Image-Based Concrete Crack Detection Method Using the Median Absolute Deviation.

This paper proposes an innovative approach for detecting and quantifying concrete cracks using an adaptive threshold method based on Median Absolute Deviation (MAD) in images. The technique applies limited pre-processing steps and then dynamically determines a threshold adapted for each sub-image depending on the greyscale distribution of the pixels, resulting in tailored crack segmentation. The edges of the crack are obtained using the Laplace edge detection method, and the width of the crack is obtained for each centreline point. The method's performance is measured using the Probability of Detection (POD) curves as a function of the actual crack size, revealing remarkable capabilities. It was found that the proposed method could detect cracks as narrow as 0.1 mm, with a probability of 94% and 100% for cracks with larger widths. It was also found that the method has higher accuracy, precision, and F2 score values than the Otsu and Niblack methods.

Dataset for damage detection retrieved from a monitored bridge pre and post verified damage.

The Vänersborg Bridge in southwest Sweden is a single-leaf bascule bridge carrying railway traffic over a canal. The load consists of passing commuter trains, occasional freight trains and leaf openings to allow ships to pass on the canal. The bridge constructed from 1914 to 1916 was built by riveted truss members in steel. Over the years, several assessments and maintenance actions have been performed to keep the bridge in service. During autumn 2021, a long-term monitoring campaign was initiated with the installation of sensors to register the load effect and possible changes in the behaviour. In March 2023, the cloud-based service employed detected an abrupt change of behaviour. An emergency inspection revealed a large crack in one of the truss members in the counter-weight part. The published dataset contains sensor data from 64 registered bridge openings, comprising accelerations, strains, inclinations, and weather conditions. Data from before the fracture, during, and after are provided. During the bridge opening events, the data was recorded continuously with a sampling rate of 200 Hz. The evidence of damage in a real case scenario makes the dataset valuable for testing and evaluation of data-driven routines for infrastructure surveillance.