Weakly-Supervised Surface Crack Segmentation by Generating Pseudo-Labels using Localization with a Classifier and Thresholding

König, Jacob; Jenkins, Mark A.; Mannion, Mike; Barrie, Peter; Morison, Gordon

doi:10.48550/arxiv.2109.00456

Cited by 2 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This then yields a segmentation map as darker pixels are segmented as crack pixels. A similar approach is shown in [55], where a classifier is used to create a detection map as shown in Figure 4, which is then merged with a thresholding approach. Merging the detection map with the thresholding in this approach aims Fig.…”

Section: B Semi and Weakly Supervised Learningmentioning

confidence: 99%

“…Approaches that train on classification labels and then use thresholding to create a segmentation map [55], [82] S Training on coarse segmentation labels [83] Q Rotation analysis of cracks by rotating the input [39] Unsupervised S Transformation of an input image into latent space or frequency domain before reversing transforming it back into an image. The differences between the input and output then segment areas belonging to cracks or other anomalies.…”

mentioning

confidence: 99%

See 1 more Smart Citation

What's Cracking? A Review and Analysis of Deep Learning Methods for Structural Crack Segmentation, Detection and Quantification

König¹,

Jenkins²,

Mannion³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Surface cracks are a very common indicator of potential structural faults. Their early detection and monitoring is an important factor in structural health monitoring. Left untreated, they can grow in size over time and require expensive repairs or maintenance. With recent advances in computer vision and deep learning algorithms, the automatic detection and segmentation of cracks for this monitoring process have become a major topic of interest. This review aims to give researchers an overview of the published work within the field of crack analysis algorithms that make use of deep learning. It outlines the various tasks that are solved through applying computer vision algorithms to surface cracks in a structural health monitoring setting and also provides in-depth reviews of recent fully, semi and unsupervised approaches that perform crack classification, detection, segmentation and quantification. Additionally, this review also highlights popular datasets used for cracks and the metrics that are used to evaluate the performance of those algorithms. Finally, potential research gaps are outlined and further research directions are provided.

show abstract

Section: B Semi and Weakly Supervised Learningmentioning

confidence: 99%

mentioning

confidence: 99%

What's Cracking? A Review and Analysis of Deep Learning Methods for Structural Crack Segmentation, Detection and Quantification

König¹,

Jenkins²,

Mannion³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Because YOLOv5 [10] is known to provide a high accuracy with a low time complexity in the object detection research field, we use it as a baseline architecture of AugMoCrack. To address the issue of a lack of crack data in practical applications, we devised a crack data augmentation method based on Poisson blending [11] and a classifier of crack and non-crack patches [12]. We also enforce frequency augmentation in the spectral domain of an AugMoCrack network.…”

mentioning

confidence: 99%

AugMoCrack: Augmented morphological attention network for weakly supervised crack detection

Hong

Lee

Yoo

2022

Electronics Letters

View full text Add to dashboard Cite

Most crack-detection methods adopt a pixel-level segmentation-based approach, which requires considerable time and complexity to detect the pixel area of the crack. Unlike a pixel-level segmentation-based approach, in this paper, the authors proposed an AugMoCrack network, a bounding box-level crack detection approach for weakly supervised crack detection achieved by augmenting the training data with Poisson blending, as well as high-frequency discrete cosine transformbased features. The proposed AugMoCrack detects the box position of the crack object from a morphological perspective, such as neighbour connectivity within the crack pixels and crack-area fitting. Based on this perspective, the authors also proposed new morphological attention loss functions for considering the neighbour connectivity and the box area border. Specifically, the authors trained the AugMoCrack network using two datasets and verified its performance based on 591 validation images in the concrete crack dataset and 672 validation images in the Crack500 dataset. Compared with the baseline architecture, with the authors' proposed network, the authors achieved increases of approximately 4.5% points and 2.5% points in the mean average precision (mAP) in the concrete crack and Crack500 datasets, respectively. The proposed network also outperforms previous state-of-the-art crackdetection methods in a weakly supervised learning environment where the training data are insufficient.

show abstract

Weakly-Supervised Surface Crack Segmentation by Generating Pseudo-Labels using Localization with a Classifier and Thresholding

Cited by 2 publications

References 0 publications

What's Cracking? A Review and Analysis of Deep Learning Methods for Structural Crack Segmentation, Detection and Quantification

What's Cracking? A Review and Analysis of Deep Learning Methods for Structural Crack Segmentation, Detection and Quantification

AugMoCrack: Augmented morphological attention network for weakly supervised crack detection

Contact Info

Product

Resources

About