Automated counting of off-axis tunnelling cracks using digital image processing

Glud, Jens Ammitzbøll; Dulieu-Barton, J.M.; Thomsen, Ole Thybo; Overgaard, Lars C. T.

doi:10.1016/j.compscitech.2016.01.019

Cited by 51 publications

(45 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The characterisation is enabled by a fully automated crack identification and counting procedure, known as the Automatic Crack Counting methodology (ACC) presented in [26]. The high temporal resolution and data-rich characterisation has allowed for the following conclusions to be made:…”

Section: Discussionmentioning

confidence: 99%

“…The crack state generally consists of many cracks which are unevenly distributed in the region of interest, so the crack counting task is labour intensive and difficult, essentially because the images are difficult to analyse by eye e.g. [9,26]. This limits the scope and size of studies and leads to a relatively poor temporal resolution of the crack state.…”

Section: Introductionmentioning

confidence: 99%

“…To capture the CGR, the ACC methodology [26] is extended so that isolated cracks are tracked and their length recorded. To determine if a tracked crack could be considered to isolated, a radius of 4 times the layer thickness from the crack-tip was searched for the existence of neighbouring cracks.…”

Section: Crack Growth Rate (Cgr)mentioning

confidence: 99%

“…The VA tests consisted of a block of 10 5 cycles at a stress level of 39 MPa followed by a block of ~2.5 • 10 cycles at 50 MPa. The image filtering parameters required for using ACC were chosen based on the procedure described in [26] and the Gabor parameters (,  G and )…”

Section: Materials and Experimentsmentioning

confidence: 99%

“…Moreover, as a result of the complex images of the crack state, the There is a clear need to devise a new approach to derive statistically representative fatigue failure parameters from MD laminate tests. With this aim in mind, an approach has been devised known as the Automatic Crack Counting (ACC) procedure [26], which quantifies the crack state for each ply in terms of the length and location for each individual crack for every processed image. The ACC procedure has allowed the collection of the necessary data sets without human errors at sufficient temporal resolution to obtain the parameters that define off-axis crack initiation and growth.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Fatigue damage evolution in GFRP laminates with constrained off-axis plies

Glud¹,

Dulieu-Barton²,

Thomsen³

et al. 2017

Composites Part A: Applied Science and Manufacturing

Self Cite

View full text Add to dashboard Cite

., "Fatigue damage evolution in GFRP laminates with constrained off-axis plies", Composites Part A, http://dx.doi. org/10.1016/j.compositesa.2017. method with a data mining approach and applying these to large data sets obtained during fatigue tests. It is shown that for a constant stress level, the stochastic nature of off-axis crack initiation and crack growth is accurately modelled by the Weibull distribution, with the distribution parameters being efficiently derived using the developed approach. The data-rich characterisation provides new insight in the crack density evolution process for VA and C-T loading, as well as derived Weibull distribution parameters in combination with the classical S-N curves and Paris' Law relationship.Hence, providing an improved approach that includes the stochastic and deterministic information for physically based modelling of crack density evolution for fatigue loading.Glud, J.A., Dulieu-Barton, J.M., Thomsen, O.T. and Overgaard, L.C.T., "Fatigue damage evolution in GFRP laminates with constrained off-axis plies", Composites Part A, http://dx

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Crack Growth Rate (Cgr)mentioning

confidence: 99%

Section: Materials and Experimentsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Fatigue damage evolution in GFRP laminates with constrained off-axis plies

Glud¹,

Dulieu-Barton²,

Thomsen³

et al. 2017

Composites Part A: Applied Science and Manufacturing

Self Cite

View full text Add to dashboard Cite

show abstract

Tunnel crack detection using coarse‐to‐fine region localization and edge detection

Niu

et al. 2019

WIREs Data Min & Knowl

View full text Add to dashboard Cite

Detecting cracks on the concrete surface is crucial for the tunnel health monitoring and maintenance of Chinese transport facilities, since it is closely related with the structural health and reliability. The automated and efficient tunnel crack detection recently has attracted more research studies, particularly cheap availability of digital cameras makes this issue easier. However, it is still a challenging task due to concrete blebs, stains, and illumination over the concrete surface. This paper presents an efficient crack detection method in the tunnel concrete structure based on digital image processing and deep learning. Three contributions of the paper are summarized as follows. First, we collect and annotate a tunnel crack dataset including three kinds of common cracks that might benefit the research in the field. Second, we propose a new coarse-to-fine crack detection method using improved preprocessing, coarse crack region localization and classification, and fine crack edge detection. Third, we introduce a faster region convolutional neural network to develop a coarse crack region localization and classification, then deploy edge extraction to implement the fine crack edge detection, gaining a high-efficiency and high-accuracy performance.deep learning, edge detection, region localization, tunnel crack detection | INTRODUCTIONIn recent years, with the rapid development of road traffic in China, safety inspection of concrete structures is crucial to the cost-effective maintenance of Chinese transport facilities, since it is closely related with the structural health and reliability. As an important part of road traffic, tunnels are also the top priority for security inspection and maintenance. Due to the geology, topography, climate, and construction conditions, lining crack is one of the most common diseases on the surface of tunnel's concrete structure along which it has split without breaking apart.The traditional manual inspection approaches are subjective and time-consuming. Nowadays, more and more researchers make studies on the industrial sensors, such as charge coupled device cameras, ground penetrating radar, and lasers, employ them to catch the crack image and measure the concrete crack automatically. These sensors, especially the cheap cameras, can rapidly collect information over wide concrete areas on the tunnel and get the crack detection results. However, the automatic and efficient tunnel crack detection is still a challenging task due to the concrete blebs, stains, and illumination. This paper focus on judging the lining cracks by acquiring and processing the concrete's image, aiming to reducing the cost of maintenance and time-consuming in the safety inspection of concrete structures.

show abstract