Image Feature Streaming for Faster Camera Pose Localization

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing image-based localization techniques using multiple images for pose estimation in real-world environments face challenges with increased processing time and resource consumption, particularly when transmitting and processing multiple sets of image features to a remote device for pose estimation.

Innovation Solution

The method involves capturing multiple images simultaneously or sequentially and transmitting detected image features to a remote device in parallel, allowing the remote device to begin pose estimation before all features are extracted, thereby reducing overall processing time and resource consumption.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If multiple images are captured and processed sequentially to improve pose estimation accuracy, then measurement precision is improved, but loss of time increases

Engineering Contradiction:
Improvepose estimation accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent applies preliminary action by transmitting the first set of image features to the remote device before completing detection of additional image features. This allows the remote device to start pose estimation processing early, using available features while more features are being detected and transmitted, thereby reducing overall processing time while maintaining accuracy through progressive refinement as more features become available.

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If multiple images are captured and fully processed before transmission to improve accuracy, then measurement precision is improved, but use of energy increases

Engineering Contradiction:
Improvepose estimation accuracyVSAvoidpower consumption
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent reduces power consumption by performing preliminary transmission of the first set of image features before completing full processing of all images. This early transmission allows the camera device to offload computation to the remote device while still capturing additional images, distributing the energy burden and reducing peak power consumption on the mobile device while maintaining accurate pose estimation through subsequent feature updates.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3973444B1Image-based localization
Publication Date: 2025.12.17 MICROSOFT TECHNOLOGY LICENSING LLC
  • EP3973444B1 patent drawingFigure 1A~1B
  • EP3973444B1 patent drawingFigure 2
  • EP3973444B1 patent drawingFigure 3

AI summary

A method for image-based localization includes, at a camera device, capturing a plurality of images of a real-world environment. A first set of image features are detected in a first image of the plurality of images. Before additional sets of image features are detected in other images of the plurality, the first set of image features is transmitted to a remote device configured to estimate a pose of the camera device based on image features detected in the plurality of images. As the additional sets of image features are detected in the other images of the plurality, the additional sets of image features are transmitted to the remote device. An estimated pose of the camera device is received from the remote device.