Pavement Crack Detection using Convolutional Neural Network

Nguyen, Nhung Thi Hong; Le, Thanh; Perry, Stuart; Nguyen, Thi Thuy

doi:10.1145/3287921.3287949

Cited by 33 publications

(27 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Results show that proposed method gets a Pr of 97.24%, an Re of 94.31%, and an F1 of 95.75%, which are higher than other state-of-theart pavement crack segmentation methods, such as Crack-Forest (Shi et al, 2016). Although the recall of proposed method is lower by a small margin than that achieved by (Zhao, Qin, & Wang, 2010), (d) local thresholding (Oliveira & Correia, 2009), (e) CrackForest (Shi et al, 2016), (f) method of Jenkins and colleagues (Jenkins, Carr, Insa-Iglesias, Buggy, & Morison, 2018), (g) method of Nguyen and colleagues (Nguyen, Le, Perry, & Nguyen, 2018), (h) method of Fan and colleagues (Fan et al, 2018), (i) proposed method Cheng, Xiong, Chen, Gu, and Li (2018), the precision of proposed method is higher than other methods, and the F1 score of proposed method outperforms other methods more than 3%. The high precision and F1 score show that the proposed method correctly segments more actual crack pixels and fewer fake crack pixels than other methods and the segmentation results of proposed method are closer to the ground truths.…”

Section: Automated Pavement Crack Segmentationmentioning

confidence: 87%

Automated pavement crack detection and segmentation based on two‐step convolutional neural network

Liu

Yang

Lau

et al. 2020

Computer aided Civil Eng

252

View full text Add to dashboard Cite

Cracking is a common pavement distress that would cause further severe problems if not repaired timely, which means that it is important to accurately extract the information of pavement cracks through detection and segmentation. Automated pavement crack detection and segmentation using deep learning are more efficient and accurate than conventional methods, which could be further improved. While many existing studies have utilized deep learning in pavement crack segmentation, which segments cracks from non-crack regions, few studies have taken the exact pavement crack detection into account, which identifies cracks in the images from other objects. A two-step pavement crack detection and segmentation method based on convolutional neural network was proposed in this paper. An automated pavement crack detection algorithm was developed using the modified You Only Look Once 3rd version in the first step. The proposed crack segmentation method in the second step was based on the modified U-Net, whose encoder was replaced with a pre-trained ResNet-34 and the upsample part was added with spatial and channel squeeze and excitation (SCSE) modules. Proposed method combines pavement crack detection and segmentation together, so that the detected cracks from the first step are segmented in the second step to improve the accuracy. A dataset of pavement crack images in different circumstances were also built for the study. The F1 score of proposed crack detection and segmentation methods are 90.58% and 95.75%, respectively, which are higher than other state-of-the-art methods. Compared with existing one-step pavement crack detection or segmentation methods, proposed two-step method showed advantages of accuracy.

show abstract

Section: Automated Pavement Crack Segmentationmentioning

confidence: 87%

Automated pavement crack detection and segmentation based on two‐step convolutional neural network

Liu

Yang

Lau

et al. 2020

Computer aided Civil Eng

252

View full text Add to dashboard Cite

show abstract

“…The feature pyramid modules merge feature maps from two successive CNN layers in the downsampling blocks, whereas the hierarchical boosting modules assign weights to easy and hard samples accordingly. For pavement crack segmentation tasks, several researchers, such as Jenkins et al [18] and Nguyen et al [19], used a U-Net-based network architecture in their supervised learning algorithms. However, these methods did not use transfer learning in their network architecture design, which works well in computer vision tasks [20].…”

Section: Related Workmentioning

confidence: 99%

“…Comparison of results among various methods on the Crack500 dataset. From left to right column: (a) original image, (b) ground truth, (c) U-Net by Jenkins et al [18], (d) U-Net by Nguyen et al[19], (e) CNN by Fan et al[14], (f) Split-Attention Network[34], (g) our method.…”

mentioning

confidence: 99%

Automated Pavement Crack Segmentation Using U-Net-Based Convolutional Neural Network

et al. 2020

View full text Add to dashboard Cite

Automated pavement crack image segmentation is challenging because of inherent irregular patterns, lighting conditions, and noise in images. Conventional approaches require a substantial amount of feature engineering to differentiate crack regions from non-affected regions. In this paper, we propose a deep learning technique based on a convolutional neural network to perform segmentation tasks on pavement crack images. Our approach requires minimal feature engineering compared to other machine learning techniques. We propose a U-Net-based network architecture in which we replace the encoder with a pretrained ResNet-34 neural network. We use a "one-cycle" training schedule based on cyclical learning rates to speed up the convergence. Our method achieves an F1 score of 96% on the CFD dataset and 73% on the Crack500 dataset, outperforming other algorithms tested on these datasets. We perform ablation studies on various techniques that helped us get marginal performance boosts, i.e., the addition of spatial and channel squeeze and excitation (SCSE) modules, training with gradually increasing image sizes, and training various neural network layers with different learning rates. INDEX TERMS Convolutional neural network, deep learning, fully convolutional network, pavement crack segmentation, U-Net.

show abstract

“…Therefore, a deep CNN requires an adequate set of training samples to avoid overfitting the model [43,44]. This can be achieved by applying several data augmentation techniques such as flipping, random cropping, and resizing to increase variation among the images used to train the model [45,46]. In the current study, we applied three techniques for data augmentation, including cropping, flipping, and rotating.…”

Section: Data Collection and Pre-processing Of Crack Imagesmentioning

confidence: 99%

Inspecting Buildings Using Drones and Computer Vision: A Machine Learning Approach to Detect Cracks and Damages

Munawar

Ullah

Heravi

et al. 2021

Drones

View full text Add to dashboard Cite

Manual inspection of infrastructure damages such as building cracks is difficult due to the objectivity and reliability of assessment and high demands of time and costs. This can be automated using unmanned aerial vehicles (UAVs) for aerial imagery of damages. Numerous computer vision-based approaches have been applied to address the limitations of crack detection but they have their limitations that can be overcome by using various hybrid approaches based on artificial intelligence (AI) and machine learning (ML) techniques. The convolutional neural networks (CNNs), an application of the deep learning (DL) method, display remarkable potential for automatically detecting image features such as damages and are less sensitive to image noise. A modified deep hierarchical CNN architecture has been used in this study for crack detection and damage assessment in civil infrastructures. The proposed architecture is based on 16 convolution layers and a cycle generative adversarial network (CycleGAN). For this study, the crack images were collected using UAVs and open-source images of mid to high rise buildings (five stories and above) constructed during 2000 in Sydney, Australia. Conventionally, a CNN network only utilizes the last layer of convolution. However, our proposed network is based on the utility of multiple layers. Another important component of the proposed CNN architecture is the application of guided filtering (GF) and conditional random fields (CRFs) to refine the predicted outputs to get reliable results. Benchmarking data (600 images) of Sydney-based buildings damages was used to test the proposed architecture. The proposed deep hierarchical CNN architecture produced superior performance when evaluated using five methods: GF method, Baseline (BN) method, Deep-Crack BN, Deep-Crack GF, and SegNet. Overall, the GF method outperformed all other methods as indicated by the global accuracy (0.990), class average accuracy (0.939), mean intersection of the union overall classes (IoU) (0.879), precision (0.838), recall (0.879), and F-score (0.8581) values. Overall, the proposed CNN architecture provides the advantages of reduced noise, highly integrated supervision of features, adequate learning, and aggregation of both multi-scale and multilevel features during the training procedure along with the refinement of the overall output predictions.

show abstract

Pavement Crack Detection using Convolutional Neural Network

Cited by 33 publications

References 9 publications

Automated pavement crack detection and segmentation based on two‐step convolutional neural network

Automated pavement crack detection and segmentation based on two‐step convolutional neural network

Automated Pavement Crack Segmentation Using U-Net-Based Convolutional Neural Network

Inspecting Buildings Using Drones and Computer Vision: A Machine Learning Approach to Detect Cracks and Damages

Contact Info

Product

Resources

About