AI Utilization Case Study: Verification Experiment of Crack Survey Using AI at Tokyu Construction Co., Ltd.
Tokyu Construction introduced NTT e-Drone Technology's 'e-Drone AI' for railway viaduct inspections, achieving a 50% reduction in crack survey workload and improving inspection quality.
📋 Article Processing Timeline
- 📰 Published: April 23, 2026 at 19:00
- 🔍 Collected: April 23, 2026 at 10:31
- 🤖 AI Analyzed: April 24, 2026 at 03:36 (17h 4m after Collected)
The damage detection AI service "e-Drone AI" (Service page: https://www.nttedt.co.jp/edrone-ai) is an inspection support service that uses AI to analyze surface images of concrete structures and detect cracks and deterioration damage with high precision. (Ministry of Land, Infrastructure, Transport and Tourism Inspection Support Technology Performance Catalog Technology Number: BR010076-V0126)
This time, we will introduce a case study of its utilization in railway viaduct inspection at Tokyu Construction Co., Ltd.
1. Background
Tokyu Construction Co., Ltd. (Headquarters: Shibuya-ku, Tokyo), which used "e-Drone AI" this time, had the following challenges in inspecting infrastructure structures such as railway viaducts:
- There are many places where visual confirmation is difficult, such as high places.
- A lot of time and manpower are required to extract and organize damage from the vast amount of images taken.
- It tends to depend on the inspector's experience, leading to variations in judgment.
- There was a demand for efficiency and labor saving in the overall inspection survey business.
To solve these challenges and improve operational efficiency while maintaining and improving inspection quality, they utilized "e-Drone AI".
Location of use: Railway viaduct currently undergoing repair work
2. Details of Utilization
◇ Targets for Inspection Survey
Floor slabs, main girders, and cross girders of railway viaducts (Concrete structures)
◇ Shooting Method
Shooting in high resolution using a single-lens high-resolution camera.
Comprehensively shooting the target area to acquire data for analysis.
◇ Analysis Details
AI analysis of captured images using "e-Drone AI".
For some members, orthophotos are generated from captured images and analyzed by AI.
(It is possible to grasp the damaged areas planarly.)
CAD output of crack damage maps.
◇ Main Detection Items by AI
- Cracks (width/length)
- Exfoliation
- Rebar exposure
- Water leakage
- Free lime
3. Implementation Effects
The utilization of "e-Drone AI" yielded the following effects:
- Halved the work required for crack surveys (Labor saving)
- Improved inspection quality by reducing the risk of oversight (Extractable from a crack width of 0.05mm)
- Utilized for estimating repair work (Utilized for calculating information quantities such as crack width and length)
- Streamlined report material creation (A CAD file drawn with crack line figures is generated, allowing for the creation of damage maps by overlaying it on drawings)
As a result, it contributes to creating an environment where the post-inspection survey processes, which conventionally required a lot of time, are streamlined, allowing focus on tasks with higher added value.
4. Contact Information for Customers and Press Regarding this Matter
NTT e-Drone Technology Co., Ltd. Service Promotion Department
omakase_edrone@nttedt.co.jp
This time, we will introduce a case study of its utilization in railway viaduct inspection at Tokyu Construction Co., Ltd.
1. Background
Tokyu Construction Co., Ltd. (Headquarters: Shibuya-ku, Tokyo), which used "e-Drone AI" this time, had the following challenges in inspecting infrastructure structures such as railway viaducts:
- There are many places where visual confirmation is difficult, such as high places.
- A lot of time and manpower are required to extract and organize damage from the vast amount of images taken.
- It tends to depend on the inspector's experience, leading to variations in judgment.
- There was a demand for efficiency and labor saving in the overall inspection survey business.
To solve these challenges and improve operational efficiency while maintaining and improving inspection quality, they utilized "e-Drone AI".
Location of use: Railway viaduct currently undergoing repair work
2. Details of Utilization
◇ Targets for Inspection Survey
Floor slabs, main girders, and cross girders of railway viaducts (Concrete structures)
◇ Shooting Method
Shooting in high resolution using a single-lens high-resolution camera.
Comprehensively shooting the target area to acquire data for analysis.
◇ Analysis Details
AI analysis of captured images using "e-Drone AI".
For some members, orthophotos are generated from captured images and analyzed by AI.
(It is possible to grasp the damaged areas planarly.)
CAD output of crack damage maps.
◇ Main Detection Items by AI
- Cracks (width/length)
- Exfoliation
- Rebar exposure
- Water leakage
- Free lime
3. Implementation Effects
The utilization of "e-Drone AI" yielded the following effects:
- Halved the work required for crack surveys (Labor saving)
- Improved inspection quality by reducing the risk of oversight (Extractable from a crack width of 0.05mm)
- Utilized for estimating repair work (Utilized for calculating information quantities such as crack width and length)
- Streamlined report material creation (A CAD file drawn with crack line figures is generated, allowing for the creation of damage maps by overlaying it on drawings)
As a result, it contributes to creating an environment where the post-inspection survey processes, which conventionally required a lot of time, are streamlined, allowing focus on tasks with higher added value.
4. Contact Information for Customers and Press Regarding this Matter
NTT e-Drone Technology Co., Ltd. Service Promotion Department
omakase_edrone@nttedt.co.jp