Imaging Device Position Mapping With Dynamic Feature Reliability

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for measuring the position/orientation of an imaging device based on image features suffer from decreased stability when the number of natural feature points is small, leading to errors and reduced accuracy in position measurement.

Innovation Solution

An information processing device that evaluates the stability of the position/orientation of an imaging device, adjusts the reliability of features in a three-dimensional map based on stability, and corrects the map to maintain accuracy and extend the measurable range by incorporating additional features and auxiliary indicators.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If high reliability is set for fixed feature points and correction is performed, then measurement accuracy is improved, but stability of position measurement decreases when the number of natural feature points is small

Engineering Contradiction:
Improveposition measurement accuracyVSAvoidposition measurement stability
Core Design Contradiction:
Measurement precisionVSStability of the object's composition

Solution Approach 1:

The patent applies dynamics by making the reliability values of feature points dynamic rather than fixed. The reliability of each feature point is adjusted based on the stability evaluation result, allowing the system to adaptively balance between using fixed feature points for accuracy and natural feature points for stability. This dynamic adjustment resolves the contradiction by enabling the system to maintain both measurement accuracy and stability under different conditions.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent changes the parameter of reliability values assigned to feature points based on the evaluation of position measurement stability. When stability is sufficient, higher reliability is assigned to fixed feature points to improve accuracy. When stability is insufficient, the system adjusts reliability distribution to incorporate more natural feature points, thereby maintaining both accuracy and stability through parameter adaptation.

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If the number of natural feature points is small, then measurement accuracy deteriorates, but using more fixed feature points increases device complexity

Engineering Contradiction:
Improveposition measurement accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies partial action by selectively using only the necessary number of fixed feature points based on the evaluation result, rather than using all available fixed feature points unconditionally. This allows the system to achieve sufficient measurement accuracy without unnecessarily increasing complexity by incorporating more fixed feature points than needed.

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The system performs self-evaluation of position measurement stability and automatically adjusts the reliability distribution between fixed and natural feature points without external intervention. This self-service mechanism enables the system to optimize its own complexity-accuracy balance by determining the appropriate mix of feature points based on current measurement conditions.

Inventive Principle:
Principle #25Self-service

Data Source

PatentUS20250245924A1Information processing device, information processing method, and storage medium
Publication Date: 2025.07.31 CANON KK
  • US20250245924A1 patent drawing
  • US20250245924A1 patent drawing
  • US20250245924A1 patent drawing

AI summary

An information processing device includes a derivation unit configured to derive a position of an imaging device using a captured image and a three-dimensional map; an evaluation unit configured to evaluate a stability of the position based on information used to derive the position; a preparation unit configured to prepare the three-dimensional map based on the captured image and the position; a setting unit configured to set information indicating reliabilities of information indicating the three-dimensional position of the feature of the subject and information indicating a three-dimensional position of the feature included in a predetermined area in the three-dimensional map, which are acquired based on the captured image in an extended area of a predetermined area, based on a result of evaluation from the evaluation unit; and a correction unit configured to correct the three-dimensional map based on the information indicating the reliabilities set.