Image Coordinate Uncertainty Estimation During Large Camera Motion

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing image coordinate tracking methods in computer vision and robotics suffer from reduced accuracy due to changes in visual characteristics such as motion blur, illumination changes, and occlusion, leading to tracking failures and accumulated errors, especially when camera motion is large.

Innovation Solution

An apparatus and method that utilize both a camera sensor and a motion sensor to estimate the uncertainty of image coordinates by calculating a target coordinate distribution based on image-based and motion-based tracking coordinates, incorporating depth values and motion data to update the tracking coordinates and reduce uncertainty.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If image coordinate tracking is performed using only image data from camera sensor, then the method is simple to implement, but tracking accuracy deteriorates under large camera motion due to motion blur, illumination change, and occlusion

Engineering Contradiction:

Improvetracking method complexityVSAvoidcoordinate tracking accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent combines image-based tracking coordinates from the camera sensor with motion-based tracking coordinates from the motion sensor to create a unified coordinate estimation system. By merging these two data sources, the system achieves higher tracking accuracy under large camera motion while maintaining reasonable implementation complexity through integrated processing.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The patent introduces an intermediary coordinate distribution model that mediates between image-based and motion-based tracking coordinates. This intermediary structure allows the system to reconcile differences between the two tracking methods and produce a more accurate estimated coordinate, effectively resolving the accuracy-complexity contradiction.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If motion-based tracking coordinate is added to improve tracking accuracy, then coordinate estimation reliability improves, but system complexity increases due to integration of motion sensor data

Engineering Contradiction:

Improvecoordinate estimation reliabilityVSAvoidsystem integration complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent creates a universal coordinate estimation framework that can process both image-based and motion-based tracking coordinates through a single integrated system. This multi-functional approach allows the system to handle multiple data sources uniformly, improving reliability without proportionally increasing complexity.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent transforms the coordinate estimation problem into a parameter optimization problem by modeling the coordinate distribution as a probability distribution with unknown parameters. By estimating these parameters from both image and motion data, the system achieves higher reliability while managing complexity through mathematical formalism rather than computational complexity.

Inventive Principle:

Principle #35Parameter changes

3Productivity

If coordinate tracking is performed without uncertainty estimation, then the processing is faster, but the impact of visual characteristic changes cannot be quantified or corrected

Engineering Contradiction:

Improveprocessing speedVSAvoidtracking result reliability

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent introduces uncertainty estimation as a feedback mechanism that quantifies the reliability of coordinate tracking results. By calculating and utilizing this uncertainty information, the system can adapt to visual characteristic changes and correct tracking errors, improving reliability while maintaining acceptable processing speeds through efficient uncertainty computation.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS12387360B2Apparatus and method for estimating uncertainty of image coordinate

Publication Date: 2025.08.12 SAMSUNG ELECTRONICS CO LTD

AI summary

An apparatus for estimating an uncertainty includes a processor configured to receive a first tracking coordinate corresponding to a reference coordinate, the reference coordinate being included in first image data acquired by a camera sensor, the first tracking coordinate including an image-based tracking coordinate in second image data acquired after the first image data; acquire, based on motion data acquired from a motion sensor and a depth value of the first image data, a second tracking coordinate corresponding to the reference coordinate, the second tracking coordinate including a motion-based tracking coordinate in the second image data; calculate a target coordinate distribution in the second image data based on the first tracking coordinate and the second tracking coordinate; acquire an estimated target coordinate and an uncertainty of the estimated target coordinate based on the calculated target coordinate distribution; and update the first tracking coordinate based on the estimated target coordinate.