Find and Characterize Cracks in Concrete

DAnoBi (Detection of Anomalies in Image Data)

The universal building material concrete is strong and resistant, but brittle. Thin cracks in concrete are almost unavoidable, but usually not harmful either. For the inspection, diagnosis and maintenance of concrete surfaces, cracks must nevertheless be reliably found and evaluated. Experts often assess crack patterns purely visually.

Concrete and crack structures vary greatly depending on the field of application. Concrete surfaces can be very irregular. It is therefore difficult to reliably segment thin crack structures automatically.

We have developed two very flexible and robust solutions for this task – one using classical image processing and one using Machine Learning (ML). They find hairline cracks that are only one pixel thick even on heterogeneous backgrounds.

In Focus 3D Images and Computed Tomography

Internal cracks can be imaged non-destructively using computer tomography. They are thin and their low gray values often barely differ from the heterogeneous microstructure of the concrete in the 3D images. It is therefore particularly challenging to reliably find cracks, fully record their course and analyze them in 3D.

In the project DAnoBi (Detection of Anomalies in Image Data), we have developed methods together with partners to reliably find and segment cracks even in images as large as 400GB.

The Future: Globally Unique CT System for the Construction Industry

A major challenge: Micro-CT technology such as the one we use at the Fraunhofer ITWM scans concrete samples with an edge length and diameter of just a few centimetres. Mechanical load tests on concrete samples several meters long cannot be carried out. In future, this will be possible at the University of Kaiserslautern-Landau (RPTU), in the Department of Civil Engineering. A globally unique CT system is currently being built there, which will be launched in 2024. The system works with much stronger X-rays – nine megaelectron volts –than medical X-ray machines, so that reinforced concrete components up to a diameter of 30 centimetres and a length of six meters can be X-rayed.

Computed tomography portal Gulliver.
© Fraunhofer ITWM
Computed tomography portal Gulliver.
Concrete sample with crack.
© Fraunhofer ITWM
Concrete sample with a crack.

One of the first and most important application scenarios in Gulliver, as the large-scale device is called, is the 3D mapping of crack development in large concrete beams during a four-point bending test. The technology will help scientists to better understand the complex composite material concrete. Gulliver generates between 120 gigabytes and two terabytes of image data for each experiment.

More about Gulliver, the CT system (large-scale equipment initiative) of the University Kaiserslautern-Landau (German Website) 

Our Expertise and Scope of the Project

At the Fraunhofer ITWM, we optimize the memory management and image access of our extensive 3D image processing and analysis software in order to efficiently handle the huge amounts of data generated. The complex algorithms must enable short response times during image processing. This is a challenging task, as it is necessary to find the finest structures in the huge amount of data in a short space of time. For the subsequent analysis, the ITWM software offers various methods, for example for local correlation, thickness and orientation analysis.

Quantum computing has the potential to significantly simplify the analysis of huge image data.

More About Quantum Computing at Fraunhofer ITWM