XR Relocalization Using Sensor-Guided Feature Subsets

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Extended reality systems face computational challenges in accurately relocalizing user devices due to the complexity of comparing captured images with large data sets, which can be mitigated by using data from multiple sensors to reduce the scope of comparison.

Innovation Solution

Utilizing sensors such as security cameras, motion detectors, and infrared sensors to refine and verify the approximate location of a mobile device, thereby generating a smaller subset of data for comparison to determine its position and orientation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If the entire known environment data set is compared with the captured image to determine device location, then localization accuracy is improved, but computational complexity increases

Engineering Contradiction:
Improvelocalization accuracyVSAvoidcomputational complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent divides the large known environment data set into multiple smaller subsets based on spatial regions or semantic categories. Instead of comparing the captured image with the entire data set, the system segments the comparison task into multiple smaller operations, each handling a specific subset. This reduces the computational complexity of each individual comparison while maintaining overall localization accuracy through coordinated results from multiple subsets.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary actions by pre-processing the known environment data set into organized subsets before the actual localization task. Data structures are pre-computed, indexed, and arranged in advance so that during runtime, the system can quickly select and compare only relevant subsets rather than processing the entire data set. This preliminary organization significantly reduces real-time computational complexity.

Inventive Principle:
Principle #10Preliminary action

2Productivity

If data from multiple sensors is used to refine approximate location, then relocalization efficiency is improved, but device complexity increases

Engineering Contradiction:
Improverelocalization efficiencyVSAvoidsensor integration complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent merges data from multiple sensors (cameras, LIDAR, inertial sensors, etc.) into a unified localization framework. Instead of treating each sensor independently, the system combines their outputs to generate a refined approximate location. This merging approach improves relocalization efficiency by leveraging complementary information from different sensors while managing complexity through integrated processing.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent implements a multi-functional sensor fusion system where the same processing framework handles data from various sensor types. The system is designed to be universal, accommodating different sensor inputs through a common interface and processing pipeline. This multi-functionality improves efficiency by reusing the same computational infrastructure across multiple sensor modalities rather than creating separate processing chains.

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

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

This approach reduces computational complexity and enhances the accuracy and efficiency of relocalization processes in extended reality environments.

Implementation Method 1

An infrared sensor may detect heat generated by the mobile device to further refine the approximate location

Methodology Applied
Scientific EffectInfrared radiation detection: Infrared Radiation

Data Source

PatentUS12470892B2Extended reality localization
Publication Date: 2025.11.11 COMCAST CABLE COMM LLC
  • US12470892B2 patent drawing
  • US12470892B2 patent drawing
  • US12470892B2 patent drawing

AI summary

Systems, apparatuses, and methods are described for relocalizing a mobile device within an extended reality environment. A subset of a data set, such as a feature pointcloud may be generated based on determining an approximate location of a mobile device. The approximate location may be determined based on data received from one or more sensors in the extended reality environment. Features associated with the approximate location may be included in the subset while other features may be removed. Features extracted from an image taken by the mobile device may be compared with the subset of the data set to relocalize the mobile device.