A deep learning approach to automatic road surface monitoring and pothole detection

Anomalies in road surface not only impact road quality but also affect driver safety, mechanic structure of the vehicles, and fuel consumption. Several approaches have been proposed to automatic monitoring of the road surface condition in order to assess road roughness and to detect potholes. Some o...

Full description

Saved in:
Bibliographic Details
Published in:Personal and ubiquitous computing 2020-08, Vol.24 (4), p.519-534
Main Authors: Varona, Braian, Monteserin, Ariel, Teyseyre, Alfredo
Format: Article
Language:English
Subjects:
Accelerometers
Anomalies
Artificial neural networks
Computer Science
Deep learning
Driver behavior
Drivers
Mobile Computing
Monitoring
Original Article
Personal Computing
Repair & maintenance
Road conditions
Road humps
Road surface
Smartphones
Surface properties
User Interfaces and Human Computer Interaction
Vehicle safety
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Anomalies in road surface not only impact road quality but also affect driver safety, mechanic structure of the vehicles, and fuel consumption. Several approaches have been proposed to automatic monitoring of the road surface condition in order to assess road roughness and to detect potholes. Some of these approaches adopt a crowdsensing perspective by using a built-in smartphone accelerometer to sense the road surface. Although the crowdsensing perspective has several advantages as ubiquitousness and low cost, it has certain sensibility to the false positives produced by man-made structures, driver actions, and road surface characteristics that cannot be considered as road anomalies. For this reason, we propose a deep learning approach that allows us (a) to automatically identify the different kinds of road surface, and (b) to automatically distinguish potholes from destabilizations produced by speed bumps or driver actions in the crowdsensing-based application context. In particular, we analyze and apply different deep learning models: convolutional neural networks, LSTM networks, and reservoir computing models. The experiments were carried out with real-world information, and the results showed a promising accuracy in solving both problems.
ISSN:1617-4909
1617-4917
DOI:10.1007/s00779-019-01234-z