HMD Facial Tracking via Integrated Sensors

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional virtual reality systems provide limited graphical representations of users, lacking immersive facial expressions due to the need for dedicated peripherals and markers, which are unsuitable for portable, lightweight, and high-performance headsets.

Innovation Solution

A head-mounted display with integrated facial sensors and a controller that uses machine learning to capture and process facial expressions, projecting a realistic facial animation model onto the virtual environment without the need for external markers or peripherals.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional facial tracking systems use dedicated peripherals and markers, then facial expression tracking accuracy is improved, but device complexity and weight increase

Engineering Contradiction:
Improvefacial expression tracking accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent combines facial tracking sensors directly into the HMD device itself, merging the tracking function with the display device. This eliminates the need for separate dedicated peripheral devices and markers, reducing overall system complexity while maintaining tracking capability through integrated sensors that capture facial expressions directly.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent extracts the facial tracking functionality from separate peripheral devices and integrates it into the HMD. By taking out the tracking sensors and embedding them within the headset structure, the system eliminates external markers and dedicated tracking peripherals, simplifying the overall system architecture.

Inventive Principle:
Principle #2Taking out (Extraction)

2Measurement precision

If conventional facial tracking systems use dedicated peripherals and markers, then facial expression tracking accuracy is improved, but portability and comfort deteriorate

Engineering Contradiction:
Improvefacial expression tracking accuracyVSAvoidheadset weight
Core Design Contradiction:
Measurement precisionVSWeight of moving object

Solution Approach 1:

By merging facial tracking sensors into the HMD structure, the patent eliminates the need for separate peripheral devices and external markers. This integration reduces the total weight that would otherwise be required for dedicated tracking equipment, improving portability and user comfort while maintaining tracking accuracy.

Inventive Principle:
Principle #5Merging (Combining)

3Measurement precision

If conventional facial tracking systems use markers and dedicated peripherals, then facial expression tracking is achieved, but user immersion in virtual environment deteriorates

Engineering Contradiction:
Improvefacial expression tracking accuracyVSAvoiduser immersion
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The patent extracts and eliminates the need for external markers and dedicated peripheral devices by integrating sensors directly into the HMD. This removal of extraneous tracking components allows users to interact naturally with the virtual environment without being separated by physical markers or additional equipment, thereby enhancing immersion.

Inventive Principle:
Principle #2Taking out (Extraction)

4Device complexity

If limited facial expressions are used in avatars, then device complexity is reduced, but user experience immersion deteriorates

Engineering Contradiction:
Improvesystem complexityVSAvoidfacial expression variety
Core Design Contradiction:
Device complexityVSAdaptability or versatility

Solution Approach 1:

The patent enables the system to automatically capture and process a full range of facial expressions through integrated sensors and machine learning algorithms. The system serves itself by autonomously tracking multiple facial muscle movements and translating them into corresponding avatar expressions, eliminating the need for pre-programmed limited expressions while maintaining system efficiency.

Inventive Principle:
Principle #25Self-service

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 a more immersive user experience by accurately reflecting facial expressions, enhancing the realism of graphical representations within virtual reality environments without the limitations of traditional tracking systems.

Implementation Method 1

a facial sensor is a camera or other image capture device positioned to capture images of portions of the user's face

Methodology Applied
Scientific EffectReflection: Reflection

Implementation Method 2

the facial sensor also includes an illumination device configured to illuminate the portions of the user's face captured by the facial sensor

Methodology Applied
Scientific EffectLight emission: Light

Data Source

PatentUS10636192B1Generating a graphical representation of a face of a user wearing a head mounted display
Publication Date: 2020.04.28 META PLATFORMS TECHNOLOGIES LLC
  • US10636192B1 patent drawing
  • US10636192B1 patent drawing
  • US10636192B1 patent drawing

AI summary

A virtual reality (VR) or augmented reality (AR) head mounted display (HMD) includes various facial sensors, such as cameras, that capture images of portions of the user's face outside of the HMD. For example, multiple facial sensors capture images of a portion of the user's face below the HMD. Through image analysis, points of the portion of the user's face are identified from the images and their movement is tracked. The identified points are mapped to a three dimensional model of a face. Additionally, a parametric representation of the user's face is determined for each captured image, resulting in various representations indicating the user's facial expressions. From the parametric representations and transforms mapping the captured images to three dimensions, a rendering model is used and applied to the three dimensional model of the face to render the user's facial expressions.