Automatic Pixel-Level Pavement Crack Detection Using Information of Multi-Scale Neighborhoods

Ai, Dihao; Jiang, Guiyuan; Lam, Siew-Kei; Li, Chengwu

doi:10.1109/access.2018.2829347

Cited by 133 publications

(83 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For objective comparison, the performance of several stateof-the-art methods are also reported. In CFD, we compare the proposed CAOPFs with CrackIT (Oliveira & Correia, 2014), CrackForest (Shi et al, 2016), ConvNet (Zhang et al, 2016b), MFCD (Li et al, 2019a), PGM-SVM (Ai et al, 2018), and Original-SegNet (Badrinarayanan et al, 2017). In TRIMMD, the performance of CrackIT, ConvNet, MPS (Amhaz et al, 2016), and MFCD are used for comparisons.…”

Section: Comparative Evaluationmentioning

confidence: 99%

“…The proposed methods are evaluated on three datasets, CFD (Shi et al., ), Tomorrows Road Infrastructure Monitoring, Management Dataset (TRIMMD) (Amhaz et al., ), and Customized Field Test Dataset (CFTD). In CFD, MSMP‐CAOPF increases the Boundary F1 (BF) score of state‐of‐the‐art crack detection algorithms by 2.71% over Probabilistic Generative Model (PGM)‐SVM (Ai et al., ), by 14.2% over Multi‐scale Fusion Crack Detection (MFCD) (Li et al., ), and outperforms the other recent crack detection algorithms, such as CrackForest (Shi et al., ), ConvNet (Zhang et al., ), and CrackIT (Oliveira & Correia, ) by an average of 34.2%. In TRIMMD, MSMP‐CAOPF increases the BF score by an average of 2.6% over state‐of‐the‐art algorithms including MFCD and MPS (Amhaz et al., ), and outperforms the other recent crack detection algorithms, that is, 21.7% over CrackIT.…”

Section: Introductionmentioning

confidence: 99%

“…Based on the advantages mentioned, a pixel-wise semantic segmentation scheme is highly desired in crack detection applications (Ai, Jiang, Kei, & Li, 2018;Chen & Jahanshahi, 2018;Li et al, 2019a;Li, Zhao, & Zhou, 2019b;Ni, Zhang, & Chen, 2019;Yang et al, 2018;Zhang et al, 2017b). Classification of the central pixel in a sliding window is a good attempt to bridge pixel-wise semantic segmentation to deep learning schemes (Zhang, Yang, Zhang, & Zhu, 2016b).…”

Section: Introductionmentioning

confidence: 99%

“…Unlike the assumption that a crack pixel has a lower intensity value than background pixels in Li et al (2019a), the proposed semantic segmentation network segments the cracks without any prior knowledge. Considering different fusion algorithms, the multi-scale neighborhood fusion in Ai et al (2018) merges the multiple-scale image patches at each pixel using simple maximum operation and dilates the border of the obtained cracks to improve the connectivity. The Naïve Bayes fusion (Chen & Jahanshahi, 2018) fuses the crack "tubelets" without considering the spatial constraints and lacks flexibilities to apply general machine learning algorithms due to different number of patches within each tubelet.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Concrete crack detection using context‐aware deep semantic segmentation network

Zhang

Rajan

Story

2019

Computer aided Civil Eng

150

View full text Add to dashboard Cite

Computer‐vision and deep‐learning techniques are being increasingly applied to inspect, monitor, and assess infrastructure conditions including detection of cracks. Traditional vision‐based methods to detect cracks lack accuracy and generalization to work on complicated infrastructural conditions. This paper presents a novel context‐aware deep convolutional semantic segmentation network to effectively detect cracks in structural infrastructure under various conditions. The proposed method applies a pixel‐wise deep semantic segmentation network to segment the cracks on images with arbitrary sizes without retraining the prediction network. Meanwhile, a context‐aware fusion algorithm that leverages local cross‐state and cross‐space constraints is proposed to fuse the predictions of image patches. This method is evaluated on three datasets: CrackForest Dataset (CFD) and Tomorrows Road Infrastructure Monitoring, Management Dataset (TRIMMD) and a Customized Field Test Dataset (CFTD) and achieves Boundary F1 (BF) score of 0.8234, 0.8252, and 0.7937 under 2‐pixel error tolerance margin in CFD, TRIMMD, and CFTD, respectively. The proposed method advances the state‐of‐the‐art performance of BF score by approximately 2.71% in CFD, 1.47% in TRIMMD, and 4.14% in CFTD. Moreover, the averaged processing time of the proposed system is 0.7 s on a typical desktop with Intel® Quad‐Core™ i7‐7700 CPU@3.6 GHz Processor, 16GB RAM and NVIDIA GeForce GTX 1060 6GB GPU for an image of size 256 × 256 pixels.

show abstract

Section: Comparative Evaluationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Concrete crack detection using context‐aware deep semantic segmentation network

Zhang

Rajan

Story

2019

Computer aided Civil Eng

150

View full text Add to dashboard Cite

show abstract

“…However, CNN requires a significant amount of training samples to construct a robust classifier and therefore consumes a considerable computational cost. A SVM based method that takes into account the information of neighboring pixels has been recently introduced by Ai et al [17]. Hoang and Nguyen [2] employed the image processing methods of Steerable Filters and Projective Integral for the feature extraction task as well as machine learning for classification task.…”

Section: Mathematical Problems In Engineeringmentioning

confidence: 99%

Automatic Recognition of Asphalt Pavement Cracks Based on Image Processing and Machine Learning Approaches: A Comparative Study on Classifier Performance

Hoang

Nguyen

2018

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Periodic surveys of asphalt pavement condition are very crucial in road maintenance. This work carries out a comparative study on the performance of machine learning approaches used for automatic pavement crack recognition. Six machine learning approaches, Naïve Bayesian Classifier (NBC), Classification Tree (CT), Backpropagation Artificial Neural Network (BPANN), Radial Basis Function Neural Network (RBFNN), Support Vector Machine (SVM), and Least Squares Support Vector Machine (LSSVM), have been employed. Additionally, Median Filter (MF), Steerable Filter (SF), and Projective Integral (PI) have been used to extract useful features from pavement images. In the feature extraction phase, performance comparison shows that the input pattern including the diagonal PIs enhances the classification performance significantly by creating more informative features. A simple moving average method is also employed to reduce the size of the feature set with positive effects on the model classification performance. Experimental results point out that LSSVM has achieved the highest classification accuracy rate. Therefore, this machine learning algorithm used with the feature extraction process proposed in this study can be a very promising tool to assist transportation agencies in the task of pavement condition survey.

show abstract

Automatic bridge crack detection using boundary refinement based on real‐time segmentation network

Liu

Fang

et al. 2022

Structural Contr & Hlth

View full text Add to dashboard Cite

Summary The appearance of surface cracks is an important feature of the early safety of the architecture being threatened, which is of great significance to maintaining the safety of the bridge. Bridge safety maintenance is still a challenging issue owing to noise interference and unclear bridge images. The detection method based on deep learning has achieved remarkable result in semantic segmentation, target detection, and other fields, but still be unable to focus on balancing speed and accuracy. Wherefore, we designed a new crack detection network‐dense boundary refinement network (DBR‐Net), which combines the advantages of STDC‐Net (Short‐Term Dense Concatenate network) and refinement network. STDC‐Net mainly improves the detection rate by eliminating redundant structures and optimizes the detailed information by binary cross‐entropy loss and dice loss. Finally, the detail aggregation module combines the shallow spatial details with the deep semantic information to predict the segmentation results. Among them, the refinement network refines the segmentation results of the offset map generated by the training stage and the test stage. We verified the feasibility of DBR‐Net on three datasets. At the same time, the detection accuracy rate on our self‐made crack dataset reached 97.54%. What's more worth mentioning is that our detection rate has reached 37.0 images per second (IPS), realizing real‐time crack detection.

show abstract

Automatic Pixel-Level Pavement Crack Detection Using Information of Multi-Scale Neighborhoods

Cited by 133 publications

References 31 publications

Concrete crack detection using context‐aware deep semantic segmentation network

Concrete crack detection using context‐aware deep semantic segmentation network

Automatic Recognition of Asphalt Pavement Cracks Based on Image Processing and Machine Learning Approaches: A Comparative Study on Classifier Performance

Automatic bridge crack detection using boundary refinement based on real‐time segmentation network

Contact Info

Product

Resources

About