CrackSeg9k: A Collection and Benchmark for Crack Segmentation Datasets and Frameworks

Kulkarni, Shreyas; Singh, Shreyas; Balakrishnan, Dhananjay; Sharma, Siddharth; Devunuri, Saipraneeth; Korlapati, Sai Chowdeswara Rao

doi:10.1007/978-3-031-25082-8_12

Cited by 12 publications

(5 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The final crack segmentation was refined using a minimum spanning tree. CrackSeg9K 52 applied U‐Net and DeepLab as deep learning models on the CrackTree data set and reported the performance in terms of mean IoU and F1 scores. The images in the CrackTree data set are relatively complex because roadside shadows may occlude pavement cracks.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Crack segmentation in the wild using convolutional neural networks and bootstrapping

Ahmad,

Gharehbaghi,

et al. 2023

Earthquake Engineering and Resilience

View full text Add to dashboard Cite

Computer vision and deep learning methods have found numerous practical applications over the last decade. The field of structural health monitoring has greatly benefited from such advancements. Accurate crack detection and segmentation are a critical part of structural health monitoring and assessment. In the past decade, researchers have developed different computer vision and deep learning methods to address this challenging task. In this article, we propose to use convolutional neural networks and bootstrapping to improve crack segmentation in the wild. Specifically, we investigate fully convolutional network (FCN) and DeepLabV3 with different ResNet architectures as the back bone and assess their performance. A unique feature of this work is the use of bootstrapping with a segmentation network and image augmentation. Bootstrapping is an important component of our proposed methodology for better extracting features from the datasets. We also incorporate superpixel pooling for FCN which improves performance. We assess the performance of our method using five publicly available datasets, which include a wide variety of crack images such as thin pavement cracks, tree shadows on cracks, cracks in asphalt roads, concrete wall cracks, wide cracks on concrete surfaces, and so on. A comparative study is also performed with several established methods in the literature. Results indicate that overall, our proposed method outperforms other state‐of‐the‐art methods for crack segmentation.

show abstract

Section: Resultsmentioning

confidence: 99%

“…These high‐resolution images were cropped into 16 nonoverlapping regions. The image patches not containing the cracks have been discarded, resulting in a total of 3404 image patches 52 . We used a 56:10:34 split for training, validation, and testing 52 …”

Section: Methodsmentioning

confidence: 99%

Crack segmentation in the wild using convolutional neural networks and bootstrapping

Ahmad,

Gharehbaghi,

et al. 2023

Earthquake Engineering and Resilience

View full text Add to dashboard Cite

show abstract

“…For the restoration of concrete crack images and crack detection, the same dataset was used for training and performance evaluation of the SRGAN and segmentation network. DeepCrack [38], SDNET2018 [39], the Mendeley dataset [40], Rissbilder dataset [41], EugenMuller dataset [42], and Volker dataset [43] provide various concrete crack RGB images and labeled data. Because the sizes of the images provided by each dataset were diferent, the image sizes were converted to 256 × 256 pixels.…”

Section: Methodsmentioning

confidence: 99%

Learning Structure for Concrete Crack Detection Using Robust Super-Resolution with Generative Adversarial Network

Kim

Shim

Kang

et al. 2023

Structural Control and Health Monitoring

View full text Add to dashboard Cite

To develop countermeasures against the inevitable aging of tunnels, accurate inspection is critical for ensuring stable tunnel services. Tunnels are large-scale infrastructures, whereas the cracks in such tunnels are small-scale objects, necessitating the development of methods capable of rapidly detecting cracks in a wide field of view. Therefore, this study proposes a new learning structure based on a segmentation network. This structure includes super-resolution and generative adversarial networks, which contribute to improved detection performance with robustness to input data. Furthermore, a method for the effective construction of training data for the application of the proposed structure is presented. Subsequently, the performance of the method over 1,606 crack images with randomly degraded qualities is evaluated. The proposed structure presents improved crack intersection over union and F1-scores of 63.686% and 77.811%, respectively, and low variances of 0.9008 and 0.5015 compared to the original structure. The results presented herein indicate the possible application of the proposed accurate condition inspection technology to tunnel maintenance in the future.

show abstract

“…We used the public datasets DeepCrack [ 24 ] and Crack500 [ 43 ] to evaluate the performance of PCTC-Net in detecting cracks in paved roads made of asphalt and concrete. We also utilized the public dataset Crackseg9k [ 44 ] to evaluate whether PCTC-Net performs well in detecting cracks in a variety of materials, including ceramic, glass, and masonry. The dataset sizes were 539 for DeepCrack, 3020 for Crack500, and 9255 for Crackseg9k.…”

Section: Dataset and Experiments Environmentmentioning

confidence: 99%

PCTC-Net: A Crack Segmentation Network with Parallel Dual Encoder Network Fusing Pre-Conv-Based Transformers and Convolutional Neural Networks

Moon,

Choi,

Kim

et al. 2024

Sensors

View full text Add to dashboard Cite

Cracks are common defects that occur on the surfaces of objects and structures. Crack detection is a critical maintenance task that traditionally requires manual labor. Large-scale manual inspections are expensive. Research has been conducted to replace expensive human labor with cheaper computing resources. Recently, crack segmentation based on convolutional neural networks (CNNs) and transformers has been actively investigated for local and global information. However, the transformer is data-intensive owing to its weak inductive bias. Existing labeled datasets for crack segmentation are relatively small. Additionally, a limited amount of fine-grained crack data is available. To address this data-intensive problem, we propose a parallel dual encoder network fusing Pre-Conv-based Transformers and convolutional neural networks (PCTC-Net). The Pre-Conv module automatically optimizes each color channel with a small spatial kernel before the input of the transformer. The proposed model, PCTC-Net, was tested with the DeepCrack, Crack500, and Crackseg9k datasets. The experimental results showed that our model achieved higher generalization performance, stability, and F1 scores than the SOTA model DTrC-Net.

show abstract

CrackSeg9k: A Collection and Benchmark for Crack Segmentation Datasets and Frameworks

Cited by 12 publications

References 48 publications

Crack segmentation in the wild using convolutional neural networks and bootstrapping

Crack segmentation in the wild using convolutional neural networks and bootstrapping

Learning Structure for Concrete Crack Detection Using Robust Super-Resolution with Generative Adversarial Network

PCTC-Net: A Crack Segmentation Network with Parallel Dual Encoder Network Fusing Pre-Conv-Based Transformers and Convolutional Neural Networks

Contact Info

Product

Resources

About