Methods for segmenting cracks in 3d images of concrete: A comparison based on semi-synthetic images

Barisin, Tin; Jung, Christian; Müsebeck, Franziska; Redenbach, Claudia; Schladitz, Katja

doi:10.1016/j.patcog.2022.108747

Cited by 15 publications

(30 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, we give a short introduction to the segmentation methods that were previously identified [1] to be the most suitable. Hessian-based percolation belongs to the classical image processing methods.…”

Section: Crack Segmentation Methodsmentioning

confidence: 99%

“…A good set of candidate voxels is crucial for the performance of the algorithm. For this first step, Hessian-based filters such as the sheet filter [10] or the Frangi filter [4] have been applied successfully [1]. The Hessian matrix contains the second order local gray value variations around a voxel.…”

Section: Hessian-based Percolationmentioning

confidence: 99%

“…Recently, deep learning methods have been established for solving various image segmentation tasks. In a previous work [1], we have compared the 3d U-Net and a random forest with the classical methods from [3]. The methods were tuned in a controlled setting with fixed crack scales.…”

Section: Introductionmentioning

confidence: 99%

“…A further advantage of this approach is that the data allows for an objective method comparison. Based on [1], the two most promising methods were selected for further validation on CT images with real cracks: the 3d U-Net [2] representing the class of machine learning approaches and Hessian-based percolation as a classical image processing technique [3]. In [6], both methods were applied to real CT images of concrete with cracks resulting from tensile tests.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Crack segmentation in 3d concrete images: perspectives and challenges

Barisin¹,

Jung²,

Nowacka³

et al. 2022

eJNDT

View full text Add to dashboard Cite

Concrete is one of the most frequently used building materials. Since failure of concrete can have catastrophic consequences, understanding its properties is a prerequisite to wide-spread application. In particular, mechanical tests are applied to investigate the cracking behaviour of concrete. Computed tomography (CT) is used to analyze the concrete’s microstructure non-destructively. Segmenting cracks in CT images is challenging. Crack structures may be very thin and, therefore, insufficiently resolved in the image data. Additionally, concrete is a heterogeneous composite material typically consisting of cement paste, aggregates, pores, and reinforcements. Hence, cracks have to be distinguished from these components. The immense size of representative image data (up to 2,000^2x10,000 voxels for a concrete beam) prohibits manual processing. We compare several methods for automatic crack segmentation. To enable a fair comparison, we design a comparative study based on simulated data. Simulated cracks of varying width and shape are integrated in CT images of concrete to achieve realistic images. Using these data, machine learning methods can be trained for the segmentation. Additionally, the existence of a ground truth allows for an objective evaluation of the results. The best segmentation results are obtained by a convolutional neural network (U-net) and by Hessian-based percolation. These two methods are applied to real CT scans. There we observe an additional challenge: The thickness of cracks varies continuously while the crack propagates. Hence, multi-scale approaches covering crack widths between 1 and 20 voxels are explored. On large images, voxel-wise crack segmentation on the whole image is not feasible from a computational point of view. Hence, we suggest to initially roughly scan the image for regions that are likely to contain cracks. Then, crack segmentation is restricted to those regions. Applicability, limitations, and robustness of our methods are discussed.

show abstract

Section: Crack Segmentation Methodsmentioning

confidence: 99%

Section: Hessian-based Percolationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Crack segmentation in 3d concrete images: perspectives and challenges

Barisin¹,

Jung²,

Nowacka³

et al. 2022

eJNDT

View full text Add to dashboard Cite

show abstract

“…The results of the assessment of 2D images are simplified patterns and can include not all damage aspects due to the limitation of a spatial survey of the sample, but, due to this method being rather simple and fast, this type is reasonable for realization and quantitative evaluation of inner structure. On the opposite side, 3D segmentation starts to be a new method in X-ray CT image analysis of structure which represents the whole structural composition of the testing sample (Barisin et al, 2021). An example of this study is shown in Figure 7.…”

Section: Characteristics Of Extracted Concrete Particles By Visual An...mentioning

confidence: 99%

Visualization and evaluation of concrete damage in-service headworks by X-ray CT and non-destructive inspection methods

Morozova

Shibano

Shimamoto

et al. 2022

Front. Built Environ.

View full text Add to dashboard Cite

The durability of concrete irrigation infrastructures decreases easily due to environmental effects, such as the freeze-thawed process. The degree of damage in concrete is, in most cases, evaluated by an unconfined compression test or ultrasonic test. The limiting states of structures are the result of a gradual accumulation of microdefects during the in-service period, which leads to the initiation and development of macroscopic cracks, loss of performance, and Failure. Therefore, to maintain such structures, it is necessary to properly determine the degree of damage by non-destructive testing. For effective maintenance and management of in-service structures, it is necessary to evaluate not only such mechanical properties as strength but also the degree of damage. Quantitative damage evaluation of concrete is proposed by applying the X-ray CT method and related non-destructive inspection, which is based on estimating cracking damage effects. In this study, the damage evaluation of concrete-core samples is investigated by X-ray CT parameters and the non-destructive parameters. The samples tested were taken from the damaged concrete headwork in Niigata, Japan, about 50 years after its construction. The geometric properties of the concrete matrix were calculated by the analysis of X-ray CT images. After X-ray CT measurement, an ultrasonic test and a resonant frequency test were performed. The dynamic modulus of elasticity was calculated by using ultrasonic pulse velocity and resonant frequency. As a result, based on the relationship between the geometric properties of the concrete matrix and the non-destructive parameters, the accumulation of damage in the samples tested was correlated with the ratio of the total area of cracks to the observation area. In damaged conditions, the high value of its ratio is demonstrated under low ultrasonic pulse velocity. These results suggest that the most sensitive components in a concrete body to the degree of damage are cracks in mortar and the ratio of the total area of cracks to the observation area. These values are affected by the internal actual cracks. Thus, the damage of concrete could be quantitatively evaluated by the geometric properties of the concrete matrix and its physical properties.

show abstract