A Study of Methods using Image Processing Technique in Crack Detection

Shifani, S. Agnes; Thulasiram, P.; Narendran, Kailas; Sanjay, D.R.

doi:10.1109/icimia48430.2020.9074966

Cited by 9 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The adoption of the proposed CDM allows the user to filter out all unwanted features present on the monitored surface. This has the potential to significantly reduce a common issue related to the inclusion of no-crack related features [16,17]. This is advantageous when working in challenging conditions (e.g., structural surfaces with various sources of noises), and further investigation must be conducted to assess the real potential in such contexts.…”

Section: Discussionmentioning

confidence: 99%

“…In the literature there are several examples of works focused on the implementation of image-based crack detection approaches for a range of applications [12][13][14][15]. Detailed reviews of works focusing on crack detection through image-processing techniques are reported by [16,17]. When dealing with image processing techniques applied to single images for crack assessment, the majority of works on this topic carry out the recognition, exploiting the crack geometry and the sudden variation of intensity of pixels provoked by the presence of a crack [6,18].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Image-Based Monitoring of Cracks: Effectiveness Analysis of an Open-Source Machine Learning-Assisted Procedure

et al. 2022

View full text Add to dashboard Cite

The proper inspection of a cracks pattern over time is a critical diagnosis step to provide a thorough knowledge of the health state of a structure. When monitoring cracks propagating on a planar surface, adopting a single-image-based approach is a more convenient (costly and logistically) solution compared to subjective operators-based solutions. Machine learning (ML)- based monitoring solutions offer the advantage of automation in crack detection; however, complex and time-consuming training must be carried out. This study presents a simple and automated ML-based crack monitoring approach implemented in open sources software that only requires a single image for training. The effectiveness of the approach is assessed conducting work in controlled and real case study sites. For both sites, the generated outputs are significant in terms of accuracy (~1 mm), repeatability (sub-mm) and precision (sub-pixel). The presented results highlight that the successful detection of cracks is achievable with only a straightforward ML-based training procedure conducted on only a single image of the multi-temporal sequence. Furthermore, the use of an innovative camera kit allowed exploiting automated acquisition and transmission fundamental for Internet of Things (IoTs) for structural health monitoring and to reduce user-based operations and increase safety.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Image-Based Monitoring of Cracks: Effectiveness Analysis of an Open-Source Machine Learning-Assisted Procedure

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Furthermore, recent advances in hardware and software technology led to a wide growth of image processing-based degradation inspection research works over the past few decades. Depending on the applications and the degree of accuracy desired, a wide range of image-based processing techniques and classification approaches can be adopted (Mohan and Poobal, 2018;Sizyakin et al, 2018;Shifani et al, 2020;Parente et al, 2022).…”

Section: Structural Damages Monitoringmentioning

confidence: 99%

Built Heritage in post-Disaster Scenarios

Balzani,

Maietti,

Montuori

et al. 2024

View full text Add to dashboard Cite

The 20 th and 29 th May 2012 are dates that will be etched into Emilians' memories forever. On those days, terrible earthquakes killed 28 and wounded 300, with 45 thousand people evacuated and 12.2 billion euros of damage, affecting 59 municipalities in the provinces of Modena, Ferrara, Bologna and Reggio Emilia. The efforts made to restore services, schools, jobs, places, piazzas, and social opportunities to those communities have never stopped, continuously supported by the achievement of goals set by the Emilia-Romagna Region from the beginning: reopening schools in time for the beginning of the school year, continuity of and attention to public services, support for work and industrial and agricultural production, "no to new towns", and plans for interventions on the huge amount of cultural heritage damaged. A commitment sustained by the desire to start again, and the courage to do so immediately, has consistently distinguished the communities hit. Right from the beginning they expressed the need to not give up, the will to help each other, the hope to come out of this stronger than before, this time too.Today, the reconstruction work is 90% complete -private reconstructions (homes and companies) are almost finished, and the reconstruction of public spaces and the historical-artistic heritage is underway, and it is this that we are concentrating on the most, in order to bring it to completion.Along with the reconstruction, for a few years the Emilia-Romagna Region has also been focusing on the promotion of a culture of seismic prevention and risk management -topics that need to inspire great interest through widespread campaigns from all institutions, in collaboration with universities and research institutes.For this purpose, a permanent collaboration has been established with the universities of the area and the "Clusters" of the regional economic system, and taking place in this context is the international summer school, "After the Damages", which has the goal of addressing topics in the area of risk management relating to natural disasters, starting from the experience gained following the seismic events of May 2012, and training students, graduates, and directors in public administration, governing bodies and international organisations, as well as researchers, specialists and professionals.A unique opportunity to bring many different professional views to the same table, both public and private, so that they can address topics that are essential for the future of our territory and our communities with an interdisciplinary approach. This occasion, as the records collected in this volume demonstrate, continues to open up results and best practices from the reconstruction in Emilia to opportunities for diffusion and discussion, also with the international academic and scientific worlds, which yet again guarantee the quality of the work carried out and the integrity of the routes taken.

show abstract

“…However, only a few recently published review articles incorporating image processing methods are still evident in the literature. In paper [34], the author has demonstrated a variety of recent techniques and their analysis in the image processing used to identify various types of cracks on the concrete surface. Various forms of cracks on a different surface and the technique available for identification along with the algorithm used have been briefly outlined and clarified in this paper.…”

Section: Image Processing Familymentioning

confidence: 99%

Automatic Multiclass Instance Segmentation of Concrete Damage Using Deep Learning Model

2021

View full text Add to dashboard Cite

Concrete is one of the primary and most commonly used materials for the construction of buildings, roads, bridges, and dams. But it may lose its strength with age, moisture content, or due to other factors. As a result, little damage (crack and spall) to these structures may lead to sudden collapse or breakage, which in turn can decimate many lives with economic losses. Hence, to ensure their strength with the proper load, accurate screening of concrete surface damage is necessary for maintenance engineers to understand and evaluate the severity of the damage. Few preceding vision-based studies have proposed object detection and semantic segmentation approaches to carry out damage detection; however, the developed models could not segment different objects of the same class. The semantic segmentation approach separates regions that contain only objects of the same class. Concrete surface damage, on the other hand, may contain multiple objects, such as the Horizontal Crack, Vertical Crack, Diagonal Crack, Branch Crack, and Spall, that needs to be segmented separately so that specific measures can be taken. This study utilizes Mask Region-Based Convolutional Neural Network (Mask R-CNN) to manage concrete damage images and employ it to detect and segment defects in civil infrastructure with multiple objects. As we understand, this is the first research involving a Structural Health Monitoring (SHM) application for damage detection using instance segmentation. Our proposed model has been trained and tested on a dataset containing 800 images (480*480 pixels) of different types of crack and spall are collected from distinct structures of CSIR-CEERI, Pilani, campus. To test and validate the generosity, an additional 96 damage images are downloaded using Google. The pre-processed and annotated images are used to train and validate the Mask R-CNN Classifier. Our experimental results show that damage can be classified efficiently with 95.13% accuracy on a custom dataset and 96.87% on randomly picked images.

show abstract

A Study of Methods using Image Processing Technique in Crack Detection

Cited by 9 publications

References 9 publications

Image-Based Monitoring of Cracks: Effectiveness Analysis of an Open-Source Machine Learning-Assisted Procedure

Image-Based Monitoring of Cracks: Effectiveness Analysis of an Open-Source Machine Learning-Assisted Procedure

Built Heritage in post-Disaster Scenarios

Automatic Multiclass Instance Segmentation of Concrete Damage Using Deep Learning Model

Contact Info

Product

Resources

About