Automated Damage Figure Creation from Marking Color Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing inspection methods for structures, such as bridges, impose a heavy burden on inspection engineers and are prone to errors in creating damage figures due to the lack of standardized use of chalk colors for marking damage.

Innovation Solution

A damage figure creation supporting system that detects the color of markings from images taken during inspections and analyzes them to efficiently create damage figures, allowing for standardized classification of damage based on marking colors.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If inspection engineers manually create damage figures based on sketches and photographs, then damage figures can be created, but the burden on inspection engineers is heavy and errors are likely to occur

Engineering Contradiction:
Improveaccuracy of damage figure creationVSAvoidcomplexity of inspection process
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent replaces the manual mechanical process of creating damage figures with an automated image processing system. The system automatically detects markings in captured images, extracts their coordinates and colors, and generates damage figures without manual intervention, thereby reducing the burden on inspection engineers while maintaining accuracy.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The inspection system performs self-service by automatically processing inspection images to generate damage figures. The image processing unit autonomously detects markings, determines their positions and colors, and creates damage figures without requiring inspection engineers to manually sketch or photograph each damage location.

Inventive Principle:
Principle #25Self-service

2Loss of information

If different colors of chalk are used for marking according to damage characteristics, then damage information can be categorized, but there is no specific rule for color usage making it difficult for third parties to utilize the information

Engineering Contradiction:
Improvepreservation of damage classification informationVSAvoidusability of marking color information
Core Design Contradiction:
Loss of informationVSEase of operation

Solution Approach 1:

The system provides feedback by automatically analyzing the colors of markings in captured images and correlating them with damage characteristics. The image processing unit detects marking colors and uses this information to automatically classify and annotate damage types in the generated damage figures, making the previously ambiguous color information meaningful and usable.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent transforms the physical parameter of marking color into actionable data by automatically detecting and analyzing color values in images. The system converts color information into classified damage categories, changing the parameter from a visual characteristic to a structured data element that can be systematically utilized.

Inventive Principle:
Principle #35Parameter changes

3Productivity

If automatic detection techniques are applied to detect markings from captured images, then damage figure creation is accelerated, but the techniques require specific conditions such as water-retaining agents or standardized marking colors

Engineering Contradiction:
Improveefficiency of damage figure creationVSAvoidflexibility of marking methods
Core Design Contradiction:
ProductivityVSAdaptability or versatility

Solution Approach 1:

The system changes the detection parameter from relying on specific marking conditions (like water-retaining agents or standardized colors) to analyzing general color characteristics in the image. By detecting color differences between markings and the background structure, the system achieves automatic detection without requiring specialized marking materials or conditions.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The image processing system achieves universality by being able to detect various types of markings regardless of the specific chalk color or marking method used. The system processes any color marking on the structure surface, making it adaptable to different inspection scenarios without requiring standardized marking procedures.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The system enables accurate and efficient creation of damage figures, reducing the burden on inspection engineers and minimizing errors by standardizing the interpretation of marking colors, thus facilitating more reliable inspection reports.

Implementation Method 1

an image processing unit that analyzes the captured image and detects a color of a marking in the captured image

Methodology Applied
Scientific EffectImage processing: Image Processing

Data Source

PatentEP3896435B1Damage diagram creation assistance device, damage diagram creation assistance method, damage diagram creation assistance program, and damage diagram creation assistance system
Publication Date: 2025.04.23 FUJIFILM CORP
  • EP3896435B1 patent drawingFigure 1
  • EP3896435B1 patent drawingFigure 2
  • EP3896435B1 patent drawingFigure 3

AI summary

Provided are a damage figure creation supporting apparatus, a damage figure creation supporting method, a damage figure creation supporting program, and a damage figure creation supporting system that enable efficient creation of a damage figure using marking colors. The damage figure creation supporting method includes a step of acquiring an image obtained by photographing a surface of a structure in color, a step of analyzing the acquired image and detecting markings applied to damaged portions on the surface of the structure for respective colors, and a step of creating a damage figure, based on detection results of the markings for the respective colors. The damage figure is configured as a diagram of tracing the markings and has a layered structure with layers each corresponding to a color.