Faster region convolutional neural network for automated pavement distress detection

Song, Liang; Wang, Xuancang

doi:10.1080/14680629.2019.1614969

Cited by 88 publications

(22 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Training result of best iteration was then used to evaluate the performance of proposed crack detection method, as shown in Figure 8. The overall precision, recall, and F1 score of proposed method are 91.95%, 89.31%, and 90.58%, respectively, which are higher than the pavement crack detection results of Faster R-CNN (Song & Wang, 2019) and YOLOv2 (Mandal et al, 2018).…”

Section: Automated Pavement Crack Detection Resultsmentioning

confidence: 76%

“…Meanwhile, few existing researches have been involved with actual pavement crack detection. Song and Wang (2019) used Faster R-CNN to recognize and locate pavement distresses, including detecting pavement cracks, and got accuracy rate of 90.4% for all pavement distresses. Mandal, Uong, and Adu-Gyamfi (2018) used YOLOv2 to detect pavement cracks, and got the results as precision of 0.8851, recall of 0.8710, and F1 score of 0.8780, which could be further improved.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Liu

Yang

Lau

et al. 2020

Computer aided Civil Eng

270

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 Detection Resultsmentioning

confidence: 76%

Section: Introductionmentioning

confidence: 99%

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

Liu

Yang

Lau

et al. 2020

Computer aided Civil Eng

270

View full text Add to dashboard Cite

show abstract

“…If these graphs are examined, it is seen that the polyfit value shown in red has decreased. Unlike the studies conducted with Faster R-CNN in the literature, this study gained originality by classifying according to different cracks, not whether there are cracks or not [16]. These results show that the Faster R-CNN structure is an impressive method for the detection of cracks on asphalt.…”

Section: Resultsmentioning

confidence: 88%

Faster R-CNN Structure for Computer Vision-based Road Pavement Distress Detection

Balcı

YILMAZ

2023

Politeknik Dergisi

View full text Add to dashboard Cite

Smart cities can be controlled in all aspects and it is desired to have a structure that is planned to have controllable feedback. Asphalt is generally used as pavement material on roads that provide transportation of vehicles such as cars and buses on the highway. Asphalt material is deformed due to weather conditions, heavy vehicle passage. In the smart city structure, similar deformations should be reported to the relevant unit. In this article, it was tried to determine the deteriorations on the asphalt by selecting the data set obtained from a region with image processing methods and deep learning technique. With the action camera placed in an automobile, a total of 4315 asphalt images with various distortions and without any deterioration were used as dataset. The dataset was classified using a pixel-based Faster Region-based Convolutional Neural Network. Accuracy, precision and sensitivity values were used to make the performance result obtained as a result of classification meaningful. With this proposed method, the average accuracy rate was 93.2%. With these results, an approach that can automatically detect asphalt deterioration in smart city structures has been developed.

show abstract

“…These features are passed to a fully connected layer with a nonlinear function that gives the probability distribution over each target class. CNNs have been used in the area of traffic prediction ( 15 , 16 ), transportation safety analysis ( 17 , 18 ), and pavement distress recognition ( 19 , 20 ).…”

Section: Methodsmentioning

confidence: 99%

Detection of Pavement Maintenance Treatments using Deep-Learning Network

Gao

Yao

Ren

et al. 2021

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

Pavement maintenance and rehabilitation (M&R) records are important as they provide documentation that M&R treatment is being performed and completed appropriately. Moreover, the development of pavement performance models relies heavily on the quality of the condition data collected and on the M&R records. However, the history of pavement M&R activities is often missing or unavailable to highway agencies for many reasons. Without accurate M&R records, it is difficult to determine if a condition change between two consecutive inspections is the result of M&R intervention, deterioration, or measurement errors. In this paper, we employed deep-learning networks of a convolutional neural network (CNN) model, a long short-term memory (LSTM) model, and a CNN-LSTM combination model to automatically detect if an M&R treatment was applied to a pavement section during a given time period. Unlike conventional analysis methods so far followed, deep-learning techniques do not require any feature extraction. The maximum accuracy obtained for test data is 87.5% using CNN-LSTM.

show abstract

Faster region convolutional neural network for automated pavement distress detection

Cited by 88 publications

References 27 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

Faster R-CNN Structure for Computer Vision-based Road Pavement Distress Detection

Detection of Pavement Maintenance Treatments using Deep-Learning Network

Contact Info

Product

Resources

About