Wearable Heads-Up Display Item Tracking via Sensor Fusion

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Wearable heads-up displays (WHUDs) face challenges in efficiently detecting and locating items of interest in an environment, particularly in unknown settings, due to limitations in processing-intensive visual data and the need for accurate attribute recognition and tracking.

Innovation Solution

WHUDs employ a combination of sensor inputs, computer vision, and machine learning techniques to detect and track items of interest by obtaining attribute data, comparing it with environmental data, and using knowledge graphs to store and update location information, enabling efficient detection and navigation to the item's last known location.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Difficulty of detecting and measuring

If visual data processing is used to detect and locate items of interest, then detection capability is improved, but processing intensity and computational load increase

Engineering Contradiction:
Improveitem detection capabilityVSAvoidprocessing intensity
Core Design Contradiction:
Difficulty of detecting and measuringVSPower

Solution Approach 1:

The patent segments the detection process into multiple stages: initial sensor scanning, attribute extraction, candidate identification, and verification. By dividing the complex visual processing into smaller tasks executed at different times and with different computational requirements, the system achieves thorough item detection while managing processing intensity through temporal and functional segmentation of the detection workflow.

Inventive Principle:
Principle #1Segmentation

2Measurement precision

If comprehensive sensor inputs and machine learning techniques are employed, then attribute recognition accuracy is improved, but device complexity increases

Engineering Contradiction:
Improveattribute recognition accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent implements a multi-functional sensor system where a single integrated platform performs diverse functions including visual detection, audio recognition, inertial measurement, and environmental sensing. The machine learning framework serves multiple purposes: item identification, attribute recognition, location tracking, and navigation. This universal approach achieves high attribute recognition accuracy while managing device complexity through consolidated multi-functional architecture rather than separate specialized systems.

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

3Measurement precision

If continuous tracking and location updates are performed, then item location accuracy is improved, but energy consumption increases

Engineering Contradiction:
Improvelocation accuracyVSAvoidenergy consumption
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent implements periodic tracking updates rather than continuous monitoring. The system performs location updates at intervals determined by item mobility, user movement, and detection confidence levels. When an item is stationary or its location is confidently known, tracking frequency is reduced or suspended. This periodic approach maintains location accuracy for moving items while significantly reducing energy consumption during periods of stability.

Inventive Principle:
Principle #19Periodic action

Solution Approach 2:

The tracking system dynamically adjusts its behavior based on real-time conditions. Detection frequency and update rates are modulated according to item motion detection, user interaction patterns, and environmental context. The system transitions between active tracking, periodic updates, and dormant states, optimizing the balance between location accuracy and energy consumption through dynamic adaptation to changing operational requirements.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentUS11536970B1Tracking of item of interest using wearable heads up display
Publication Date: 2022.12.27 GOOGLE LLC
  • US11536970B1 patent drawing
  • US11536970B1 patent drawing
  • US11536970B1 patent drawing

AI summary

A wearable heads-up display (WHUD) obtains attribute data corresponding to an attribute of an item of interest and obtains environmental data of an environment surrounding the WHUD via one or more sensors of the WHUD. The WHUD compares the attribute data with the environmental data to detect the item of interest. In response to the detection, the WHUD obtains location data indicative of a location of the item of interest, stores the location data in association with a context of detection of the item of interest. In response to a trigger, such as a query by a user regarding the item of interest, the WHUD provides a location indication based on the location data, the location indication including, for example, a display of a description of the location of the item of interest, a display of the item of interest at the location, and the like.