Mixed Reality Camera Positioning via Dynamic Region of Interest Processing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing mixed reality (MR) technologies face challenges in maintaining a high frame rate and accurate camera positioning and orientation estimation, particularly in environments with many natural features or fine patterns, leading to reduced estimation accuracy and increased processing time.

Innovation Solution

An information processing apparatus that switches between frame rate priority and estimation accuracy priority modes based on user movement or other input signals, using feature detection and extended Kalman filter predictions to optimize camera positioning and orientation estimation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If natural features are detected from entire images to estimate camera position and orientation, then estimation accuracy is improved, but processing time increases and frame rate decreases

Engineering Contradiction:
Improvecamera position and orientation estimation accuracyVSAvoidframe rate
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The image is divided into multiple regions of interest (ROIs) based on detected salient points. Feature detection and matching is performed only within these ROIs rather than across the entire image, significantly reducing the computational area and processing time while maintaining estimation accuracy through focused analysis of critical regions.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Different processing strategies are applied to different regions of the image. Salient points and their surrounding ROIs receive intensive feature analysis, while other regions are processed more lightly or skipped. This local differentiation optimizes the balance between estimation accuracy and processing speed.

Inventive Principle:
Principle #3Local quality

2Measurement precision

If more natural features are detected to improve estimation accuracy, then measurement precision is improved, but device complexity and processing load increase

Engineering Contradiction:
Improveposition and orientation estimation accuracyVSAvoidprocessing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

Salient points are detected first as preliminary features to identify regions of interest before performing full feature detection and matching. This preliminary action guides subsequent processing to focus only on relevant areas, reducing overall processing complexity while maintaining accuracy.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The processing approach dynamically adapts based on the detected salient points and image content. The system adjusts the number and size of ROIs, and selectively applies feature detection algorithms only where needed, making the processing complexity dynamic rather than static and exhaustive.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentUS10970807B2Information processing apparatus and storage medium
Publication Date: 2021.04.06 CANON KK
  • US10970807B2 patent drawing
  • US10970807B2 patent drawing
  • US10970807B2 patent drawing

AI summary

An information processing apparatus includes an obtainment unit configured to obtain an image from an image capturing apparatus, a selection unit configured to select either of an estimation accuracy priority mode which prioritizes estimation accuracy of at least either one of a position and an orientation of the image capturing apparatus over a frame rate, and a frame rate priority mode which prioritizes the frame rate over the estimation accuracy, an estimation unit configured to estimate at least either one of the position and the orientation of the image capturing apparatus based on a feature of the image according to the mode selected by the selection unit, and a control unit configured to cause a display unit to display an image based on at least either one of the estimated position and the estimated orientation of the image capturing apparatus.