Detection of sealed and unsealed cracks with complex backgrounds using deep convolutional neural network

Huo, Ju; Li, Wei; Tighe, Susan; Zhai, Junzhi; Xu, Zhengchao; Yao, Chen

doi:10.1016/j.autcon.2019.102946

Cited by 102 publications

(59 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…40 Faster R-CNN with ResNet-101 provided an mAP of 90% for detecting spalling on historic masonry buildings. A modified version of the faster R-CNN, called CrackDN, 41 integrates sensitivity detection network and region proposal refinement network (RPRN) to detect sealed and unsealed cracks. CrackDN provides an mAP of 0.9, better than faster R-CNN and single shot detector (SSD).…”

Section: Object Detection Methods Applied To Crack Detectionmentioning

confidence: 99%

“…Sensitive to light intensities. May not perform well when designed for only two classes (instead of five) Faster R-CNN with depth camera 40 Provides volumetric quantification of concrete spalling using depth information Requires trial-and-error approach to determine anchor points to detect spalling even before training the model Faster R-CNN with sensitivity detection network 41 Improves the detection of cracks using linear crack filters in addition to localization using CNN first divided into patches, normalized, and then the trained model is used for inference (to predict) whether or not there is a crack in each patch. We highlight the patch depending on whether or not there was a crack.…”

Section: Approachmentioning

confidence: 99%

See 1 more Smart Citation

Vision-based automated crack detection using convolutional neural networks for condition assessment of infrastructure

Rao

Nguyen

Palaniswami

et al. 2020

Structural Health Monitoring

View full text Add to dashboard Cite

With the growing number of aging infrastructure across the world, there is a high demand for a more effective inspection method to assess its conditions. Routine assessment of structural conditions is a necessity to ensure the safety and operation of critical infrastructure. However, the current practice to detect structural damages, such as cracks, depends on human visual observation methods, which are prone to efficiency, cost, and safety concerns. In this article, we present an automated detection method, which is based on convolutional neural network models and a non-overlapping window-based approach, to detect crack/non-crack conditions of concrete structures from images. To this end, we construct a data set of crack/non-crack concrete structures, comprising 32,704 training patches, 2074 validation patches, and 6032 test patches. We evaluate the performance of our approach using 15 state-of-the-art convolutional neural network models in terms of number of parameters required to train the models, area under the curve, and inference time. Our approach provides over 95% accuracy and over 87% precision in detecting the cracks for most of the convolutional neural network models. We also show that our approach outperforms existing models in literature in terms of accuracy and inference time. The best performance in terms of area under the curve was achieved by visual geometry group-16 model (area under the curve = 0.9805) and best inference time was provided by AlexNet (0.32 s per image in size of 256 × 256 × 3). Our evaluation shows that deeper convolutional neural network models have higher detection accuracies; however, they also require more parameters and have higher inference time. We believe that this study would act as a benchmark for real-time, automated crack detection for condition assessment of infrastructure.

show abstract

Section: Object Detection Methods Applied To Crack Detectionmentioning

confidence: 99%

Section: Approachmentioning

confidence: 99%

Vision-based automated crack detection using convolutional neural networks for condition assessment of infrastructure

Rao

Nguyen

Palaniswami

et al. 2020

Structural Health Monitoring

View full text Add to dashboard Cite

show abstract

“…For object detection, Cha et al 25 applied a faster region‐based CNN (R‐CNN) to automated crack detection. Huyan et al 26 proposed a novel crack detection method named “Crack Deep Network” (CrackDN); this method integrates faster R‐CNN architecture, a sensitivity detection network, and a region proposal refinement network (RPRN) to detect sealed and unsealed cracks with a severely complex background. Regarding pixel segmentation, Zhang et al 27 proposed a novel method called “CrackNet‐R” for 3D automated pixel‐level crack detection on asphalt roads.…”

Section: Introductionmentioning

confidence: 99%

Image‐based road crack risk‐informed assessment using a convolutional neural network and an unmanned aerial vehicle

Xue

Wang

et al. 2021

Struct Control Health Monit

View full text Add to dashboard Cite

Rapid crack assessment is widely thought to be critical for monitoring and maintaining roads in appropriate conditions. In this paper, a novel crackaffected risk-informed assessment framework is proposed for the monitoring and maintenance of roads. The framework includes five steps: data collection, crack detection, crack location extraction, crack real-size calculation, and risklevel assessment. To support the framework, an unmanned aerial vehicle (UAV) is used to monitor roads and collect data. A state-of-the-art semantic segmentation network, DeepLabv3+, is also applied to detect cracks. Based on the height and pixel statistics of the detected crack, the real size of the crack can be calculated using the pixel-physical conversion coefficient equation. This is followed by a risk-informed assessment of the road identifying the location of the crack for maintenance priority determination. Data collection and experiments using a UAV were performed on a real road to verify the feasibility and effectiveness of the proposed method. It was found that the proposed method was not only able to determine the real size of the cracks from the collected images but also able to determine their risk levels. In summary, this method presents a convenient and reliable solution for risk-informed road crack assessment that can be employed in practical applications.

show abstract

“…proposed a CNN‐based approach to identify the presence of distinguishing patterns and classify different types of structural damage. Object detection models were used to adaptively detect crack with arbitrary aspect ratio and extent 8‐10 . Most recently, to obtain an accurate crack location for severity assessment, pixel‐level crack detection have been investigated based on encoder–decoder architectures such as FCN, 11 UNet, 12 and SegNet 13 .…”

Section: Introductionmentioning

confidence: 99%

Curve‐based crack detection using crack information gain

Chen

Huang

Weng

et al. 2021

Struct Control Health Monit

View full text Add to dashboard Cite

Summary Crack detection provides valuable information concerning the location, extent, type, and severity for structural health monitoring of civil infrastructures. Due to the influence of uneven lighting and imaging noise, as well as the debris, various textures, and materials of the different civil structure, detecting cracks in the surface images of civil infrastructures remains challenging in that there are many false positives and defragmentation of the crack curve. In this paper, an information‐based crack detection method is developed to robustly characterize and detect cracks on a curve‐by‐curve basis. Crack information gain (CIG) is defined to characterize the information of a local patch's being cracked. With the proposed model of estimating crack depth, the information‐based crack descriptor CIG is calculated by statistically modeling the probabilistic distribution of crack depth. Secondly, crack curves of different saliency are progressively detected by iteratively searching the salient string of pixels, regardless of the small gaps between fragments of the crack curve. Finally, crack curves are validated by examining the variation of CIG along the crack curve. The experimental results on a diverse set of images of different civil infrastructures demonstrate the generalizability of the proposed method, and the overall performance on each dataset outperforms the state‐of‐the‐art available methods with 2.9% improvement. The proposed method has potential for the quantitative evaluation of cracks on a meaningful curve basis.

show abstract

Detection of sealed and unsealed cracks with complex backgrounds using deep convolutional neural network

Cited by 102 publications

References 30 publications

Vision-based automated crack detection using convolutional neural networks for condition assessment of infrastructure

Vision-based automated crack detection using convolutional neural networks for condition assessment of infrastructure

Image‐based road crack risk‐informed assessment using a convolutional neural network and an unmanned aerial vehicle

Curve‐based crack detection using crack information gain

Contact Info

Product

Resources

About