system operates as a periodic action sequence where the first-stage gesture (hand swipe) and second-stage gesture (hand click) are performed in rapid succession. This periodic structure allows the system to maintain high reliability in user intent discernment while minimizing the total interaction time through efficient temporal sequencing of the two stages.

Inventive Principle:
Principle #19Periodic action

Solution Approach 2:

The system allows the user to skip or rush through the two stages by performing them in quick succession. The first-stage gesture can be followed immediately by the second-stage gesture without significant delay, enabling experienced users to complete the two-stage input process rapidly while still maintaining the reliability benefits of intent discernment.

Inventive Principle:
Principle #21Skipping (Rushing through)

3Difficulty of detecting and measuring

If hand tracking data is used for gesture recognition, then the gesture detection capability is enabled, but the false positive rate increases leading to unintentional activations

Engineering Contradiction:
Improvegesture detection capabilityVSAvoidfalse positive rate
Core Design Contradiction:
Difficulty of detecting and measuringVSReliability

Solution Approach 1:

The first-stage gesture acts as an intermediary step between the hand tracking data detection and the final gesture activation. By introducing this intermediate recognition stage (e.g., detecting a hand swipe before allowing a hand click to activate a GUI element), the system reduces false positives because the intermediary first-stage gesture must be successfully detected and recognized before the second stage can proceed, thereby filtering out spurious detections.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP3908908B1Augmented two-stage hand gesture input
Publication Date: 2026.01.28 MICROSOFT TECHNOLOGY LICENSING LLC
  • EP3908908B1 patent drawingFigure 1
  • EP3908908B1 patent drawingFigure 2A
  • EP3908908B1 patent drawingFigure 2B

AI summary

A method for augmenting a two-stage hand gesture input comprises receiving hand tracking data for a hand of a user. A gesture recognition machine recognizes that the user has performed a first-stage gesture based on one or more parameters derived from the received hand tracking data satisfying first-stage gesture criteria. An affordance cueing a second-stage gesture is provided to the user responsive to recognizing the first-stage gesture. The gesture recognition machine recognizes that the user has performed the second-stage gesture based on one or more parameters derived from the received hand tracking data satisfying second-stage gesture criteria. A graphical user interface element is displayed responsive to recognizing the second-stage gesture.