Defect-Aware Image Analysis Region Division for Infrastructure Inspection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing image-based inspection methods for infrastructure structures, such as bridges and tunnels, face inefficiencies due to the splitting of defects across multiple inspection regions, leading to misidentification and inefficient task distribution among workers.

Innovation Solution

An image processing apparatus that divides inspection regions based on defect status, including size, position, and concentration, to minimize defect splitting and improve efficiency by ensuring each defect is inspected within a single region.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If the inspection region is divided using a predetermined distance, then the inspection task is facilitated and worker efficiency is improved, but defects longer than the division size are split across multiple regions causing misidentification

Engineering Contradiction:
Improveinspection efficiencyVSAvoiddefect identification accuracy
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The inspection region is divided into multiple sub-regions, but the division is intelligently controlled to ensure defects are not split. The system segments the region based on defect boundaries detected through image analysis, rather than simple geometric division.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs preliminary image analysis to detect defects and determine their boundaries before dividing the inspection region. This preliminary action ensures that subsequent region division does not split defects, as the division boundaries are adjusted based on the detected defect locations.

Inventive Principle:
Principle #10Preliminary action

2Ease of operation

If the inspection region is divided into multiple sections, then the inspection task becomes more manageable, but multiple workers checking different portions of the same defect lead to task inefficiency

Engineering Contradiction:
Improvetask manageabilityVSAvoidinspection efficiency
Core Design Contradiction:
Ease of operationVSProductivity

Solution Approach 1:

The system provides feedback information to workers about which defects are located at region boundaries and may be visible in adjacent regions. This feedback mechanism prevents duplicate inspection of the same defect by multiple workers and ensures complete defect coverage.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system acts as an intermediary that coordinates the inspection tasks among multiple workers. It manages the assignment of defects to specific workers and provides information about defect locations that span multiple regions, ensuring efficient task distribution.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Shape

If defects are split across multiple division regions, then the region division achieves compact boundaries, but the overall defect image cannot be viewed in a single region requiring multiple checks

Engineering Contradiction:
Improveregion boundary compactnessVSAvoidtime for multiple defect checks
Core Design Contradiction:
ShapeVSLoss of time

Solution Approach 1:

The system performs preliminary detection of defect boundaries and uses this information to adjust region division boundaries. This ensures that complete defect images are contained within single inspection regions, eliminating the need for workers to check multiple regions for the same defect.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP4685739A1Image processing apparatus, image processing method, and program
Publication Date: 2026.01.28 CANON KK
  • EP4685739A1 patent drawingFigure 1
  • EP4685739A1 patent drawingFigure 2
  • EP4685739A1 patent drawingFigure 3A~3B

AI summary

An image processing apparatus includes an image analysis unit (103) configured to perform image analysis on an image to be inspected to acquire defects obtained as a result of the image analysis and a division unit (104) configured to divide a region subjected to the image analysis to acquire division regions, and the division unit (104) divides the region subjected to the image analysis on the basis of a status of the defects. The status of the defects includes at least the size and position of each defect.