• Journal of the Korea institute for structural maintenance and inspection
• /
• v.25 no.4
• /
• pp.65-74
• /
• 2021

In order to efficiently inspect rapidly increasing old tunnels in many well-developed countries, many inspection methodologies have been proposed using imaging equipment and image processing. However, most of the existing methodologies evaluated their performance on a clean concrete surface with a limited area where other objects do not exist. Therefore, this paper proposes a 6-step framework for tunnel crack detection deep learning model development. The proposed method is mainly based on negative sample (non-crack object) training and Cascade Mask R-CNN. The proposed framework consists of six steps: searching for cracks in images captured from real tunnels, labeling cracks in pixel level, training a deep learning model, collecting non-crack objects, retraining the deep learning model with the collected non-crack objects, and constructing final training dataset. To implement the proposed framework, Cascade Mask R-CNN, an instance segmentation model, was trained with 1561 general crack images and 206 non-crack images. In order to examine the applicability of the trained model to the real-world tunnel crack detection, field testing is conducted on tunnel spans with a length of about 200m where electric wires and lights are prevalent. In the experimental result, the trained model showed 99% precision and 92% recall, which shows the excellent field applicability of the proposed framework.

• Journal of the Korean Society for Railway
• /
• v.20 no.3
• /
• pp.374-381
• /
• 2017

Concrete sleepers, installed on majority of railroad track in this nation can, if not maintained properly, threaten the safety of running trains. In this paper, an algorithm for automatically identifying cracks in a sleeper image, taken by high-resolution camera, is developed based on Adaboost, known as the strongest adaptive algorithm and most actively utilized algorithm of current days. The developed algorithm is trained using crack characteristics drawn from the analysis results of crack and non-crack images of field-installed sleepers. The applicability of the developed algorithm is verified using 48 images utilized in the training process and 11 images not used in the process. The verification results show that cracks in all the sleeper images can be successfully identified with an identification rate greater than 90%, and that the developed automatic crack identification algorithm therefore has sufficient applicability.

• Journal of the Korea Concrete Institute
• /
• v.17 no.3 s.87
• /
• pp.369-374
• /
• 2005

This study proposes a technique for the recognition of crack patterns, which includes horizontal, vertical, diagonal($-45^{\circ}$), diagonal($+45^{\circ}$), and random cracks, based on image processing technique and artificial neural network. A MATLAB code was developed for the proposed image processing algorithm and artificial neural network. Features were determined using total projection technique, and the structure(no. of layers and hidden neurons) and weight of artificial neural network were determined by learning from artificial crack images. In this process, we adopted Bayesian regularization technique as a generalization method to eliminate overfitting Problem. Numerical tests were performed on thirty-eight crack images to examine validity of the algorithm. Within the limited tests in the present study, the proposed algorithm was revealed as accurately recognizing the crack patterns when compared to those classified by a human expert.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.10
• /
• pp.35-42
• /
• 2020

In this study, we propose a crack detection method using limited data with a U-Net based image inpainting technique that is a modified unsupervised anomaly detection method. Concrete cracking occurs due to a variety of causes and is a factor that can cause serious damage to the structure in the long term. In general, crack investigation uses an inspector's visual inspection on the concrete surfaces, which is less objective in judgment and has a high possibility of human error. Therefore, a method with objective and accurate image analysis processing is required. In recent years, the methods using deep learning have been studied to detect cracks quickly and accurately. However, when the amount of crack data on the building or infrastructure to be inspected is small, existing crack detection models using it often show a limited performance. Therefore, in this study, an unsupervised anomaly detection method was used to augment the data on the object to be inspected, and as a result of learning using the data, we confirmed the performance of 98.78% of accuracy and 82.67% of harmonic average (F1_Score).

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.27 no.5
• /
• pp.113-119
• /
• 2023

Most infrastructure structures were completed during periods of economic growth. The number of infrastructure structures reaching their lifespan is increasing, and the proportion of old structures is gradually increasing. The functions and performance of these structures at the time of design may deteriorate and may even lead to safety accidents. To prevent this repercussion, accurate inspection and appropriate repair are requisite. To this end, demand is increasing for computer vision and deep learning technology to accurately detect even minute cracks. However, deep learning algorithms require a large number of training data. In particular, label images indicating the location of cracks in the image are required. To secure a large number of those label images, a lot of labor and time are consumed. To reduce these costs as well as increase detection accuracy, this study proposed a learning structure based on mean teacher method. This learning structure was trained on a dataset of 900 labeled image dataset and 3000 unlabeled image dataset. The crack detection network model was evaluated on over 300 labeled image dataset, and the detection accuracy recorded a mean intersection over union of 89.23% and an F1 score of 89.12%. Through this experiment, it was confirmed that detection performance was improved compared to supervised learning. It is expected that this proposed method will be used in the future to reduce the cost required to secure label images.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.53-56
• /
• 2021

국내 산업화가 들어선 후 산업화 당시 지었던 낙후된 건물의 증가에 따라 구조물의 손상 조사 및 검사 방법의 수요가 늘어나고 있다. 일반적으로 구조물의 손상은 전문 검사원이 현장에서 직접 측량도구와 시각적인 방식으로 검사한다. 그러나 전문 검사원들이 직접 조사하는 수고에 비해 균열을 검사하는 방식 자체가 단순하고, 일반 사람이 검사하기에는 객관성이 떨어지는 한계가 있어 균열을 자동적으로 검출함으로써 객관성과 편의성을 보장할 기술이 필요하다. 본 연구에서는 이미지 기반으로 다양한 환경에서의 외벽 균열을 검출할 수 있는 딥러닝 모델 개발을 소개한다. 균열 검출을 위해 다양한 외벽 균열 관련 데이터셋을 확보 및 구축하고 각 데이터셋의 검출 정보를 보완할 반자동(semi-auto) 라벨링 작업을 수행하였다. 두 번째로 기존 높은 검출 성능을 보였던 모델들을 선정 및 비교하여 YOLO v5 모델을 최종적으로 선정하였고, 도메인이 각각 다른 데이터셋에 대한 교차 학습을 통해 각 데이터셋의 mAP의 편차가 31%에서 11%로 좁히는 작업을 수행하였다. 이를 통해 실제 상황에서의 균열 영상에서 균열을 검출할 수 있는 측량 시스템을 개발함으로써 실질적인 검사의 도구로 활용될 수 있길 기대한다.

• Journal of the Korean Geotechnical Society
• /
• v.40 no.4
• /
• pp.137-144
• /
• 2024

The purpose of this paper is to analyze the significance of independent variables in estimating crack density using machine learning algorithms. The algorithms used were random forest and SHAP, with the independent variables being compressional wave velocity, shear wave velocity, porosity, and Poisson's ratio. Rock samples were collected from construction sites and processed into cylindrical forms to facilitate the acquisition of each input property. Artificial weathering was conducted twelve times to obtain values for both independent and dependent variables with multiple features. The application of the two algorithms revealed that porosity is a crucial independent variable in estimating crack density, whereas shear wave velocity has a relatively low impact. These results suggested that the four physical properties set as independent variables were sufficient for estimating crack density. Additionally, they presented a methodology for verifying the appropriateness of the independent variables using algorithms such as random forest and SHAP.

• Tunnel and Underground Space
• /
• v.31 no.5
• /
• pp.374-384
• /
• 2021

In this study, we propose a new approach for automatic fracture detection in CT scan images of rock specimens. This approach is built on top of two-stage object detection deep learning algorithm called Faster R-CNN with a major modification of using rotated bounding box. The use of rotated bounding box plays a key role in the future work to overcome several inherent difficulties of fracture segmentation relating to the heterogeneity of uninterested background (i.e., minerals) and the variation in size and shape of fracture. Comparing to the commonly used bounding box (i.e., axis-align bounding box), rotated bounding box shows a greater adaptability to fit with the elongated shape of fracture, such that minimizing the ratio of background within the bounding box. Besides, an additional benefit of rotated bounding box is that it can provide relative information on the orientation and length of fracture without the further segmentation and measurement step. To validate the applicability of the proposed approach, we train and test our approach with a number of CT image sets of fractured granite specimens with highly heterogeneous background and other rocks such as sandstone and shale. The result demonstrates that our approach can lead to the encouraging results on fracture detection with the mean average precision (mAP) up to 0.89 and also outperform the conventional approach in terms of background-to-object ratio within the bounding box.

• Journal of Korean Society of Steel Construction
• /
• v.19 no.6
• /
• pp.695-702
• /
• 2007

The Thermal Prestressing Method for continuous composite girder bridges is a new design and construction method developed to induce initial composite stresses in the concrete slab at negative bending regions. Due to the induced initial stresses, prevention of tensile cracks at the concrete slab, reduction of steel girder section, and reduction of reinforcing bars are possible. Thus, the construction efficiency can be improved and the construction can be made more economical. The method for determining the optimum heating region of the thermal prestressing method has not been established although such method is essential for improving the efficiency of the design process. The trial-and-error method used in previous studies is far from efficient, and a more rational method for computing optimal heating region is required. In this study, an efficient method for determining the optimum heating region in using the thermal prestressing method was developed based on the neural network algorithm, which is widely adopted to pattern recognition, optimization, diagnosis, and estimation problems in various fields. Back-propagation algorithm, commonly used as a learning algorithm in neural network problems, was used for the training of the neural network. Through case studies of two-span and three-span continuous composite girder bridges using the developed procedure, the optimal heating regions were obtained.

• Journal of the Korea Concrete Institute
• /
• v.22 no.1
• /
• pp.19-27
• /
• 2010

Aging and severe environments are major causes of damage in reinforced concrete (RC) structures such as buildings and bridges. Deterioration such as concrete cracks, corrosion of steel, and deformation of structural members can significantly degrade the structural performance and safety. Therefore, effective and easy-to-use methods are desired for repairing and strengthening such concrete structures. Various methods for strengthening and rehabilitation of RC structures have been developed in the past several decades. Recently, FRP composite materials have emerged as a cost-effective alternative to the conventional materials for repairing, strengthening, and retrofitting deteriorating/deficient concrete structures, by externally bonding FRP laminates to concrete structural members. The main purpose of this study is to investigate the effectiveness of adaptive neuro-fuzzy inference system (ANFIS) in predicting behavior of circular type concrete column retrofitted with FRP. To construct training and testing dataset, experiment results for the specimens which have different retrofit profile are used. Retrofit ratio, strength of existing concrete, thickness, number of layer, stiffness, ultimate strength of fiber and size of specimens are selected as input parameters to predict strength, strain, and stiffness of post-yielding modulus. These proposed ANFIS models show reliable increased accuracy in predicting constitutive properties of concrete retrofitted by FRP, compared to the constitutive models suggested by other researchers.