Near-Plane Gesture Recognition Using IR Difference Imaging

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Head-mounted display (HMD) devices lack a low-cost and energy-efficient method for gesture recognition in various lighting environments, as existing gesture recognition techniques rely on depth cameras that are expensive and power-intensive, and voice commands may not be appropriate in all situations.

Innovation Solution

The use of an IR light source to illuminate a specific range within a near-field environment, capturing images with and without illumination, and generating a difference image to eliminate background noise, allowing for hand and finger gesture recognition using integrated color and IR image sensors.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If depth cameras are used for gesture recognition, then gesture recognition capability is improved, but device cost and energy consumption increase

Engineering Contradiction:
Improvegesture recognition capabilityVSAvoidenergy consumption
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The patent replaces the mechanical/optical depth camera system with an infrared imaging system that uses active infrared illumination and standard color camera sensors. This substitution eliminates the need for expensive depth camera hardware while achieving gesture recognition through image processing of reflected infrared light patterns.

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

Solution Approach 2:

The patent creates a virtual depth representation by processing reflected infrared light patterns from objects in the scene. Instead of directly capturing depth information with a depth camera, the system captures infrared reflections and computationally derives depth and gesture information from these reflected patterns, effectively copying depth data from optical reflections.

Inventive Principle:
Principle #26Copying

2Reliability

If depth cameras are used for gesture recognition, then gesture recognition capability is improved, but device cost increases

Engineering Contradiction:
Improvegesture recognition capabilityVSAvoiddevice cost
Core Design Contradiction:
ReliabilityVSEase of manufacture

Solution Approach 1:

The patent replaces the mechanical/optical depth camera system with an infrared imaging system that uses active infrared illumination and standard color camera sensors. This substitution eliminates the need for expensive depth camera hardware while achieving gesture recognition through image processing of reflected infrared light patterns.

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

Solution Approach 2:

The patent makes the infrared illumination system serve multiple functions: it provides active illumination for the camera, creates depth information through reflected light patterns, and enables gesture recognition. This multi-functionality reduces the need for separate dedicated components, lowering overall system cost.

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

3Measurement precision

If active infrared illumination is used to illuminate a specific range, then gesture recognition accuracy is improved, but light intensity decay limits the illumination range

Engineering Contradiction:
Improvegesture recognition accuracyVSAvoidillumination range
Core Design Contradiction:
Measurement precisionVSLength of stationary object

Solution Approach 1:

The patent applies local quality by concentrating infrared illumination on the specific near-field region where gestures occur. The active infrared illumination is directed to illuminate only the immediate surroundings of the device, creating a localized illumination zone that provides sufficient light intensity for accurate gesture recognition without requiring wide-area illumination.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent uses partial action by providing just enough infrared illumination intensity for the near-field gesture recognition requirement. Rather than illuminating the entire field of view, the system applies illumination selectively to the necessary near-field region, optimizing the balance between illumination intensity and energy consumption.

Inventive Principle:
Principle #16Partial or excessive action

4Measurement precision

If difference imaging is used to eliminate background noise, then gesture detection accuracy is improved, but image processing complexity increases

Engineering Contradiction:
Improvegesture detection accuracyVSAvoidimage processing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies preliminary action by capturing an infrared image before the gesture occurs and using this pre-captured image as a reference for subtraction. This preliminary infrared capture allows the system to establish a baseline of the scene without gestures, enabling subsequent difference imaging to isolate gesture-related changes from background variations.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent extracts gesture information by subtracting the pre-captured infrared image from the current infrared image. This difference imaging process extracts only the changes caused by gestures, separating gesture signals from background noise and static scene elements, thereby isolating the relevant gesture data for recognition.

Inventive Principle:
Principle #2Taking out (Extraction)

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

Enables effective and energy-efficient hand and finger gesture recognition in HMD devices, functioning across a wide range of lighting conditions without the need for expensive depth cameras, thus providing a robust natural user interface.

Implementation Method 1

emitting IR light from a mobile device into an environment

Methodology Applied
Scientific EffectInfrared radiation emission: Infrared Radiation

Implementation Method 2

capturing images with and without illumination... detecting reflections of the projected IR light

Methodology Applied
Scientific EffectPhotoelectric effect: Photoelectric Effect

Data Source

PatentEP2984541B1Near-plane segmentation using pulsed light source
Publication Date: 2020.03.04 MICROSOFT TECHNOLOGY LICENSING LLC
  • EP2984541B1 patent drawingFigure 1
  • EP2984541B1 patent drawingFigure 2A
  • EP2984541B1 patent drawingFigure 2B

AI summary

Methods for recognizing gestures within a near-field environment are described. In some embodiments, a mobile device, such as a head-mounted display device (HMD), may capture a first image of an environment while illuminating the environment using an IR light source with a first range (e.g., due to the exponential decay of light intensity) and capture a second image of the environment without illumination. The mobile device may generate a difference image based on the first image and the second image in order to eliminate background noise due to other sources of IR light within the environment (e.g., due to sunlight or artificial light sources). In some cases, object and gesture recognition techniques may be applied to the difference image in order to detect the performance of hand and/or finger gestures by an end user of the mobile device within a near-field environment of the mobile device.