Research Article
Edge AI-Based Automated Detection and Classification of Road
Anomalies in VANET Using Deep Learning
Rozi Bibi,
1
Yousaf Saeed,
1
Asim Zeb,
2
Taher M. Ghazal,
3,4
Taj Rahman,
5
Raed A. Said,
6
Sagheer Abbas ,
7
Munir Ahmad ,
7
and Muhammad Adnan Khan
8
1
Department of Information Technology, e University of Haripur, Haripur, Pakistan
2
Department of Computer Science, Abbottabad University of Science and Technology, Havelian, Pakistan
3
Center for Cyber Security, Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia (UKM),
43600 Bangi, Selangor, Malaysia
4
School of Information Technology, Skyline University College, University City Sharjah, 1797 Sharjah, UAE
5
Department of Physical & Numerical Science, Qurtuba University of Science & Information Technology,
Peshawar 25000, Pakistan
6
Canadian University Dubai, Dubai, UAE
7
School of Computer Science, National College of Business Administration and Economics, Lahore 54000, Pakistan
8
Pattern Recognition and Machine Learning Lab, Department of Software, Gachon University, Seongnam 13120,
Republic of Korea
CorrespondenceshouldbeaddressedtoMunirAhmad;munir@ncbae.edu.pkandMuhammadAdnanKhan;adnan@gachon.ac.kr
Received 14 June 2021; Accepted 7 September 2021; Published 29 September 2021
Academic Editor: Amparo Alonso-Betanzos
Copyright © 2021 Rozi Bibi et al. is is an open access article distributed under the Creative Commons Attribution License,
which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Road surface defects are crucial problems for safe and smooth traffic flow. Due to climate changes, low quality of construction
material, large flow of traffic, and heavy vehicles, road surface anomalies are increasing rapidly. Detection and repairing of these
defects are necessary for the safety of drivers, passengers, and vehicles from mechanical faults. In this modern era, autonomous
vehicles are an active research area that controls itself with the help of in-vehicle sensors without human commands, especially
after the emergence of deep learning (DNN) techniques. A combination of sensors and DNN techniques can be useful for
unmanned vehicles for the perception of their surroundings for the detection of tracks and obstacles for smooth traveling based on
the deployment of artificial intelligence in vehicles. One of the biggest challenges for autonomous vehicles is to avoid the critical
road defects that may lead to dangerous situations. To solve the accident issues and share emergency information, the Intelligent
Transportation System (ITS) introduced the concept of vehicular network termed as vehicular ad hoc network (VANET) for
achieving security and safety in a traffic flow. A novel mechanism is proposed for the automatic detection of road anomalies by
autonomous vehicles and providing road information to upcoming vehicles based on Edge AI and VANET. Road images captured
via camera and deployment of the trained model for road anomaly detection in a vehicle could help to reduce the accident rate and
risk of hazards on poor road conditions. e techniques Residual Convolutional Neural Network (ResNet-18) and Visual
Geometry Group (VGG-11) are applied for the automatic detection and classification of the road with anomalies such as a pothole,
bump, crack, and plain roads without anomalies using the dataset from different online sources. e results show that the applied
models performed well than other techniques used for road anomalies identification.
1. Introduction
In our daily life, road conditions play an important role.
Road pavement irregularities can lead to mechanical failure
of vehicles and may cause accidents. Poor road conditions
also affect the comfort of drivers and passengers and increase
stress levels [1]. According to World Health Organization
(WHO) 2018 report survey, every year 1.35 million people
lose their lives in road accidents. e rate of road mortality
in low- and middle-income countries having 60% of the
Hindawi
Computational Intelligence and Neuroscience
Volume 2021, Article ID 6262194, 16 pages
https://doi.org/10.1155/2021/6262194