Low-cost monitoring through IoT: inspection, damage recognition, damage detection.
Social Infrastructure (Saitama University Research Seed Collection 2025-27 p.17)
Keywords: IoT, UAV, AI, structure, monitoring, inspection, damage
In Japan, the aging of structures such as bridges is progressing, and it is important to quickly confirm damage to structures for rapid performance recovery after an earthquake. In recent years, there has been increasing attention on the use of robots and small unmanned aerial vehicles (UAVs) for structural damage and deterioration, and UAVs specialized for expensive inspection tasks have also been developed. However, even regular smartphones and general-purpose aerial photography UAVs can capture many high-precision photos and videos. While it is possible to manually analyze these images, considering the following points: (1) Spending time on processing vast amounts of data, (2) Fatigue and errors due to long hours of work, (3) The need for highly specialized knowledge and stable judgment criteria, automated image data processing or real-time automatic damage detection is desirable. Therefore, by using deep learning to train machines on a large number of damage photos, automatic damage detection becomes possible. This technology has demonstrated high damage detection accuracy as a verification of the usefulness of deep learning for damage images, based on image classification attempts using deep learning on images collected from past visual inspections of bridges.
Inquire About This Product
basic information
Toki (Tou Ki) Associate Professor Graduate School of Science and Engineering, Department of Environmental and Social Infrastructure, Field of Social Infrastructure Creation 【Recent Research Themes】 ● Damage recognition, image processing, and corrosion detection using deep learning ● Bridge inspection using UAVs and construction of 3D models ● Seismic performance of rubber bearings in cold regions ● Earthquake response monitoring and damage estimation of structures using IoT sensors ● Virtual surveying and design implementation using 3D models
Price range
Delivery Time
Applications/Examples of results
【Appeal Points to the Industry】 ● Easy to handle and applicable to both high-rise buildings and elevated bridges. ● Extremely low initial and maintenance costs. ● Ability to check the system status in real-time via smartphone. ● Utilizing artificial intelligence, the more it is used, the higher the accuracy of structural damage estimation. 【Examples of Practical Application, Use Cases, and Utilization】 ● Water level monitoring of rivers and vibration monitoring of buildings and bridges using IoT. ● Bridge inspections using UAVs. ● Image damage detection using AI.
Detailed information
-
Damage recognition by AI
catalog（1）
Download All Catalogs
Company information
The Saitama University Open Innovation Center is a center that functions as a liaison office for industry-academia-government collaboration. It consists of three departments: the Industry-Academia-Government Collaboration Department, the Intellectual Property Department, and the Startup Support Department, each staffed with coordinators well-versed in various fields. The center's activities include solving technical challenges in companies, supporting the implementation of joint research, and conducting technology transfer aimed at introducing and utilizing Saitama University's intellectual property.
![Operator Proximity Detection "Hiyari Hunter" [Vehicle Detection Available - Demo Unit for Loan]](https://image.mono.ipros.com/public/product/image/f3e/2000240614/IPROS80854192249833723486.jpeg?w=280&h=280)
![[For the pharmaceutical manufacturing industry] Digitizing entry management in oxygen-deficient hazardous work.](https://image.mono.ipros.com/public/product/image/20a/2001525768/IPROS14827379347403299223.jpg?w=280&h=280)
![[For the food manufacturing and beverage manufacturing industry] Digitizing the management of oxygen deficiency hazard work in tank entry.](https://image.mono.ipros.com/public/product/image/bf8/2001525769/IPROS12773363766147418267.jpg?w=280&h=280)