Pavement crack detection is a critical task that is essential to ensure the safety of roads and highways. Accurate detection and classification of pavement cracks can help transportation agencies to identify potential maintenance needs and plan appropriate interventions. In this project, we propose a staged deep learning classifier approach for pavement crack detection to provide accurate and comprehensive information about the pavement condition. In this proposed pavement crack detection model, there are four main phases: pre-processing, feature extraction, feature selection, and crack detection. Firstly, raw images are pre-processed through median filtering and histogram equalization for noise removal and contrast enhancement. Next, features such as the improved local binary pattern, gray-level co-occurrence matrix, and gray-level run length matrix are extracted from the pre-processed images. The optimal features are selected using a hybrid optimization model, the tuna customized honey badger optimization algorithm, which combines the honey badger algorithm and tuna swarm optimization. This new hybrid optimization model will enhance the search strategy for solving optimization problems. The loss function of an augmented convolutional neural network (A-CNN) is modified to compute the root mean square error instead of the entropy-based loss function. The final detected outcomes (presence or absence of cracks) are acquired from the A-CNN.
Pavement Distress Detection Based on the Staged Deep Learning Classifier Approach
Transportation Research Record: Journal of the Transportation Research Board
Transportation Research Record: Journal of the Transportation Research Board ; 2679 , 2 ; 1015-1033
2024-10-10
Article (Journal)
Electronic Resource
English
Image-Based Expert-System Approach to Distress Detection on CRC Pavement
British Library Online Contents | 1994
|Image-Based Expert-System Approach to Distress Detection on CRC Pavement
Online Contents | 1994
|Wavelet-Based Pavement Distress Classification
Transportation Research Record | 2005
|