A Review of Road Surface Anomaly Detection and Classification Systems Based on Vibration-Based Techniques

Abstract

Road surfaces suffer from sources of deterioration, such as weather conditions, constant usage, loads, and the age of the infrastructure. These sources of decay generate anomalies that could cause harm to vehicle users and pedestrians and also develop a high cost to repair the irregularities. These drawbacks have motivated the development of systems that automatically detect and classify road anomalies. This study presents a narrative review focused on road surface anomaly detection and classification based on vibration-based techniques. Three methodologies were surveyed: threshold-based methods, feature extraction techniques, and deep learning techniques. Furthermore, datasets, signals, preprocessing steps, and feature extraction techniques are also presented. The results of this review show that road surface anomaly detection and classification performed through vibration-based methods have achieved relatively high performance. However, there are challenges related to the reproduction and heterogeneity of the results that have been reported that are influenced by the limited testing conditions, sample size, and lack of publicly available datasets. Finally, there is potential to standardize the features computed through the time or frequency domains and evaluate and compare the diverse set of settings of time-frequency methods used for feature extraction and signal representation.

Evaluation of data representation techniques for vibration based road surface condition classification

“…Road surface quality significantly impacts vehicle safety, driving comfort, and maintenance costs. Vibration sensors mounted on vehicles offer a promising approach for non-destructive road condition assessment 3 , 6 , 7 . Several studies have explored the use of vibration sensors for road surface condition monitoring.…”

“…Vibration data often requires preprocessing steps like noise filtering and smoothing techniques to improve its quality and consistency before feeding it into machine learning models. These techniques help to remove irrelevant information and ensure features are on a similar scale for effective learning 1 , 11 , 13 . Due to the varying lengths of road sections with different surface conditions, raw vibration data is often segmented into windows for analysis.…”

“…Regarding classification approaches, machine learning algorithms play a vital role in classifying road surface types based on the extracted features. There are three main approaches to classifying road surface conditions based on vibration data: Rule-based methods, traditional machine learning-based methods, and deep learning-based methods 1 . Initially, early Rule-based approaches relied on various thresholds to detect road anomalies by setting predefined thresholds for signal characteristics like amplitude 1 .…”

“…There are three main approaches to classifying road surface conditions based on vibration data: Rule-based methods, traditional machine learning-based methods, and deep learning-based methods 1 . Initially, early Rule-based approaches relied on various thresholds to detect road anomalies by setting predefined thresholds for signal characteristics like amplitude 1 . These thresholds are typically determined based on prior knowledge or empirical data 3 .…”

“…Road surface deterioration due to climate change, frequent use, heavy loads, and aging infrastructure can cause harm to pedestrians, drivers, and vehicles 1 , 2 . Moreover, monitoring these deteriorations using traditional approaches often requires considerable time, effort, and resources, delaying necessary repairs and potentially leading to accidents 2 , 3 .…”