Imaging Apparatus Position Estimation Using Image Feature Matching

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing three-dimensional estimation methods using fixed or portable cameras face challenges in estimating the position and attitude of imaging apparatuses, particularly when occlusion occurs, leading to difficulties in accurately estimating the three-dimensional structure of objects.

Innovation Solution

An information processing apparatus and method that estimates the position and attitude of a first imaging apparatus based on three-dimensional data and image feature values acquired from both the first imaging apparatus and a second imaging apparatus with known position and attitude, using techniques such as matching image feature values and solving perspective n-point problems.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Stability of the object's composition

If a fixed camera system is used for three-dimensional estimation, then the position of imaging apparatus is stable, but occlusion cannot be cancelled and estimation accuracy deteriorates

Engineering Contradiction:

Improveposition stability of imaging apparatusVSAvoidthree-dimensional structure estimation accuracy

Core Design Contradiction:

Stability of the object's compositionVSMeasurement precision

Solution Approach 1:

The patent transitions from fixed cameras to portable cameras that can dynamically change position and attitude. The system estimates the dynamic position and attitude of portable cameras through image feature matching and perspective n-point problems, enabling the imaging apparatus to move to optimal positions for capturing different viewpoints and canceling occlusions.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The patent introduces an estimation processing section as an intermediary that calculates the position and attitude of portable cameras based on image features. This intermediary component enables the system to handle dynamic camera positions by computing transformation matrices and projection relationships between images captured from different viewpoints.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If portable cameras are used for three-dimensional estimation, then occlusion can be cancelled, but position and attitude of imaging apparatus cannot be estimated

Engineering Contradiction:

Improvethree-dimensional structure estimation accuracyVSAvoidposition and attitude estimation difficulty

Core Design Contradiction:

Measurement precisionVSDifficulty of detecting and measuring

Solution Approach 1:

The patent implements a feedback mechanism where the estimation processing section continuously calculates the position and attitude of portable cameras based on image features, and this estimated information is fed back to correct and refine the three-dimensional structure estimation. This iterative feedback process resolves the difficulty of position and attitude estimation.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent replaces the mechanical fixed mounting system with a computational approach using image feature matching and perspective n-point problems. Instead of physically constraining cameras to fixed positions, the system uses mathematical models to estimate camera parameters from image data, substituting mechanical constraints with computational solutions.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Measurement precision

If multiple fixed cameras are deployed to improve estimation accuracy, then measurement precision improves, but device complexity and cost increase

Engineering Contradiction:

Improvethree-dimensional structure estimation accuracyVSAvoidnumber of imaging apparatus

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent makes portable cameras multi-functional by enabling them to perform both image capture and self-position estimation functions. The same portable camera that captures images for three-dimensional reconstruction also uses its captured images to estimate its own position and attitude, eliminating the need for separate fixed reference cameras and reducing overall system complexity.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent implements self-service where portable cameras estimate their own position and attitude using their captured images and the estimation processing section. This self-positioning capability eliminates the need for external fixed reference systems, allowing the portable cameras to serve themselves and reducing the total number of imaging apparatus required.

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS11302021B2Information processing apparatus and information processing method

Publication Date: 2022.04.12 SONY GROUP CORP

AI summary

Provided is an information processing apparatus, including: an estimation processing section that, on the basis of three-dimensional data and a first image feature value that are set and a second image feature value that is acquired from a captured image captured by a first imaging apparatus, estimates a position and attitude of the first imaging apparatus.