Object Relationship Management Across Multiple Image Capturing Apparatuses

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems struggle to effectively manage the relationship between objects detected in images captured by multiple image capturing apparatuses, leading to unclear relationships between objects across different images.

Innovation Solution

A method and apparatus that involve mapping the positions of multiple image capturing apparatuses to generate mapping information, detecting objects in images using trained models, and storing connection information between detected objects based on their types, behavior, and spatial relationships.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If multiple image capturing apparatuses are used to detect objects, then the quantity of detected objects increases, but the complexity of managing relationships between objects increases

Engineering Contradiction:

Improvequantity of detected objectsVSAvoidcomplexity of managing object relationships

Core Design Contradiction:

Quantity of substanceVSDevice complexity

Solution Approach 1:

The patent introduces mapping information as an intermediary data structure that represents spatial relationships between image capturing apparatuses. This mapping information serves as a mediator that connects detection results from multiple apparatuses, enabling the system to manage object relationships across different devices without direct complex interactions between the apparatuses themselves.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent creates a universal connection information structure that can represent various types of relationships between objects detected by different apparatuses. This connection information serves multiple functions: it links objects across devices, stores spatial relationships, and enables relationship management in a unified manner regardless of which specific apparatus detected which object.

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Reliability

If mapping information and connection information are stored, then the ability to identify object relationships improves, but the amount of stored data increases

Engineering Contradiction:

Improveability to identify object relationshipsVSAvoidamount of stored data

Core Design Contradiction:

ReliabilityVSQuantity of substance

Solution Approach 1:

The patent extracts and stores only the essential relationship information needed to identify object connections. Rather than storing complete image data or all possible attributes, the system extracts key connection information such as spatial relationships and object associations, storing only what is necessary to maintain relationship identification capability.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent creates simplified copies of relationship data in the form of mapping information and connection information. These are lightweight data structures that replicate only the essential spatial and relational attributes needed to identify object relationships, rather than storing full image data or comprehensive object descriptions.

Inventive Principle:

Principle #26Copying

Data Source

PatentUS20250069441A1Method for managing information of object and apparatus performing same

Publication Date: 2025.02.27 HANWHA VISION CO LTD

AI summary

Embodiments of the present disclosure relate to a method and apparatus for effectively managing a relationship between objects detected in images captured by a plurality of image capturing apparatuses. A method of managing an object detected by a plurality of image capturing apparatuses includes mapping positions of the plurality of image capturing apparatuses to generate mapping information, obtaining a first image from each of the plurality of image capturing apparatuses, detecting an object from the first image of each of the plurality of image capturing apparatuses, based on a first trained model, and storing the mapping information and connection information between detected objects.