Visual-Inertial Tracking Scale Level Selection for Motion Blur

Solution Overview

Problem

Visual tracking systems in augmented and virtual reality devices face degraded performance due to motion blur, which increases computational operations and power consumption, especially in head-worn devices with rapid camera movements.

Innovation Solution

A method is introduced to predict the optimal scale level for feature matching in visual-inertial tracking systems by estimating motion blur and scale changes, allowing for single matching attempts per image, thereby reducing processing time and power consumption.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If multiple scale levels are used for feature matching to handle motion blur, then tracking robustness is improved, but computational operations and power consumption increase

Engineering Contradiction:

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system performs preliminary estimation of motion blur levels and scale changes before feature matching. By predicting the optimal scale level in advance based on motion blur estimation and scale change detection, the system avoids unnecessary computational operations at multiple scale levels, thereby reducing power consumption while maintaining tracking robustness

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system dynamically adjusts the scale level parameter for feature matching based on estimated motion blur and scale change. Instead of using fixed multiple scale levels, the system changes the scale parameter adaptively, selecting the optimal single scale level that balances tracking accuracy with computational efficiency, thus reducing power consumption

Inventive Principle:

Principle #35Parameter changes

2Reliability

If multiple scale levels are used for feature matching to handle motion blur, then tracking robustness is improved, but processing time increases

Engineering Contradiction:

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary estimation of motion blur levels and scale changes before feature matching. By predicting the optimal scale level in advance based on motion blur estimation and scale change detection, the system avoids unnecessary computational operations at multiple scale levels, thereby reducing processing time while maintaining tracking robustness

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system extracts and utilizes only the essential information needed for scale level selection (motion blur estimation and scale change) while discarding unnecessary computational operations. This selective approach allows the system to achieve robust tracking without the time cost of exhaustive multi-scale processing

Inventive Principle:

Principle #2Taking out (Extraction)

3Measurement precision

If high computational operations are performed to maintain tracking accuracy under high dynamics, then tracking accuracy is improved, but power consumption increases

Engineering Contradiction:

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The system dynamically adjusts the scale level parameter for feature matching based on estimated motion blur and scale change. Instead of using fixed multiple scale levels, the system changes the scale parameter adaptively, selecting the optimal single scale level that balances tracking accuracy with computational efficiency, thus reducing power consumption

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The system performs preliminary estimation of motion blur levels and scale changes before feature matching. By predicting the optimal scale level in advance based on motion blur estimation and scale change detection, the system avoids unnecessary computational operations at multiple scale levels, thereby reducing power consumption while maintaining tracking accuracy

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11683585B2Direct scale level selection for multilevel feature tracking under motion blur

Publication Date: 2023.06.20

AI summary

A method for mitigating motion blur in a visual-inertial tracking system is described. In one aspect, the method includes accessing a first image generated by an optical sensor of the visual tracking system, accessing a second image generated by the optical sensor of the visual tracking system, the second image following the first image, determining a first motion blur level of the first image, determining a second motion blur level of the second image, identifying a scale change between the first image and the second image, determining a first optimal scale level for the first image based on the first motion blur level and the scale change, and determining a second optimal scale level for the second image based on the second motion blur level and the scale change.