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

•Comparison of eight methods for crack detection in 3d CT concrete images.•Simulation of 3d crack images gives unbiased ground truth for evaluation.•Parameter tuning with respect to different objectives.•Machine learning methods (3d U-net and random forest) perform best among all methods.•Hessian-ba...

Full description

Saved in:
Bibliographic Details
Published in:Pattern recognition Vol. 129; p. 108747
Main Authors: Barisin, Tin, Jung, Christian, Müsebeck, Franziska, Redenbach, Claudia, Schladitz, Katja
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.09.2022
Subjects:
3d segmentation
Computed tomography
Crack detection
Deep learning
Fractional Brownian surface
Machine learning
Deep learning
Crack detection
Computed tomography
3d segmentation
Machine learning
Fractional Brownian surface
ISSN:0031-3203, 1873-5142
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•Comparison of eight methods for crack detection in 3d CT concrete images.•Simulation of 3d crack images gives unbiased ground truth for evaluation.•Parameter tuning with respect to different objectives.•Machine learning methods (3d U-net and random forest) perform best among all methods.•Hessian-based percolation performs best among classical methods. [Display omitted] Concrete is the standard construction material for buildings, bridges, and roads. As safety plays a central role in the design, monitoring, and maintenance of such constructions, it is important to understand the cracking behavior of concrete. Computed tomography captures the microstructure of building materials and allows to study crack initiation and propagation. Manual segmentation of crack surfaces in large 3d images is not feasible. In this paper, automatic crack segmentation methods for 3d images are reviewed and compared. Classical image processing methods (edge detection filters, template matching, minimal path and region growing algorithms) and learning methods (convolutional neural networks, random forests) are considered and tested on semi-synthetic 3d images. Their performance strongly depends on parameter selection which should be adapted to the grayvalue distribution of the images and the geometric properties of the concrete. In general, the learning methods perform best, in particular for thin cracks and low grayvalue contrast.
ISSN:0031-3203
1873-5142
DOI:10.1016/j.patcog.2022.108747