Dynamic Merging Threshold for Candidate Areas in Overlapping Images

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing image processing algorithms fail to effectively merge candidate areas across overlapping regions in discontinuous images captured by single or separate image sensors, leading to missed identifications of features that are present in both images.

Innovation Solution

A method that determines an image overlap size and a merging threshold based on this size, allowing candidate areas from overlapping regions in different images to be merged if their overlap ratio exceeds the threshold, thereby forming a single merged candidate area.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If a fixed merging threshold is used for candidate areas in overlapping regions, then the merging process is simple and fast, but the accuracy of identifying the same feature across images deteriorates due to varying overlap sizes

Engineering Contradiction:

Improvemerging process speedVSAvoidfeature identification accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The merging threshold is changed from a fixed value to a dynamic value that adapts based on the image overlap size. The threshold is calculated as a function of the overlap area, allowing the merging criterion to adjust automatically to different overlap scenarios, thereby maintaining high accuracy across varying overlap conditions while preserving computational efficiency

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The merging threshold parameter is modified based on the image overlap size parameter. By establishing a relationship between the overlap size and the appropriate threshold value, the system dynamically adjusts the merging criterion to match the actual overlap conditions, resolving the contradiction between using a simple fixed threshold and achieving accurate feature identification

Inventive Principle:

Principle #35Parameter changes

2Reliability

If the merging threshold is lowered to merge more candidate areas, then more features are identified, but the risk of merging unrelated features increases

Engineering Contradiction:

Improvefeature identification completenessVSAvoidfalse positive merging

Core Design Contradiction:

ReliabilityVSLoss of information

Solution Approach 1:

The merging threshold is customized for each local region based on its specific overlap size. Regions with larger overlaps receive more permissive thresholds that encourage merging, while regions with smaller overlaps receive stricter thresholds that prevent false merges. This localized adaptation allows the system to be sensitive to local geometric conditions, improving both completeness and reliability of feature identification

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS12260605B2Device and a method for merging candidate areas

Publication Date: 2025.03.25 AXIS

AI summary

A device and method merge a first candidate area relating to a candidate feature in a first image and a second candidate area relating to a candidate feature in a second image. The first and second images have an overlapping region, and at least a portion of the first and second candidate areas are located in the overlapping region. An image overlap size is determined indicating a size of the overlapping region of the first and second images, and a candidate area overlap ratio is determined indicating a ratio of overlap between the first and second candidate areas. A merging threshold is then determined based on the image overlap size, and, on condition that the candidate area overlap ratio is larger than the merging threshold, the first candidate area and the second candidate area are merged, thereby forming a merged candidate area.