BIM-Based Building Structure Inspection With AR Image Recognition

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional building structure inspection methods using Building Information Modeling (BIM) are time-consuming and prone to operational errors due to the need for manual searching and paper-based recording, leading to inefficient and inaccurate inspections.

Innovation Solution

An inspection system utilizing a digital environment integration platform, server, and mobile device with camera and screen, which captures physical inspection images, recognizes features, and overlays augmented reality models onto the environment image for real-time comparison and form editing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If manual searching in BIM models and paper-based recording are used, then inspection completeness can be maintained, but inspection time and operational complexity increase significantly

Engineering Contradiction:

Improveinspection efficiencyVSAvoidtime for searching and recording

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical operations (physical searching through BIM models and paper-based recording) with automated image recognition technology. The system captures images of structural parts, automatically recognizes and extracts feature data through AI algorithms, and digitally records inspection results, eliminating the need for manual searching and paper forms.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The inspection system enables self-service automation where the system automatically performs data collection, recognition, and recording without continuous human intervention. The image recognition system autonomously identifies structural parts and extracts features, while the digital form system automatically populates inspection data, reducing reliance on manual operator actions.

Inventive Principle:

Principle #25Self-service

2Measurement precision

If manual searching and paper forms are used, then flexibility in inspection methods is maintained, but accuracy and completeness of recording decrease

Engineering Contradiction:

Improveaccuracy of inspection recordingVSAvoidoperational simplicity

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The patent replaces error-prone manual recording operations with automated digital systems. Image recognition algorithms accurately extract feature data from captured images, and digital forms automatically record inspection results, eliminating human errors in transcription and recording while maintaining operational simplicity through automated workflows.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system implements feedback mechanisms where inspection images are captured, automatically recognized and verified, and recording accuracy is enhanced through digital validation. The system provides feedback loops that ensure data completeness and accuracy by automatically cross-referencing recognized features with inspection requirements.

Inventive Principle:

Principle #23Feedback

3Productivity

If extensive BIM models are searched manually, then comprehensive inspection coverage is achieved, but inspection speed and efficiency deteriorate

Engineering Contradiction:

Improveinspection speedVSAvoidinspection coverage completeness

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent extracts only the necessary inspection information directly from captured images of structural parts, rather than requiring comprehensive manual searching through extensive BIM models. The image recognition system extracts relevant feature data directly from the photographed parts, achieving both speed and completeness by focusing on actual inspection targets.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The system performs preliminary actions by capturing images of structural parts at the inspection location, which are then automatically processed for recognition and data extraction. This preliminary image capture and automated processing enables comprehensive inspection coverage without requiring time-consuming manual searching through BIM models.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS12406449B2Inspection system and inspection method of building structures by using augmented reality based on building information modeling

Publication Date: 2025.09.02 LEE MING CONSTR

AI summary

An inspection system of building structures includes a digital environment integration platform based on Common Data Environment, a physical inspection image corresponding to a structural part model in the Building Information Modeling, a server, and a mobile device. An inspection method of the building structures includes: connecting the server to the digital environment integration platform; recognizing feature data of the physical inspection image and sending the feature data to the server by the mobile device; acquiring the corresponding structural part model from the digital environment integration platform and sending the structural part model and a link of an inspection form to the mobile device by the server, wherein the inspection form complies with ISO 19650 standards; displaying an environment image and an augmented reality element of the structural part model on a screen by the mobile device; linking the mobile device to the inspection form.