<p class="Abstract">This study presents characterization of cracking in pavement distress using image processing techniques and <em>k</em>-nearest neighbour (kNN) classifier. The proposed semi-automated detection system for characterization on pavement distress anticipated to minimize the human supervision from traditional surveys and reduces cost of maintenance of pavement distress. The system consists of 4 stages which are image acquisition, image processing, feature extraction and classification. Firstly, a tool for image acquisition, consisting of digital camera, camera holder and tripod, is developed to capture images of pavement distress. Secondly, image processing techniques such as image thresholding, median filter, image erosion and image filling are applied. Thirdly, two features that represent the length of pavement cracking in <em>x</em> and <em>y</em> coordinate system namely <em>delta_x</em> and <em>delta_y</em> are computed. Finally, the computed features is fed to a kNN classifier to build its committee and further used to classify the pavement cracking into two types; transverse and longitudinal cracking. The performance of kNN classifier in classifying the type of pavement cracking is also compared with a modified version of kNN called fuzzy kNN classifier. Based on the results from images analysis, the semi-automated image processing system is able to consistently characterize the crack pattern with accuracy up to 90%. The comparison of analysed data with field data shows good agreement in the pavement distress characterization. Thus the encouraging results of semi-automated image analysis system will be useful for developing a more efficient road maintenance process.</p>
Asphalt cracks are one of the major road damage problems in civil field as it may potentially threaten the road and highway safety. Crack detection and classification is a challenging task because complicated pavement conditions due to the presence of shadows, oil stains and water spot will result in poor visual and low contrast between cracks and the surrounding pavement. In this paper, the network proposed a fully automated crack detection and classification using deep convolution neural network (DCNN) architecture. First, the image of pavement cracks manually prepared in RGB format with dimension of 1024x768 pixels, captured using NIKON digital camera. Next, the image will segmented into patches (32x32 pixels) as a training dataset from the original pavement cracks and trained DCNN with two different filter sizes: 3x3 and 5x5. The proposed method has successfully detected the presence of crack in the images with 98%, 99% and 99% of recall, precision and accuracy respectively. The network was also able to automatically classify the pavement cracks into no cracks, transverse, longitudinal and alligator with acceptable classification accuracy for both filter sizes. There was no significant different in classification accuracy between the two different filters. However, smaller filter size need more processing training time compared to the larger filter size. Overall, the proposed method has successfully achieved accuracy of 94.5% in classifying different types of crack.
Effective road maintenance program is vital to ensure traffic safety, serviceability, and prolong the life span of the road. Maintenance will be carried out on pavements when signs of degradation begin to appear and delays may also lead to increased maintenance costs in the future, when more severe changes may be required. In Malaysia, manual visual observation is practiced in the inspection of distressed pavements. Nonetheless, this method of inspection is ineffective as it is more laborious, time consuming and poses safety hazard. This study focuses in utilizing an Artificial Intelligence (AI) method to automatically classify pavement crack severity. Field data collection was conducted to allow meaningful verification of accuracy and reliability of the crack’s severity prediction based on AI. Several important phases are required in research methodology processes including data collection, image labelling, image resizing, image enhancement, deep convolution neural network (DCNN) training and performance evaluation. Throughout the analysis of image processing results, the image output was successfully classified using MATLAB software. The good agreement between field measurement data and DCNN prediction of crack’s severity proved the reliability of the system. In conclusion, the established method can classify the crack’s severity based on the JKR guideline of visual assessment.
Detection of crack on asphalt pavement is an essential task of monitoring and regulatory inspection. Currently, this task is conducted manually by surveyor or human inspectors for further maintenance works. Manual practice would lead some drawback such as time-consuming, labour intensive, hazardous and also subjective valuation for different individual. To overcome this deficit circumstances an automated technique is implemented. The objective of this study is to develop an intelligent system to detect pavement crack using Deep Convolutional Neural Network (DCNN). This study consists of several procedures which is started with collecting pavement crack images using online and from own developed dataset. The images are pre-processed by resizing the image into desire dimensions. Next, small patches are extracted as inputs to ease of detection and reduce classifier burden. The images further be labelled into two (2) types which is crack and non-crack. In this study, it is utilized Python environment and Keras framework to establish DCNN model. 80% of dataset is used for training set to train, while another 20% is used for testing set to test the model in order to evaluate the performance in terms of accuracy, precision and recall and F1 score. This proposed model is compared on different patch sizes, training algorithms and architectures to get the best classification. Thus, an automated system that able to accurately detect the present of crack in pavement images within speedy computation is successfully developed. To conclude, the system can be used to assist the surveyor or human operator in task of crack detection, so that the process of detection can be done faster and more efficient. This will help in reducing cost of maintenance and enhancing safety of road users.
In an image classification system based on deep learning, a training dataset is a set of labelled images and is often composed of a large number of images. Image labelling tool is usually used to facilitate in creating the training dataset used by the classifier during the learning phase. This paper presents a new image labelling tool called CrackLabel that can automatically label the cracks in the asphalt pavement images. A specially designed image thresholding method called the Global and Lower Quartile Average Intensity (GLQAI) method is utilised. In this study, the training dataset is developed by using real pavement images that resized to 1024×768 resolution. First, crack images are automatically segmented into 768 small patches with 32×32 resolution (pixel). Then, a threshold-based method is applied to automatically segment these patches into two classes which are crack and non-crack patches. The image thresholding method based on the average of global average intensity (GAI) and lower quartile intensity (LQI), namely GLQAI is proposed for this task. Next, the labelling process is performed by assigning patches associated with the crack and background into the crack and non-crack folder, respectively. Finally, the performance of CrackLabel is benchmarked by comparing the results with the manual label crack images by human experts, and three commonly used thresholding methods; Otsu, Kapur and Kittler-Illingworth thresholding. Experimental results show that the proposed thresholding method achieved the best classification rate among various thresholding methods with 94.50%, 93.60% 94.00% and 94.05% for recall, precision, accuracy, and F-score respectively. In conclusion, it is observed that the proposed method using the newly threshold algorithm is very effective in label images into the crack and non-crack patches to maximize the training performance.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.