Computer Vision‐Based Patched and Unpatched Pothole Classification Using Machine Learning Approach Optimized by Forensic‐Based Investigation Metaheuristic

Abstract

During the phase of periodic asphalt pavement survey, patched and unpatched potholes need to be accurately detected. This study proposes and verifies a computer vision-based approach for automatically distinguishing patched and unpatched potholes. Using two-dimensional images, patched and unpatched potholes may have similar shapes. Therefore, this study relies on image texture descriptors to delineate these two objects of interest. The texture descriptors of statistical measurement of color channels, the gray-level cooccurrence matrix, and the local ternary pattern are used to extract texture information from image samples of asphalt pavement roads. To construct a classification model based on the extracted texture-based dataset, this study proposes and validates an integration of the Support Vector Machine Classification (SVC) and the Forensic-Based Investigation (FBI) metaheuristic. The SVC is used to generalize a classification boundary that separates the input data into two class labels of patched and unpatched potholes. To optimize the SVC performance, the FBI algorithm is utilized to fine-tune the SVC hyperparameters. To establish the hybrid FBI-SVC framework, an image dataset consisting of 600 samples has been collected. The experiment supported by the Wilcoxon signed-rank test demonstrates that the proposed computer vision is highly suitable for the task of interest with a classification accuracy rate = 94.833%.

A Novel Approach for Detection of Pavement Crack and Sealed Crack Using Image Processing and Salp Swarm Algorithm Optimized Machine Learning

“…us, this finding complies with results reported in recent studies that utilize hybrid computing models in civil engineering [119][120][121][122][123][124][125]. Although SSA has been demonstrated to be an effective swarm intelligent method used for solving various complex optimization tasks Houssein et al 2020; [76,126,127], its application in constructing sophisticated computer vision-based systems is still rare.…”

Pothole and Plain Road Classification Using Adaptive Mutation Dipper Throated Optimization and Transfer Learning for Self Driving Cars

“…Detection was made using nonlinear SVM. For the purpose of training an SVM that can recognize potholes in annotated photographs, authors in [43] (FBI) metaheuristic, Authors in [44] achieved a 94.83% success rate in pothole detection. Experts must manually extract features to support the machine learning approach's high processing power in order to increase pothole detection accuracy.…”

Smart Pothole Detection Using Deep Learning Based on Dilated Convolution

“…There are various research efforts to automate the pothole detection process in roads using different approaches: sensor-based techniques [8][9][10][11][12], 3D reconstruction techniques (laser-based [13][14][15] and stereo vision-based [16][17][18][19][20]), image processing techniques [21][22][23][24][25][26][27][28], and model-based (machine-learning techniques and deep learning techniques) [29][30][31][32][33][34][35][36][37]. Senor-based techniques use vibration sensors to detect potholes.…”

“…Hoang [31] used least squares SVM and neural network with steerable filter-based feature extraction and achieved a pothole detection accuracy rate of roughly 89%. Recently, Hoang et al [32] integrated the SVM and the forensic-based investigation (FBI) metaheuristic to optimize the detection accuracy, and their experiments achieved an accuracy of 94.833% for detecting potholes. The stated machine learning approach achieved significant accuracy, although they encountered the following challenges: (1) manual feature extraction must be performed by experts to improve the accuracy performance during the pothole detection process, and (2) they required high computational power, which are not feasible to be used by drivers in their devices.…”