Pang‐jo Chun 교수

Automated crack detection based on image processing is widely used when inspecting concrete structures. The existing methods for crack detection are not yet accurate enough due to the difficulty and complexity of the problem; thus, more accurate and practical methods should be developed. This paper proposes an automated crack detection method based on image processing using the light gradient boosting machine (LightGBM), one of the supervised machine learning methods. In supervised machine learn

Photographs of bridges can reveal considerable technical information such as the part of the structure that is damaged and the type of damage. Maintenance and inspection engineers can benefit greatly from a technology that can automatically extract and express such information in readable sentences. This is possibly the first study on developing a deep learning model that can generate sentences describing the damage condition of a bridge from images through an image captioning method. Our study

The deterioration of bridges as a result of ageing is a serious problem in many countries. To prevent the failure of these deficient bridges, early damage detection which helps us to evaluate the safety of bridges is important. Therefore, the present research proposed a method to quantify damage severity by use of multipoint acceleration measurement and artificial neural networks. In addition to developing the method, we developed a cheap and easy-to-make measurement device which can be made by

Machine learning models have been developed to perform damage detection using images to improve bridge inspection efficiency. However, in damage detection using images alone, the 3D coordinates of the damage cannot be recorded. Furthermore, the accuracy of the detection depends on the quality of the images. This paper proposes a method to integrate and record the damage detected from multiple images into a 3D model using deep learning to detect the damage from bridge images and structure from mo

The crack ratio is one of the indices used to quantitatively evaluate the soundness of asphalt pavement. However, since the inspection of pavement requires much labor and cost, automatic inspection of pavement damage by image analysis is required in order to reduce the burden of such work. In this study, a system was constructed that automatically detects and evaluates cracks from images of pavement using a convolutional neural network, a kind of deep learning. The most novel aspect of this stud

This study proposes a novel self-training framework for unsupervised domain adaptation in the segmentation of concrete wall cracks using accumulated crack data. The proposed method incorporates Bayesian neural networks for uncertainty estimation of pseudo-labels, and spatial priors of cracks for screening noisy labels. Experiments demonstrate that the proposed approach achieves significant improvements in F1 score. Comparing the F1 scores, Bayesian DeepLabv3+ and Bayesian U-Net showed performanc

High-resolution (HR) crack images offer more detailed information for assessing structural conditions compared to low-resolution (LR) images. This wealth of detail proves indispensable in bolstering the safety of unmanned aerial vehicle (UAV)-based inspection procedures and elevating the precision of small crack segmentation. Nonetheless, achieving a balance between segmentation accuracy and GPU memory consumption poses a substantial challenge for deep learning models when processing HR crack im

In recent years, aging of bridges has become a growing concern, and the danger of bridge collapse is increasing. To appropriately maintain bridges, it is necessary to perform inspections to accurately understand their current state. Until now, bridge inspections have involved a visual inspection in which inspection personnel come close to the bridges to perform inspection and hammering tests to investigate abnormal noises by hammering the bridges with an inspection hammer. Meanwhile, as there ar

To conduct safety checks of corroded steel structures and formulate appropriate maintenance strategies, the residual strength of steel structural members must be assessed with high accuracy. Finite element method (FEM) analyses that precisely recreate the morphology of corroded surfaces using solid elements are expected to accurately assess the strength; however, the cost of conducting these calculations is extremely high. Therefore, a model that uses mean thickness as the thickness of the shell

It is necessary to assess damage properly for the safe use of a structure and for the development of an appropriate maintenance strategy. Although many efforts have been made to measure the vibration of a structure to determine the degree of damage, the accuracy of evaluation is not high enough, so it is difficult to say that a damage evaluation based on vibrations in a structure has not been put to practical use. In this study, we propose a method to evaluate damage by measuring the acceleratio

• In this study, an AI that outputs explanatory texts about bridge damage from bridge photography images was realized by combining CNN and LSTM, making it easier to understand bridge damage. • This study also developed a web system that makes the above system usable in practical applications. • Additionally, a mechanism has been implemented in the web system that increases data and enhances the AI's intelligence the more it is utilized, and it was confirmed that the accuracy improves as the amou

アスファルト舗装のひび割れ損傷を定量的に評価する指標としてひび割れ率が定められている．このひび割れ率の算出にあたっては路面のひび割れをスケッチした後に区画内のひび割れの本数を数える必要があるが，手作業となるため膨大な労力と時間が必要となり，さらにはひび割れ開口幅などの重要な情報を得ることができないという問題がある．そこで本研究ではナイーブベイズ法による機械学習と画像解析を組み合わせ，撮影画像からひび割れを自動的に検出する手法を構築した．本手法は画素単位でひび割れを検出できるため，上述のひび割れ開口幅や面積などについても計算が容易である．そして本手法を複数箇所の密粒度アスファルトおよびポーラスアスファルト舗装の路面から撮影された画像に適用した実験により，本手法の高いひび割れ検出性能を確認した．

アスファルト舗装の健全度を定量的に評価する指標の1つにひび割れ率がある．しかし舗装の点検は労力面，コスト面の負担が大きく，そういった負担を軽減するための新技術が求められている状況にある．そういった新技術の一環として，画像解析によりひび割れの自動検出を目指した研究は国内外に多くある．しかしマンホールや白線などが撮影画像に写っていると誤認識の要因となってしまうなど，精度面に課題を抱えていた．そこで本研究ではディープラーニングの一種であるCNNを用いて，白線やマンホールを区別した上で舗装の撮影画像からひび割れを自動的に検出，評価し，GIS上で可視化するシステムを構築した．そして実際に車両から撮影した画像に本手法を適用した実験により，高いひび割れ評価性能を確認した．

近年，橋梁やトンネルなどの損傷状態の把握を目的として近接目視点検が行われている．各種点検要領では様々な項目を点検するように定められているが，その中でもコンクリート構造物のひび割れは劣化の進行速度に大きな影響を与えるため，そのひび割れ幅や位置，長さを記録するように定められている．しかし点検に伴う膨大な作業量，コストが問題となっており，また，点検員によって判定がばらつくという主観性の問題もある．これらの解決のため，撮影画像からひび割れを自動検出するという研究が様々な機関において行われているが，現状ではこれらの手法が完成しているとは言い難い．そこで本研究では，画像解析にRandom Forestによる機械学習を組み合わせたひび割れ検出手法を構築した．また，実際の撮影画像を用いた実験の結果，高い精度であることを確認した．

Deterioration of the concrete deck surface, including disintegration and delamination between the deck slab and pavement, presents significant challenges in bridge maintenance due to its hidden nature and the risk it poses to the deck's durability as damage progresses. Early detection is critical for preventing issues such as pothole formation and ensuring long-term durability. However, traditional methods require core sampling, which often delays detection until damage is extensive. This study