• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.351-363
• /
• 2023

Visual structural inspections are an inseparable part of post-earthquake damage assessments. With unmanned aerial vehicles (UAVs) establishing a new frontier in visual inspections, there are major computational challenges in processing the collected massive amounts of high-resolution visual data. We propose twin deep learning models that can provide accurate high-resolution structural components and damage segmentation masks efficiently. The traditional approach to cope with high memory computational demands is to either uniformly downsample the raw images at the price of losing fine local details or cropping smaller parts of the images leading to a loss of global contextual information. Therefore, our twin models comprising Trainable Resizing for high-resolution Segmentation Network (TRS-Net) and DmgFormer approaches the global and local semantics from different perspectives. TRS-Net is a compound, high-resolution segmentation architecture equipped with learnable downsampler and upsampler modules to minimize information loss for optimal performance and efficiency. DmgFormer utilizes a transformer backbone and a convolutional decoder head with skip connections on a grid of crops aiming for high precision learning without downsizing. An augmented inference technique is used to boost performance further and reduce the possible loss of context due to grid cropping. Comprehensive experiments have been performed on the 3D physics-based graphics models (PBGMs) synthetic environments in the QuakeCity dataset. The proposed framework is evaluated using several metrics on three segmentation tasks: component type, component damage state, and global damage (crack, rebar, spalling). The models were developed as part of the 2^nd International Competition for Structural Health Monitoring.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2003.11a
• /
• pp.602-607
• /
• 2003

Sensors based bridge monitoring system (SBBMS) is designed to perform real-time monitoring and to store the performance history of in-service bridges. In general, visual inspections play a major role in maintenance of in-service bridges; however, they are not adequate to document the behavior of a bridge. Therefore, visual inspections and sensor based monitoring systems complement each other. Sensor based bridge monitoring systems consist of hardware and software systems. The hardware system contains the sensors and data-loggers to measure the behavior of a structure, the communicational equipment to transmit the measured data from the site to the monitoring center, and the computers to arrange and analyze the data. The software system controls data-loggers, arranges and analyzes the measured data, makes real-time display, stores the performance history.

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.5
• /
• pp.811-816
• /
• 2022

Even though continuous management and supervision of reinforcement of policies to safeguard accidents at workplace and work sites were implemented. Accident prevention activities such as inspection and diagnosis are urgently required to induce a preliminary investigation to identify the risk factors for each type of work, before the work task to eliminate risks at the worksites. Since safety inspections at work sites were generally conducted through visual inspections, the results of safety inspections may vary depending on the findings and proficiency of the safety officers. The results of those inspections may have loopholes to prevent potential accidents at work. Therefore, the purpose of this study was to develop a risk identification checklist that can effectively perform safety inspections to prevent accidents at work sites. This study initially analyzed the previously developed accident checklist to identify current complications and issues in safety checklists. Based on the findings of major industrial accidents over the past three years, the relationship between accident, workplace, and work type were analyzed refereeing the safety inspection standards. A risk recognition-checklist was developed to provide basic data on identifying risk factors, and inspection guidance at work sites. To prepare for potential accidents by identifying and taking countermeasures to mitigate the high risk and serious accidents at sites by the guidelines of the checklist. The developed inspection checklist has been practically used by experts at work sites to perform safety inspections, and it has been verified its suitability, and feasibility, to prevent or mitigate workplace accidents, including securing the safety and health of field workers. The role of the developed safety checklist has been considered effective at worksites.

• International Journal of Advanced Culture Technology
• /
• v.11 no.1
• /
• pp.389-394
• /
• 2023

Based on intelligent visual information and 5G, this paper studies the intelligent visual communication of landscape bamboo buildings, and provides a new method of intelligent perception and interactive computing for the real world, which can represent, model, Perception and cognition; through the integration of virtual and real, the situational understanding of the human-machine-material fusion environment and the interaction with nature. The 5G network can well meet the combination of high-bandwidth uplink transmission and low-latency downlink control. At the same time, 5G-based AR intelligent inspection, remote operation and maintenance guidance, and machine vision inspection. Taking the bamboo building as an example, through field inspections to analyze tourism Bamboo buildings before and after development, and the intelligentization of bamboo buildings based on 5G and visual modeling.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.16 no.4
• /
• pp.25-33
• /
• 2012

In electric power transmission tower structures on offshore, implementation of life management using the event data of regular safety inspections for structural and material damages is strongly recommended. In this study, six tower structures in Sihwa Lake around Yeoungheung island were target bodies for the safety inspections. safety inspections for deterioration about each of six towers were performed about three items for steel member, five items for concrete foundation, and four items for steel-pipe pile in seawater and seawater itself. Safety inspections for steel members included the visual observations of surface appearances, the measurements of member thicknesses, and the checks of painting states. Also safety inspections for concrete foundations comprised the estimation of crack features, the evaluation of non-destructive compression strengths, and the measurements of neutralization depths and chlorides contents. For steel-pipe piles in seawater the inspections comprised the surveys of corrosion states in accordance with potential levels tests and anode tests, the analyses of photos taken on surfaces of the piles as well as the evaluation of seawater quality. A set of deterioration inspections was performed at the same positions around october of each year for three consecutive years. As a result in this study, Newly developed deterioration indexes have been applied profitably to maintain structural safety for electric power transmission towers by utilizing these event data systematically.

• Structural Monitoring and Maintenance
• /
• v.2 no.3
• /
• pp.283-300
• /
• 2015

Visual condition inspections remain paramount to assessing the current deterioration status of a bridge and assigning remediation or maintenance tasks so as to ensure the ongoing serviceability of the structure. However, in recent years, there has been an increasing backlog of maintenance activities. Existing research reveals that this is attributable to the labour-intensive, subjective and disruptive nature of the current bridge inspection method. Current processes ultimately require lane closures, traffic guidance schemes and inspection equipment. This not only increases the whole-of-life costs of the bridge, but also increases the risk to the travelling public as issues affecting the structural integrity may go unaddressed. As a tool for bridge condition inspections, Unmanned Aerial Vehicles (UAVs) or, drones, offer considerable potential, allowing a bridge to be visually assessed without the need for inspectors to walk across the deck or utilise under-bridge inspection units. With current inspection processes placing additional strain on the existing bridge maintenance resources, the technology has the potential to significantly reduce the overall inspection costs and disruption caused to the travelling public. In addition to this, the use of automated aerial image capture enables engineers to better understand a situation through the 3D spatial context offered by UAV systems. However, the use of UAV for bridge inspection involves a number of critical issues to be resolved, including stability and accuracy of control, and safety to people. SLAM (Simultaneous Localisation and Mapping) is a technique that could be used by a UAV to build a map of the bridge underneath, while simultaneously determining its location on the constructed map. While there are considerable economic and risk-related benefits created through introducing entirely new ways of inspecting bridges and visualising information, there also remain hindrances to the wider deployment of UAVs. This study is to provide a context for use of UAVs for conducting visual bridge inspections, in addition to addressing the obstacles that are required to be overcome in order for the technology to be integrated into current practice.

• Journal of Sensor Science and Technology
• /
• v.32 no.3
• /
• pp.187-193
• /
• 2023

Previous research has explored early expression of fire signs before the burning of insulation. To achieve this, typically, automatic inspections are used to detect gas emitted from odor capsules at electrical connection points; additionally, early fire signs can be expressed using visual inspection of changes in the appearance of temperature caps. However, early detection of electrical fire is often difficult because only specific inspections, which are not complex, are performed. Therefore, in this paper, we present complex inspection techniques, such as visual inspection, odor inspection, and automatic inspection, and propose a showing material of fire signs that can solve conventional problems. In addition, this study examines the conditions under which the candidate material for the showing material is designed, the composition of the candidate material selected based on the designed conditions, the manufacturing means used to produce the showing material considering the temperature for early expression of fire signs, and the performance of the produced showing material. Furthermore, we analyze various effects that can occur through the proposed display material.

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.4_2
• /
• pp.573-586
• /
• 2022

Corrosion can cause dangerous and expensive damage and failures of ship hulls and equipment. Therefore, it is necessary to maintain the vessel by periodic corrosion inspections. During visual inspection, many corrosion locations are inaccessible for many reasons, especially safety's point of view. Including subjective decisions of inspectors is one of the issues of visual inspection. Automation of visual inspection is tried by many pieces of research. In this study, we propose image preprocessing methods by image patch segmentation and thresholding. YOLOv5 was used as an object detection model after the image preprocessing. Finally, it was evaluated that corrosion detection performance using the proposed method was improved in terms of mean average precision.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.25 no.6
• /
• pp.569-582
• /
• 2023

In recent years, the service life of major SOC facilities in south korea has exceeded 30 years, and rapid aging is expected within the next 10 years. This has led to a growing recognition of the need for proactive maintenance of these facilities. Consequently, there have been numerous research efforts to introduce smart inspection technologies into maintenance. However, the current system relies primarily on manpower for safety inspections and diagnostics, and on-site surveys rely on visual inspections. Manpower inspections can be time-consuming, and subjective errors may occur during result analysis. In the case of tunnels, there are disadvantages, such as the loss of social overhead capital due to partial closures during inspections. Therefore, institutionalizing smart safety inspections is essential, considering specific measures like using advanced equipment and updating qualifications for experts. Furthermore, it is necessary to verify and validate safety inspection results using advanced equipment before instituting changes. This could be achieved through national-level official research programs and the operation of verification and validation institutions. If smart inspection technology is introduced into maintenance, routine inspections of SOC facilities, such as tunnels, will become feasible. As a result, maintenance technology capable of early detection and proactive response to safety incidents caused by changes in facility conditions is anticipated.

• Journal of Construction Engineering and Project Management
• /
• v.5 no.4
• /
• pp.16-22
• /
• 2015

This paper presents an automated computer vision-based system to update BIM data by leveraging multi-modal visual data collected from existing buildings under inspection. Currently, visual inspections are conducted for building envelopes or mechanical systems, and auditors analyze energy-related contextual information to examine if their performance is maintained as expected by the design. By translating 3D surface thermal profiles into energy performance metrics such as actual R-values at point-level and by mapping such properties to the associated BIM elements using XML Document Object Model (DOM), the proposed method shortens the energy performance modeling gap between the architectural information in the as-designed BIM and the as-is building condition, which improve the reliability of building energy analysis. Several case studies were conducted to experimentally evaluate their impact on BIM-based energy analysis to calculate energy load. The experimental results on existing buildings show that (1) the point-level thermography-based thermal resistance measurement can be automatically matched with the associated BIM elements; and (2) their corresponding thermal properties are automatically updated in gbXML schema. This paper provides practitioners with insight to uncover the fundamentals of how multi-modal visual data can be used to improve the accuracy of building energy modeling for retrofit analysis. Open research challenges and lessons learned from real-world case studies are discussed in detail.