Crack detection

This paper proposes a thresholding approach for crack detection in an unmanned aerial vehicle (UAV) based infrastructure inspection system. The proposed algorithm performs recur-sively on the intensity histogram of UAV-taken images to exploit their crack-pixels appearing at the low intensity interval. A quantified criterion of interclass contrast is proposed and employed as an object cost and stop condition for the recursive process. Experiments on different datasets show that our algorithm outper-forms different segmentation approaches to accurately extract crack features of some commercial buildings.

The railway conveyance mainly depends on railway track. The railway track is the combination of several components, if there is any damage to any component of track it cause major accident. Most of the accidents in the railway conveyance are due to failure of materials and human error. To avoid this problem, we are using the crack detector model, In this project have come up with a solution for the same using this simple electrical and the mechanical technology we have sorted to automate the control from either side, The infra-red sensor mounted at reliable distance from the both side of the track for crack detection and metal detecting sensor are used for the detecting land mine under the track line accordingly controls the operation by solar power. Withal our robot is immaculate the track when it goes forward by remote command. This detecting system can be used to prevent the railway accidents.

Cracks are typical line structures that are of interest in many computer-vision applications. In practice, many cracks, e.g., pavement cracks, show poor continuity and low contrast, which brings great challenges to image-based crack detection by using low-level features. In this paper, we propose DeepCrack-an end-to-end trainable deep convolutional neural network for automatic crack detection by learning high-level features for crack representation. In this method, multi-scale deep con-volutional features learned at hierarchical convolutional stages are fused together to capture the line structures. More detailed representations are made in larger-scale feature maps and more holistic representations are made in smaller-scale feature maps. We build DeepCrack net on the encoder-decoder architecture of SegNet, and pairwisely fuse the convolutional features generated in the encoder network and in the decoder network at the same scale. We train DeepCrack net on one crack dataset and evaluate it on three others. The experimental results demonstrate that DeepCrack achieves F-Measure over 0.87 on the three challenging datasets in average and outperforms the current state-of-the-art methods.

This paper presents a methodology for automating the processingof highway pavement video images using an integration of artificial neural network models with conventional image-processing techniques. The methodology developed is able to classify pavement surface cracking by the type, severity, and extent of cracks detected in video images. The approach is divided into five major steps: (1) image segmentation, which involves reduction of a raw gray-scale pavement image into a binary image, (2) feature extraction, (3) decomposition of the image into tiles and identification of tiles with cracking, (4) integration of the results from step (3) and classification of the type of cracking in each image, and (5) computation of the severities and extents of cracking detected in each image. In this methodology, artificial neural network models are used in automatic thresholding of the images in stage (1) and in the classification stages (3) and (4). The results obtained in each stage of the process are presented and discussed in this paper. The research results demonstrate the feasibility of this new approach for the detection, classification, and quantification of highway pavement surface cracking.

Our book, ‘Researches on Urban and Architectural Design Studies’, consists of various studies produced in the fields of architecture and urban planning whose titles are given below:
·* Examination of Malatya Kernek Square and its Close Surroundings within the Context of the Conservation and Sustainability of the Culture-Space Relationship,
* Sustainable Disaster Management and Urban Transformation: The Case of Elazig Karsiyaka
* Crack Detection with Digital Image Processing,
* Reinforced Concrete Structural Design Failures Related to the Architecture of  ​Buildings: Lessons Learned From The January 24, 2020 Earthquake in Sivrice-Elazıg,
* Evaluation of Wind Velocity Ratio for Changing Aspect Ratios in Urban Areas,
* A Comparative Examination of Early Republic Period Primary School Structures in Anatolia with a Comparison Analysis by Space Syntax Method and Principle Suggestions for Their Conservation,
* Evaluation of Thermal Comfort Models and Energy-Saving Potential in an Office Space in Istanbul.·
* Parthenon: A Phenomenological Examination,
* The Contribution of Digital Technology and Modern Methods with Fundamental Approaches to the Conservation of Archeological, Architectural and Cultural Assets,
* The Theoretical Framework of Urban Morphology,
* Landscape Planning Criteria in Historical Environments,
* Determining the Effect of Facade Design in Buildings on Sunlight Reception and Lighting Energy Performance on the BEP-TR Regulation and BEP-BUY Program.

We would like to express our gratitude to the authors who made contributions with their genuine academic studies, to the reviewers who provided guidance for the perfection of the study, and to the staff of ‘ Livre de Lyon Publishing House’, the publisher of our book, for their considerable assistance during the printing phase.

We hope that this book, which addresses important issues in the fields of urban planning and architectural design, will be useful for the reader.
                                                  ​Assoc. Prof. Dr. Betül BEKTAŞ EKİCİ
                                                  ​Fırat University, Department of Architecture
                                                  ​Asst. Prof. Dr. Nihal Arda AKYILDIZ
                                                  ​Balıkesir University, Department of Architecture.

ABSTRACT: The general topic investigated in this thesis is “structural health monitoring”, with special care being devoted to damage detection and localization. The study is focused on methods which work in the space of the observed variables, where the global information measures can be used to detect the damage. In this context damage detection is demanded to global measures such as entropy or Lyapunov exponents. The comparison of these measures computed in subspaces of the observed variables or in their expansions, allows one to perform a sort of sensitivity analysis on the role of the variables involved in the problem.
Such global measures are able to detect but not to directly  localize damage. For this purpose, a new approach to detect and localize the damage is formulated and implemented. It exploits response surface techniques to approximate the relationship among the observed variables. Comparing the resulting models in different damaged and undamaged situations identifies the response differences and their causes.
The response surface procedure is described from its basic theoretical aspects up to the features of its numerical implementation. Additionally, the global measures introduced above drive the analyst in establishing whether or not the problem is well posed, i.e., whether or not the set of measured quantities are able to detect the specific damage to be localized.
The validation of the proposed methodology is first numerically pursued by applying it to the benchmark case set up by the Structural Health Monitoring Panel of the American Society of Civil Engineering (ASCE). The procedure is then tested on two different experimental situations. While the first study of a three-dimensional steel frame reproduces the features of the benchmark problem, the second investigation covers a monumental structure situation, where damage is represented by more or less extended cracks in the masonry. The potential expressed by the procedure also in this second application seems to promise interesting exploitation possibilities.

This paper presents crack detection in concrete structure based on fuzzy logic. Safety inspection of concrete structures is very important since it is closely related with the structural health and reliability. Automated structural health monitoring system becomes necessity in recent years that encourages various researches to be going on in this area. Cheap availability of digital cameras makes research work in this field easier. This paper presents digital image processing and fuzzy logic based efficient crack detection technique in concrete structure. Here features from digital image of concrete structure are extracted by using morphological image processing technique and then extracted features are fed to fuzzy logic to accurately identify the crack.

This paper describes the use of wavelet entropy as a feature extractor for robust classification of cracks in sewer pipe structures. Video image data was ac- quired using an infrared camera in an experimen- tal sewer pipe setup. Video frames were partitioned into 64 64 pixel sections. 1,885 'crack' and 1,675 'clean' (non-crack) sections were manually classified. Each section was

Crack in component if undetected may lead to catastrophic failure of the component. The
cracked rotor problem received the first attention in 1970 and after that the interest among the
researchers started. The vibration behavior of cracked structures, in particular cracked rotors, is
important to study as the introduction of the crack alters the vibration characteristics of the structure.
The problem of damage and crack detection in structural components has acquired important role in past
few years. However, cracked rotor studies are mainly deals with single crack. For multiple cracked
structures the problem of crack sizing and location becomes more complex. Only few authors have
pointed out the multiple crack assessment in the rotor. The proposed work is on vibration analysis of
multiple cracked shaft beam. An Euler Bernoulli beam fixed at one end with two transverse cracks is
considered. The vibration characteristics of the shaft are studied using Experimental Modal Analysis and
Finite Element Analysis. The mode shapes and natural frequencies of the beams are studied and their
variation with change in position and depth of the crack is also studied. The study shows good agreement
of the results obtained using Finite Element Analysis and Experimental Modal Analysis.

A new technique for crack detection in beam structures based on kurtosis is presented. The fundamental vibration mode of the cracked cantilever beam is analyzed and both the location and size of the crack are estimated. The location of the crack is determined by the abrupt changes in the spatial variation of the analyzed response, while the size of the crack is related to the estimate of kurtosis. The proposed prediction method was validated by experiments on cracked Plexiglas beams. The influence of added noise on the estimation accuracy of the method has been investigated. Compared to existing methods for crack detection, the proposed kurtosis-based prediction scheme is attractive due to low computational complexity and inherent robustness against noise.

In an image classification system based on deep learning, a training dataset is a set of labelled images and is often composed of a large number of images. Image labelling tool is usually used to facilitate in creating the training dataset used by the classifier during the learning phase. This paper presents a new image labelling tool called CrackLabel that can automatically label the cracks in the asphalt pavement images. A specially designed image thresholding method called the Global and Lower Quartile Average Intensity (GLQAI) method is utilised. In this study, the training dataset is developed by using real pavement images that resized to 1024×768 resolution. First, crack images are automatically segmented into 768 small patches with 32×32 resolution (pixel). Then, a threshold-based method is applied to automatically segment these patches into two classes which are crack and non-crack patches. The image thresholding method based on the average of global average intensity (GAI) and lower quartile intensity (LQI), namely GLQAI is proposed for this task. Next, the labelling process is performed by assigning patches associated with the crack and background into the crack and non-crack folder, respectively. Finally, the performance of CrackLabel is benchmarked by comparing the results with the manual label crack images by human experts, and three commonly used thresholding methods; Otsu, Kapur and Kittler-Illingworth thresholding. Experimental results show that the proposed thresholding method achieved the best classification rate among various thresholding methods with 94.50%, 93.60% 94.00% and 94.05% for recall, precision, accuracy, and F-score respectively. In conclusion, it is observed that the proposed method using the newly threshold algorithm is very effective in label images into the crack and non-crack patches to maximize the training performance.

In this paper, crack detection and estimation method is presented
in structures using modified extreme learning machine. For this
purpose, extreme learning machine was modified using modified
weights and biases. By using the first three frequencies and mode
shapes as input, crack was detected as output. Performance of the
proposed method was evaluated by using some numerical examples
consisting of a simply supported beam, cantilever beam and fixedsimply
supported beam. In addition, noise effect (3% noise level) on
the measured frequencies and mode shapes have been investigated.
In another work, a portal frame has been studied. The results indicated
that the proposed method is effective and fast in crack detection and
estimation of structures.

Pavement cracks are important information for evaluating the road condition and conducting the necessary
road maintenance. In this paper, we develop CrackTree, a fully-automatic method to detect cracks
from pavement images. In practice, crack detection is a very challenging problem because of (1) low contrast
between cracks and the surrounding pavement, (2) intensity inhomogeneity along the cracks, and
(3) possible shadows with similar intensity to the cracks. To address these problems, the proposed
method consists of three steps. First, we develop a geodesic shadow-removal algorithm to remove the
pavement shadows while preserving the cracks. Second, we build a crack probability map using tensor
voting, which enhances the connection of the crack fragments with good proximity and curve continuity.
Finally, we sample a set of crack seeds from the crack probability map, represent these seeds by a graph
model, derive minimum spanning trees from this graph, and conduct recursive tree-edge pruning to identify
desirable cracks. We evaluate the proposed method on a collection of 206 real pavement images and
the experimental results show that the proposed method achieves a better performance than several
existing methods.