Gesture Recognition via Sinusoidal Pattern Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for recognizing motion gestures lack accuracy and efficiency, particularly in distinguishing between intentional and unintentional movements, which affects the reliability of human-computer interfaces.

Innovation Solution

A system that tracks the position of a moving object over time along a defined shape within a motion history map, graphing its position as a proportion of a single dimension to identify waving, swiping, or oscillating gestures by recognizing patterns resembling sinusoids, and maps these gestures to control inputs, eliminating the need for physical buttons and reducing blurring effects on touch screens.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional motion gesture recognition methods are used, then the system can detect basic movements, but the accuracy in distinguishing intentional gestures from unintentional movements is insufficient

Engineering Contradiction:
Improvegesture recognition accuracyVSAvoidgesture detection reliability
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The patent segments the motion detection process into multiple components: motion history map generation, sinusoidal pattern extraction, parameter calculation (amplitude, frequency, phase), and threshold-based classification. This segmentation allows each component to be optimized independently, improving overall gesture recognition accuracy while maintaining reliability.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent transforms 2D motion data into a temporal dimension by analyzing motion history maps across multiple frames. By graphing position versus time and detecting sinusoidal patterns, the system adds a temporal dimension to gesture recognition, enabling distinction between intentional rhythmic gestures and unintentional movements.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Ease of operation

If physical buttons are used for user interaction, then the interface is simple to implement, but touch screen blurring occurs and physical interaction is required

Engineering Contradiction:
Improveinterface usabilityVSAvoidtouch screen blurring
Core Design Contradiction:
Ease of operationVSObject-affected harmful factors

Solution Approach 1:

The patent replaces mechanical touch input with optical motion detection. Instead of requiring physical contact with the touchscreen (which causes blurring), the system uses a camera to detect hand gestures in 3D space and interprets them as control commands, eliminating the blurring issue while maintaining ease of operation.

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

Solution Approach 2:

The patent creates a virtual copy of button functionality through gesture recognition. Instead of physical buttons, the system recognizes specific hand motion patterns (such as waving gestures) and maps them to equivalent control functions, providing the same user experience without the harmful effects of physical touch on the screen.

Inventive Principle:
Principle #26Copying

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

Enhances the accuracy and efficacy of human-computer interfaces by allowing users to invoke functions through defined gestures, improving functionality selection and eliminating the need for physical interaction, thus reducing errors and blurring issues.

Implementation Method 1

Cameras have been used to capture images of objects

Methodology Applied
Scientific EffectPhotoelectric effect: Photoelectric Effect

Implementation Method 2

optical flow has been used to detect motion of an object by analyzing multiple images of the object taken at different times

Methodology Applied
Scientific EffectOptical flow:

Data Source

PatentEP2327005B1Enhanced detection of waving gesture
Publication Date: 2017.08.23 QUALCOMM INC
  • EP2327005B1 patent drawingFigure 1A
  • EP2327005B1 patent drawingFigure 1B
  • EP2327005B1 patent drawingFigure 2

AI summary

The enhanced detection of a waving engagement gesture, in which a shape is defined within motion data, the motion data is sampled at points that are aligned with the defined shape, and, based on the sampled motion data, positions of a moving object along the defined shape are determined over time. It is determined whether the moving object is performing a gesture based on a pattern exhibited by the determined positions, and an application is controlled if determining that the moving object is performing the gesture.