Non-Destructive Inspection Revolution: Structural Inspection DX Realized with AR and 3D Point Clouds

The Importance of Non-Destructive Inspection and the Limits of Traditional Methods

As social infrastructure ages, non-destructive inspection—which examines condition without causing damage—has become increasingly important to ensure the safety of structures such as bridges and tunnels. Since 2014, periodic close-range visual inspections of road bridges and tunnels have been legally mandated every five years, greatly increasing the frequency and scope of inspections nationwide. Many structures built intensively during the high-growth era are now entering a high-aging phase of over 50 years, so the importance and burden of inspections are expected to grow further. Traditionally, inspections of structures have been carried out by experienced technicians using visual inspection and simple tools to check for abnormalities. However, the following limitations and challenges of these conventional methods have been pointed out.

• Subjectivity: Inspection results are influenced by the individual inspector’s experience and subjective judgment, leading to potential discrepancies between veterans and newcomers

• Ambiguous records: Methods and formats for recording inspection results are not standardized; the accuracy and granularity of photos and notes vary by person, making it difficult to accurately reconstruct conditions later

• Low reproducibility: It is difficult to compare and verify against past inspections, making it hard to objectively grasp the rate of deterioration over time

For example, even with a single concrete crack, the conventional method was for the inspector to mark it with chalk, measure its length, and record it by hand. With this approach, it is hard for others reading the record to form a clear image of where and how large the crack was, and even locating the same spot at the next inspection can be difficult. Relying on such person-dependent methods limits the potential to improve the precision of infrastructure maintenance management. Therefore, there is a growing demand to realize inspection DX (digital transformation of inspections) using digital technologies to create a system in which anyone can perform high-precision inspection and recording consistently.

The Importance of “Visualization” and “Recordability” in Non-Destructive Inspection

The key to overcoming the above challenges is improving inspection information “visualization” and “recordability.” “Visualization” means making previously unseen things visible. In traditional inspections, the presence or degree of abnormalities often remained in the inspector’s head or on paper reports and was not visualized in a way that all stakeholders could intuitively share. For example, even if a report states “a 0.3 mm crack was found on the bearing of XX Bridge,” it is hard to grasp at a glance exactly where and what shape the crack has. When information is not sufficiently shared and visualized, decisions about necessary repairs may be delayed or overlooked. Investigations of actual infrastructure accidents have pointed out cases where warning signs existed but insufficient records prevented appropriate measures.

On the other hand, improving “recordability” means leaving inspection results in sufficient detail so that anyone can reproduce them later. With clear records, comparing the same location five or ten years later becomes easy, enabling quantitative assessment of deterioration progress. If recordability is poor, knowledge from past inspections may not be transferred when personnel change, and valuable inspection insights can be lost.

Incorporating digital technologies into non-destructive inspection can dramatically enhance both this “visualization” and “recordability.” Specifically, two pillars are central to inspection DX: intuitive onsite visualization through AR (augmented reality) and precise digital recording using 3D point cloud data. The next sections examine the benefits each technology brings to the field.

Intuitive Inspection Support and Construction History Visualization with AR

AR (augmented reality) is a technology that overlays digital information on real-world imagery via a smartphone, tablet, or AR glasses. Deploying AR in non-destructive inspection makes inspection work far more intuitive and easy to understand.

For example, what if past inspection records could be overlaid on site via AR during a bridge inspection? Displaying the positions of previously detected cracks and repair histories like holograms on the actual structure eliminates the hassle of flipping through paper records and saying, “I think the crack was around here.” If previous damage locations are highlighted in AR, inspectors can instantly identify the points to check by following the camera view. At the same time, inspectors can compare the real object and digital records in real time to determine whether “the crack has widened since the last inspection,” preventing missed progression of deterioration.

AR is not limited to comparing past data; it can also be applied to work navigation. For example, inspection checklist items can be displayed in sequence in AR space according to the procedure manual, with arrows or markings indicating the next target to inspect. Following a digital guide allows newcomers to perform inspections thoroughly and reliably without relying on veteran intuition or experience. For large structures like bridges, AR can also be used to overlay as-built drawings or design information to check the “intended position and shape” against the current state. In structures containing internal cables or pipes, displaying the layout from drawings in AR makes it possible to visually understand what is behind a wall before conducting appropriate non-destructive tests (such as flaw detection), helping avoid unnecessary openings or excavations.

In this way, AR supports fieldwork in a way that aligns with human senses. Its greatest advantage for inspectors is that they can immediately obtain information onsite. Without spreading paper forms or carrying large drawings, necessary data appears in the surrounding space, greatly improving inspection efficiency and accuracy. As not only tablets but wearable devices like AR glasses become more common, inspectors will be able to have necessary information displayed in their field of view while keeping both hands free, further enhancing safety and efficiency.

Refining Defect Detection and Record Accuracy with 3D Point Cloud Data to Improve Reproducibility

The other major pillar is the method of recording and analyzing structures’ shapes in detail as 3D point cloud data. Point cloud data represent the surfaces of structures or terrain as a collection of countless points (a set of coordinates). Recently, with the spread of laser scanners, photogrammetry, and LiDAR-equipped smart devices, high-precision 3D scans can be readily performed onsite to acquire point cloud data.

Leveraging 3D point clouds dramatically improves the precision of defect detection and recording in non-destructive inspections. For example, analyzing point clouds obtained by scanning a tunnel inner wall can reveal subtle deformations and surface irregularities that visual inspection might miss. The width of cracks and the area of detached regions can be measured accurately on point clouds. Dimensions that were previously measured with scales or crack gauges can be quantified digitally down to the millimeter, reducing human measurement error.

Moreover, point cloud data dramatically enhance the reproducibility of inspection records. Once a point cloud is saved, comparing it with point clouds acquired five or ten years later allows changes to be captured as objective numerical values. For example, you can visualize deterioration progress such as “a displacement of XX mm compared to Y years ago” or “an increase in the area of loss.” While photo records vary in shooting angle and distance and are difficult to compare rigorously, point cloud data record the entire space, making it easy to later analyze differences at the same section.

There are many other advantages of point cloud data. Representative benefits include:

• Intuitive 3D visualization: Point clouds can be displayed in three dimensions as if the structure were copied whole, allowing immediate understanding of depth and shape. Information that is hard to convey in drawings or photos can be easily shared with clients and stakeholders in 3D.

• High-precision measurement: Distances between arbitrary points, areas of loss, and volumes can be measured freely, more accurately than manual methods and with fewer human errors. Advanced evaluations, such as calculating detached concrete volume from point cloud volumes, are possible.

• Comprehensive information coverage: Point cloud measurement records all locations on site without omission, eliminating worries like “I forgot to measure that area.” It functions as a digital archive for later additional analysis or secondary use as needed.

Against this backdrop, 3D point cloud technology is increasingly expected to be a core innovation for infrastructure maintenance in construction DX initiatives promoted by the Ministry of Land, Infrastructure, Transport and Tourism, such as *i-Construction*. In the non-destructive inspection field, research and demonstrations of crack detection using 3D point clouds combined with AI, automatic deformation analysis, and other applications are progressing. In the near future, parts of inspection work that once relied on human eyes and hands may be automated on digital twins.

Streamlining the Inspection Process with Cloud Integration and Remote Assistance

Digital data acquired via AR and 3D point clouds can be further leveraged by cloud integration. Centralizing inspection data in the cloud makes it possible to understand site conditions from the office and enables remote assistance, where multiple personnel can view and analyze data simultaneously.

For example, if high-resolution point cloud data or photos captured onsite are uploaded to the cloud immediately, supervisors or specialists in remote locations can review them instantly. Field personnel can continue inspections with real-time advice to avoid oversights, and in difficult judgment cases they can consult veterans on the spot. Processes that previously required “take it back and consult later” and took several days can now be completed the same day thanks to cloud-based information sharing.

Cloud-based inspection data management systems allow viewing 3D point cloud models and photos via a web browser without installing dedicated software, adding annotations, and organizing information. Because everyone can access the latest data, discrepancies such as “the field was looking at a new drawing while the office was working from an old version” are avoided. In infrastructure inspection, where road administrators, municipal owners of bridges, inspection contractors, and construction consultants are involved, aggregating data and insights in the cloud has great value.

A rapidly growing need is for remote on-site presence, or remote inspection support. If inspections or guidance can be conducted from the office based on site video and data, it helps address labor shortages and reduce costs. For example, sharing the real-time footage from a camera worn by an inspector and having a remote expert annotate or instruct on that footage—the practical use of AR remote support—has been advancing. This enables less experienced technicians to work under constant veteran support, making knowledge sharing across regions and generations a reality. The Ministry of Land, Infrastructure, Transport and Tourism has also actively promoted remote technologies for infrastructure inspections, starting trials of remote close-range visual inspection for bridge inspections in 2021, and regulatory frameworks are supporting DX. Widespread implementation of remote on-site presence could enable uniform inspection quality nationwide, regardless of geographic conditions.

Combining cloud integration and remote assistance can thus be expected to improve and sophisticate the entire inspection process. Data collection → analysis → reporting can be carried out seamlessly without spatial or temporal constraints, allowing limited human resources to maintain and manage more infrastructure appropriately.

LRTK Features and Use Cases in Non-Destructive Inspection (Back Sides of Structures, Heights, Complex Shapes, etc.)

An accessible solution that makes such DX technologies practicable onsite is our LRTK. LRTK is an integrated platform that combines high-precision RTK-GNSS positioning technology with smartphone-based 3D scanning and AR functions, enabling anyone to easily perform point cloud measurement with absolute coordinates and AR display. By linking a dedicated positioning device with a smartphone, users can walk the site as if filming a video to three-dimensionally scan wide areas of structures and create digital records. The acquired point clouds have absolute coordinates based on the standards of the Geospatial Information Authority of Japan, making them reliable data with high positional accuracy. It is easy to accurately align and compare datasets acquired in multiple inspections or to overlay them with design drawings or CIM models.

LRTK demonstrates strong performance in various non-destructive inspection scenarios. For example, inspections of the backsides of structures or narrow areas that are normally difficult to approach can be performed simply by pointing a camera from a safe location to acquire 3D point clouds of the target. For areas at heights where people cannot enter, photogrammetric analysis of zoomed images taken from the ground can generate 3D models that allow later detailed measurements. In addition, by aligning a crosshair on the smartphone screen and pressing the shutter, users can remotely measure coordinates of distant objects. This subject positioning capability makes it easy to record the coordinates of a crack located 6 m high from the ground. Inspections that previously required aerial work platforms or scaffolding can be performed with LRTK while significantly reducing manpower, time, and cost and improving safety. LRTK also integrates with drones and 360-degree cameras, enabling inspections of areas such as bridge undersides and dam crests that are inaccessible to personnel.

LRTK is also effective for inspecting structures with complex shapes. It can scan curved or intricate steel structures from every angle to capture accurate point cloud data, digitally recording the entire structure including blind spots that visual inspection might miss. Point clouds captured onsite can be immediately reviewed in a cloud 3D viewer, and distance or area measurements and cross-section creation are available with one touch. The ability to record wide areas in a short time is another notable feature. For example, in slope inspections in mountainous areas, LRTK can scan slopes over 100 m in as little as about one minute, recording surface irregularities and displacements in detail. Areas that would take a full day to cover manually can be efficiently captured digitally. Even rivet arrangements or weld shapes on steel bridges can be observed in detail on point clouds, aiding early detection of deterioration signs.

LRTK is already being trialed in various sites such as bridge and tunnel periodic inspections and plant equipment maintenance, contributing to labor savings and advanced inspection processes. The operation is simple and designed so that technicians unfamiliar with the equipment can master it after a short briefing. This helps address the problem of skill transfer caused by retiring veterans and labor shortages, allowing organizations to maintain stable inspection quality.

Conclusion

The world of non-destructive inspection that supports infrastructure safety is now entering a revolutionary turning point. With the introduction of digital technologies such as AR, 3D point clouds, and the cloud, inspection work that once depended heavily on people is shifting to objective, data-driven processes. This structural inspection DX is essential for efficiently and reliably maintaining aging social infrastructure. Digitalization not only improves inspection efficiency but also enables the use of collected big data to develop preventive and predictive maintenance, reducing long-term maintenance costs and mitigating risks. Promoting DX is not merely labor-saving but a shift toward smart management that views the infrastructure life cycle holistically. With data-driven prioritization of repairs and renewals, unnecessary work can be reduced and limited budgets used more effectively. DX is expected to be a key to achieving both cost reduction and enhanced safety.

In this context, LRTK has emerged as a reliable partner to embed non-destructive inspection DX onsite. Its ease and precision—enabling simple surveying and detailed recording with a smartphone—have the potential to overturn conventional practices in inspection sites. By eliminating subjectivity, standardizing records, and ensuring reproducibility, LRTK contributes to solving all the issues discussed in this article and is expected to raise the quality of infrastructure inspection. Such advanced technologies will also be a major aid in skills transfer and addressing manpower shortages in the field.

The digital revolution in non-destructive inspection has only just begun. As technologies advance further, new developments such as AI-driven automatic analysis and robot-based inspections will likely emerge. To maximize the benefits of DX, however, the starting point is accurate onsite data acquisition and sharing. Take this opportunity to step into smart inspection using LRTK and get ahead in future infrastructure maintenance management.