Camera-Based Gesture Recognition on Arbitrary Surfaces

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional gesture recognition technologies are limited by the need for specialized sensors integrated into touch-sensitive surfaces, restricting touch interactions to specific surfaces and failing to leverage arbitrary surfaces in the physical environment.

Innovation Solution

A system that uses a camera to capture images and generate a static geometry model of the environment, allowing for gesture recognition based on the interaction of dynamic objects with static objects, and combining camera orientation and image inputs to initiate device operations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If specialized sensors are integrated into touch-sensitive surfaces for gesture recognition, then gesture recognition accuracy is improved, but device complexity and manufacturing cost increase

Engineering Contradiction:
Improvegesture recognition accuracyVSAvoidsensor integration complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces specialized mechanical touch sensors with an optical system using a camera and image processing algorithms. The gesture recognition system captures images of the environment and analyzes interactions between dynamic objects (hands) and static objects (surfaces) through computer vision, eliminating the need for integrated touch-sensitive sensors while maintaining gesture recognition capability

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

Solution Approach 2:

The patent introduces an image processing system as an intermediary between the physical gesture and the computing device response. The camera captures visual information, and software algorithms process this data to recognize gestures, serving as a mediator that translates physical actions into device commands without requiring direct sensor integration into surfaces

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If touch interactions are restricted to specific surfaces with integrated sensors, then gesture recognition reliability is improved, but adaptability to arbitrary surfaces deteriorates

Engineering Contradiction:
Improvegesture recognition reliabilityVSAvoidsurface adaptability
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent creates a universal gesture recognition system that works across arbitrary surfaces without requiring surface-specific sensors. The camera-based system can detect gestures on any surface within its field of view by analyzing image data, making the system adaptable to diverse environments and surfaces while maintaining reliable gesture recognition through robust image processing algorithms

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

3Ease of operation

If physical contact sensing is used for gesture recognition, then ease of operation is improved, but the system becomes limited to detected physical interactions only

Engineering Contradiction:
Improvegesture interaction easeVSAvoidinteraction type versatility
Core Design Contradiction:
Ease of operationVSAdaptability or versatility

Solution Approach 1:

The patent transitions from static contact detection to dynamic gesture recognition by analyzing motion and interaction over time. The system captures a series of images and detects changes in the environment, allowing it to recognize gestures based on movement patterns and interactions between dynamic objects (hands) and static objects (surfaces), thereby expanding interaction versatility while maintaining ease of use

Inventive Principle:
Principle #15Dynamics

Data Source

PatentUS10761612B2Gesture recognition techniques
Publication Date: 2020.09.01 MICROSOFT TECHNOLOGY LICENSING LLC
  • US10761612B2 patent drawing
  • US10761612B2 patent drawing
  • US10761612B2 patent drawing

AI summary

In one or more implementations, a static geometry model is generated, from one or more images of a physical environment captured using a camera, using one or more static objects to model corresponding one or more objects in the physical environment. Interaction of a dynamic object with at least one of the static objects is identified by analyzing at least one image and a gesture is recognized from the identified interaction of the dynamic object with the at least one of the static objects to initiate an operation of the computing device.