Automatic concrete infrastructure crack semantic segmentation using deep learning

Chen, Bo; Zhang, Hua; Wang, Guijin; Huo, Jianwen; Li, Yonglong; Li, Linjing

doi:10.1016/j.autcon.2023.104950

Cited by 15 publications

(5 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The F value, in this case, is shown to be about 0.73. In addition to our work ( [9]), other deep learning applications include the development of a technique for detecting cracks in concrete [16] and the use of transition learning to detect cracks in masonry walls [18].…”

Section: Related Workmentioning

confidence: 99%

Smart non-destractive test of a concrete wall using a hammer

Ito,

Koike,

Hibino

2024

International Journal of Electronics and Telecommunications

View full text Add to dashboard Cite

Large concrete structures such as buildings, bridges, and tunnels are aging. In Japan and many other countries, those built during economic reconstruction after World War II are about 60 to 70 years old, and flacking and other problems are becoming more noticeable. Periodic inspections were made mandatory by government and ministerial ordinance during the 2013-2014 fiscal year, and inspections based on the new standards have just begun. There are various methods to check the soundness of concrete, but the hammering test is widely used because it does not require special equipment. However, long experience is required to master the hammering test. Therefore, mechanization is desired. Although the difference between the sound of a defective part and a normal part is very small, we have shown that neural network is useful in our research. To use this technology in the actual field, it is necessary to meet the forms of concrete structures in various conditions. For example, flacking in concrete exists at various depths, and it is impossible to learn about flacking in all cases. This paper presents the results of a study of the possibility of finding flacking at different depths with a single inspection learning model and an idea to increase the accuracy of a learning model when we use a rolling hammer.

show abstract

Section: Related Workmentioning

confidence: 99%

Smart non-destractive test of a concrete wall using a hammer

Ito,

Koike,

Hibino

2024

International Journal of Electronics and Telecommunications

View full text Add to dashboard Cite

show abstract

“…In this work, Weighted Cross-Entropy loss and Dice loss are employed to form the hybrid loss function. It is calculated as follows: loss = loss wce + λ * loss dice (8) where loss wce and loss dice present Weighted Cross-Entropy loss and Dice loss, and λ is the weight ratio between these two loss functions. As the network progresses through multiple epochs and gains preliminary understanding of both background and crack foreground information, the Weighted Cross-Entropy loss tends to be a certain multiple of the Dice loss.…”

Section: Loss Functionmentioning

confidence: 99%

“…With the rapid advancements in computer hardware and computer vision technology, vision-based automated detection methods have demonstrated notable success in detecting concrete surface cracks in civil infrastructure [8][9][10]. In these vision-based approaches, a crucial step is to extract features from the images that are sensitive to cracks.…”

Section: Introductionmentioning

confidence: 99%

Vison Transformer-Based Automatic Crack Detection on Dam Surface

Zhou,

Zhao,

2024

Water

Self Cite

View full text Add to dashboard Cite

Dam is an essential structure in hydraulic engineering, and its surface cracks pose significant threats to its integrity, impermeability, and durability. Automated crack detection methods based on computer vision offer substantial advantages over manual approaches with regard to efficiency, objectivity and precision. However, current methods face challenges such as misidentification, discontinuity, and loss of details when analyzing real-world dam crack images. These images often exhibit characteristics such as low contrast, complex backgrounds, and diverse crack morphologies. To address the above challenges, this paper presents a pure Vision Transformer (ViT)-based dam crack segmentation network (DCST-net). The DCST-net utilizes an improved Swin Transformer (SwinT) block as the fundamental block for enhancing the long-range dependencies within a SegNet-like encoder–decoder structure. Additionally, we employ a weighted attention block to facilitate side fusion between the symmetric pair of encoder and decoder in each stage to sharpen the edge of crack. To demonstrate the superior performance of our proposed method, six semantic segmentation models have been trained and tested on both a self-built dam crack dataset and two publicly available datasets. Comparison results indicate that our proposed model outperforms the mainstream methods in terms of visualization and most evaluation metrics, highlighting its potential for practical application in dam safety inspection and maintenance.

show abstract

“…The use of pre-trained models as initial parameters for a different task is called transfer learning [36]. This method is frequently used in some deep learning problems.…”

Section: Transfer Learningmentioning

confidence: 99%

“…Furthermore, a GAN-based neural network called CrackSegAN is proposed for automatic pavement crack segmentation, achieving high F1 scores on different datasets [35]. Finally, an automatic concrete infrastructure crack semantic segmentation method is proposed using deep learning, which shows optimal performance for crack image segmentation [36].…”

Section: Introductionmentioning

confidence: 99%

Deep Learning-Based Automated Detection of Cracks in Historical Masonry Structures

Hacıefendioğlu,

Altunışık,

Abdioğlu

2023

Buildings

View full text Add to dashboard Cite

The efficient and precise identification of cracks in masonry stone structures caused by natural or human-induced factors within a specific region holds significant importance in detecting damage and subsequent secondary harm. In recent times, remote sensing technologies have been actively employed to promptly identify crack regions during repair and reinforcement activities. Enhanced image resolution has enabled more accurate and sensitive detection of these areas. This research presents a novel approach utilizing deep learning techniques for crack area detection in cellphone images, achieved through segmentation and object detection methods. The developed model, named the CAM-K-SEG segmentation model, combines Grad-CAM visualization and K-Mean clustering approaches with pre-trained convolutional neural network models. A comprehensive dataset comprising photographs of numerous historical buildings was utilized for training the model. To establish a comparative analysis, the widely used U-Net segmentation model was employed. The training and testing datasets for the developed technique were meticulously annotated and masked. The evaluation of the results was based on the Intersection-over-Union (IoU) metric values. Consequently, it was concluded that the CAM-K-SEG model exhibits suitability for object recognition and localization, whereas the U-Net model is well-suited for crack area segmentation.

show abstract

Automatic concrete infrastructure crack semantic segmentation using deep learning

Cited by 15 publications

References 31 publications

Smart non-destractive test of a concrete wall using a hammer

Smart non-destractive test of a concrete wall using a hammer

Vison Transformer-Based Automatic Crack Detection on Dam Surface

Deep Learning-Based Automated Detection of Cracks in Historical Masonry Structures

Contact Info

Product

Resources

About